Researcher profile

Rui Wang

Rui Wang contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author

187works

0followers

60topics

4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

Federated Cross-Client Subgraph Pattern Detection

Subgraph pattern detection aims to uncover complex interaction structures in graphs. However, state-of-the-art graph neural network (GNN)-based solutions assume centralized access to the entire graph. When graphs are instead distributed across multiple parties, client-local GNN computations diverge from those of a centralized model, resulting in a representation-equivalence gap. We formalize this as a structural observability problem, where subgraph patterns crossing partition boundaries become locally unidentifiable. To bridge this gap, we propose a per-step, layer-wise embedding exchange framework in which clients synchronize intermediate node representations at each layer of the forward pass, without exposing raw features or labels. Under an extended-subgraph assumption and shared model parameters across clients, this framework recovers the same node representations as a centralized GNN over the full graph. Experiments on synthetic directed multigraphs with cycles, bicliques, and scatter-gather patterns show that embedding exchange and federated parameter aggregation are complementary rather than interchangeable: their combination recovers most of the representation gap, provided exchanged embeddings are fresh per-step rather than stale per-epoch.

preprint2026arXiv

Large-Small Model Collaboration for Farmland Semantic Change Detection

Farmland Semantic Change Detection (SCD) is essential for cultivated land protection, yet existing benchmarks and models remain insufficient for fine-grained farmland conversion monitoring. Current datasets often lack dedicated "from-to" annotations, while visual change detection models are easily disturbed by phenology-induced pseudo-changes caused by crop rotation, seasonal variation, and illumination differences. To address these challenges, we construct HZNU-FCD, a large-scale fine-grained farmland SCD benchmark with a unified five-class farmland-to-non-farmland annotation protocol. It contains 4,588 bitemporal image pairs with pixel-level labels for practical farmland protection. Based on this benchmark, we propose a large-small collaborative SCD framework that integrates a task-driven small visual model with a frozen large vision-language model. The small model, Fine-grained Difference-aware Mamba (FD-Mamba), learns dense change representations for boundary preservation and small-region localization. The large-model pathway, Cross-modal Logical Arbitration (CMLA), introduces CLIP-based textual priors for prompt-guided semantic arbitration and pseudo-change suppression. To enable effective collaboration, we design a hard-region co-training strategy that supervises the CMLA semantic score map only on low-confidence pixels. Experiments show that our method achieves 97.63% F1, 96.32% IoU, and 96.35% SCD_IoU_mean on HZNU-FCD with only 6.65M trainable parameters. Compared with the multimodal ChangeCLIP-ViT, which leverages vision-language information for change detection, our method improves F1 by 10.19 percentage points on HZNU-FCD. It also achieves 91.43% F1 and 84.21% IoU on LEVIR-CD, and 93.85% F1 and 88.41% IoU on WHU-CD, demonstrating strong robustness and generalization. The code is available at https://github.com/Lovelymili/FD-Mamba.

preprint2026arXiv

PrepBench: How Far Are We from Natural-Language-Driven Data Preparation?

Data preparation is a central and time-consuming stage in data analysis workflows. Traditionally, commercial tools have relied on graphical user interfaces (GUIs) to simplify data preparation, allowing users to define transformations through visual operators and workflows. Recent advances in large language models (LLMs) raise the possibility of a paradigm shift toward natural language (NL)-driven data preparation, in which users can specify preparation intents in NL directly. However, it remains unclear how far current LLM-based agents are from this paradigm shift in practice. Existing code generation benchmarks do not capture key characteristics of data preparation, including ambiguous user intents, imperfect real-world data, and the need to translate code into interpretable workflows for validation. To bridge this gap, we present PrepBench, a benchmark designed to evaluate NL-driven data preparation along three core capabilities: interactive disambiguation, prep-code generation, and code-to-workflow translation. We crawl data from the Preppin' Data Challenges, and then extend it into a systematically designed benchmark. The benchmark covers diverse domains, and each task involves 3 to 18 data preparation steps. Nearly half of the tasks require over 100 lines of Python code, and the longest solutions approach 300 lines. Our evaluation shows that, despite recent progress, realizing this paradigm shift remains challenging for state-of-the-art LLMs. PrepBench provides a principled benchmark for measuring this gap and helps identify key challenges toward realizing NL-driven data preparation.

preprint2026arXiv

SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning

Frontier scientific reasoning is rapidly emerging as a key foundation for advancing AI agents in automated scientific discovery. Deep research agents offer a promising approach to this challenge. These models develop robust problem-solving capabilities through post-training on information-seeking tasks, which are typically curated via knowledge graph construction or iterative web browsing. However, these strategies face inherent limitations in frontier science, where domain-specific knowledge is scattered across sparse and heterogeneous academic sources, and problem solving requires sophisticated computation and reasoning far beyond factual recall. To bridge this gap, we introduce SciResearcher, a fully automated agentic framework for frontier-science data construction. SciResearcher synthesizes diverse conceptual and computational tasks grounded in academic evidence, while eliciting information acquisition, tool-integrated reasoning, and long-horizon capabilities. Leveraging the curated data for supervised fine-tuning and agentic reinforcement learning, we develop SciResearcher-8B, an agent foundation model that achieves 19.46% on the HLE-Bio/Chem-Gold benchmark, establishing a new state of the art at its parameter scale and surpassing several larger proprietary agents. It further achieves 13-15% absolute gains on SuperGPQA-Hard-Biology and TRQA-Literature benchmarks. Overall, SciResearcher introduces a new paradigm for automated data construction for frontier scientific reasoning and offers a scalable path toward future scientific agents.

preprint2026arXiv

TouchMap-OR: Multi-View 3D Mapping of Hand-Surface Contacts

Hand-surface interactions between clinicians, patients, and medical equipment play a central role in pathogen transmission during medical procedures. However, these interactions remain largely unobserved, as current infection-prevention practices rely on manual observation and cannot reconstruct detailed contact histories. In this work we formulate the problem of identity-resolved hand-surface interaction reconstruction in operating rooms and introduce TouchMap-OR, a multi-view RGB-D vision system that models clinicians, articulated hand geometry, and the semantic structure of the clinical environment to infer when and where contacts occur. The system reconstructs globally consistent multi-person 3D skeleton tracks across cameras while estimating articulated MANO hand meshes from RGB observations aligned to depth data. Multi-view hand reconstructions are fused and associated with tracked clinicians to obtain consistent left and right hand trajectories. A semantic 3D model of the operating room is built from multi-view segmentation and depth fusion, enabling reconstructed hand trajectories to be mapped to specific surfaces, including medical equipment, movable objects, and patient body sites. Temporal hand-surface proximity is used to infer contact episodes describing which clinician touched which surface and when. We evaluate TouchMap-OR on recordings from three real anesthesia inductions with manually annotated contact events. TouchMap-OR achieves 0.75 binary contact F1, outperforming tracking-based baselines while maintaining comparable multi-person tracking accuracy and achieving 0.96 identity attribution accuracy.

preprint2026arXiv

Towards Backdoor-Based Ownership Verification for Vision-Language-Action Models

Vision-Language-Action models (VLAs) support generalist robotic control by enabling end-to-end decision policies directly from multi-modal inputs. As trained VLAs are increasingly shared and adapted, protecting model ownership becomes essential for secure deployment and responsible open-source usage. In this paper, we present GuardVLA, the first backdoor-based ownership verification framework specifically designed for VLAs. GuardVLA embeds a stealthy and harmless backdoor watermark into the protected model during training by injecting secret messages into embodied visual data. For post-release verification, we propose a swap-and-detect mechanism, in which the trigger projector and an external classifier head are used to activate and detect the embedded backdoor based on prediction probabilities. Extensive experiments across multiple datasets, model architectures, and adaptation settings demonstrate that GuardVLA enables reliable ownership verification while preserving benign task performance. Further results show that the embedded watermark remains detectable under post-release model adaptation.

preprint2025arXiv

Decoupling Constraint from Two Direction in Evolutionary Constrained Multi-objective Optimization

Real-world Constrained Multi-objective Optimization Problems (CMOPs) often contain multiple constraints, and understanding and utilizing the coupling between these constraints is crucial for solving CMOPs. However, existing Constrained Multi-objective Evolutionary Algorithms (CMOEAs) typically ignore these couplings and treat all constraints as a single aggregate, which lacks interpretability regarding the specific geometric roles of constraints. To address this limitation, we first analyze how different constraints interact and show that the final Constrained Pareto Front (CPF) depends not only on the Pareto fronts of individual constraints but also on the boundaries of infeasible regions. This insight implies that CMOPs with different coupling types must be solved from different search directions. Accordingly, we propose a novel algorithm named Decoupling Constraint from Two Directions (DCF2D). This method periodically detects constraint couplings and spawns an auxiliary population for each relevant constraint with an appropriate search direction. Extensive experiments on seven challenging CMOP benchmark suites and on a collection of real-world CMOPs demonstrate that DCF2D outperforms five state-of-the-art CMOEAs, including existing decoupling-based methods.

preprint2024arXiv

Observation and manipulation of quantum interference in a superconducting Kerr parametric oscillator

Quantum tunneling is the phenomenon that makes superconducting circuits "quantum". Recently, there has been a renewed interest in using quantum tunneling in phase space of a Kerr parametric oscillator as a resource for quantum information processing. Here, we report a direct observation of quantum interference induced by such tunneling in a planar superconducting circuit through Wigner tomography. We experimentally elucidate all essential properties of this quantum interference, such as mapping from Fock states to cat states, a temporal oscillation due to the pump detuning, as well as its characteristic Rabi oscillations and Ramsey fringes. Finally, we perform gate operations as manipulations of the observed quantum interference. Our findings lay the groundwork for further studies on quantum properties of superconducting Kerr parametric oscillators and their use in quantum information technologies.

preprint2024arXiv

Phase Transition Study meets Machine Learning

In recent years, machine learning (ML) techniques have emerged as powerful tools for studying many-body complex systems, and encompassing phase transitions in various domains of physics. This mini review provides a concise yet comprehensive examination of the advancements achieved in applying ML to investigate phase transitions, with a primary focus on those involved in nuclear matter studies.

preprint2024arXiv

Structured Learning in Time-dependent Cox Models

Cox models with time-dependent coefficients and covariates are widely used in survival analysis. In high-dimensional settings, sparse regularization techniques are employed for variable selection, but existing methods for time-dependent Cox models lack flexibility in enforcing specific sparsity patterns (i.e., covariate structures). We propose a flexible framework for variable selection in time-dependent Cox models, accommodating complex selection rules. Our method can adapt to arbitrary grouping structures, including interaction selection, temporal, spatial, tree, and directed acyclic graph structures. It achieves accurate estimation with low false alarm rates. We develop the sox package, implementing a network flow algorithm for efficiently solving models with complex covariate structures. sox offers a user-friendly interface for specifying grouping structures and delivers fast computation. Through examples, including a case study on identifying predictors of time to all-cause death in atrial fibrillation patients, we demonstrate the practical application of our method with specific selection rules.

preprint2023arXiv

A Theory of Human-Like Few-Shot Learning

We aim to bridge the gap between our common-sense few-sample human learning and large-data machine learning. We derive a theory of human-like few-shot learning from von-Neuman-Landauer's principle. modelling human learning is difficult as how people learn varies from one to another. Under commonly accepted definitions, we prove that all human or animal few-shot learning, and major models including Free Energy Principle and Bayesian Program Learning that model such learning, approximate our theory, under Church-Turing thesis. We find that deep generative model like variational autoencoder (VAE) can be used to approximate our theory and perform significantly better than baseline models including deep neural networks, for image recognition, low resource language processing, and character recognition.

preprint2023arXiv

An Indoor Environment Sensing and Localization System via mmWave Phased Array

An indoor layout sensing and localization system in 60GHz millimeter wave (mmWave) band, named mmReality, is elaborated in this paper. The mmReality system consists of one transmitter and one mobile receiver, each with a phased array and a single radio frequency (RF) chain. To reconstruct the room layout, the pilot signal is delivered from the transmitter to the receiver via different pairs of transmission and receiving beams, so that the signals at all antenna elements can be resolved. Then, the spatial smoothing and two-dimensional multiple signal classification (MUSIC) algorithm is applied to detect the angle-of-arrival (AoAs) and angle-of-departure (AoDs) of the rays from the transmitter to the receiver. Moreover, the technique of multi-carrier ranging is adopted to measure the distance of each propagation path. Synthesizing the above geometrical parameters, the location of receiver relative to the transmitter can be pinpointed, both line-of-sight (LoS) and non-line-of-sight (NLoS) paths can also be determined. Therefore, the room layout can be reconstructed by moving the receiver and repeating the above measurement in different locations of the room. At the end, we show that the reconstructed room layout can be utilized to locate a mobile device according to its AoA spectrum, even with single access point.

preprint2023arXiv

Boosting Large Language Model for Speech Synthesis: An Empirical Study

Large language models (LLMs) have made significant advancements in natural language processing and are concurrently extending the language ability to other modalities, such as speech and vision. Nevertheless, most of the previous work focuses on prompting LLMs with perception abilities like auditory comprehension, and the effective approach for augmenting LLMs with speech synthesis capabilities remains ambiguous. In this paper, we conduct a comprehensive empirical exploration of boosting LLMs with the ability to generate speech, by combining pre-trained LLM LLaMA/OPT and text-to-speech synthesis model VALL-E. We compare three integration methods between LLMs and speech synthesis models, including directly fine-tuned LLMs, superposed layers of LLMs and VALL-E, and coupled LLMs and VALL-E using LLMs as a powerful text encoder. Experimental results show that, using LoRA method to fine-tune LLMs directly to boost the speech synthesis capability does not work well, and superposed LLMs and VALL-E can improve the quality of generated speech both in speaker similarity and word error rate (WER). Among these three methods, coupled methods leveraging LLMs as the text encoder can achieve the best performance, making it outperform original speech synthesis models with a consistently better speaker similarity and a significant (10.9%) WER reduction.

preprint2023arXiv

On the nature of overcharging and charge inversion in electrical double layers

Understanding overcharging and charge inversion is one of the long-standing challenges in soft matter and biophysics. To study these phenomena, we employ the modified Gaussian renormalized fluctuation theory, which allows for the self-consistent accounting of spatially varying ionic strength, as well as the spatial variations in dielectric permittivity and excluded volume effects. The underlying dependence of overcharging on the electrostatic coupling is elucidated by varying surface charge, counterion valency, and dielectric contrast. Consistent with simulations, three characteristic regimes corresponding to weak, moderate, and strong coupling are identified. Important features like the inversion of zeta potential, crowding and ionic layering at the surface are successfully captured. For weak coupling, there is no overcharging. In the moderate coupling regime, overcharging increases with surface charge. Finally, in the strong coupling regime, ionic crowding and saturation in overcharging are observed. Our theory predicts non-monotonic dependence of charge inversion on multivalent salt concentration as well as the addition of monovalent salt, in quantitative agreement with experiments.

preprint2023arXiv

PACO: Parts and Attributes of Common Objects

Object models are gradually progressing from predicting just category labels to providing detailed descriptions of object instances. This motivates the need for large datasets which go beyond traditional object masks and provide richer annotations such as part masks and attributes. Hence, we introduce PACO: Parts and Attributes of Common Objects. It spans 75 object categories, 456 object-part categories and 55 attributes across image (LVIS) and video (Ego4D) datasets. We provide 641K part masks annotated across 260K object boxes, with roughly half of them exhaustively annotated with attributes as well. We design evaluation metrics and provide benchmark results for three tasks on the dataset: part mask segmentation, object and part attribute prediction and zero-shot instance detection. Dataset, models, and code are open-sourced at https://github.com/facebookresearch/paco.

preprint2023arXiv

Universal Multimodal Representation for Language Understanding

Representation learning is the foundation of natural language processing (NLP). This work presents new methods to employ visual information as assistant signals to general NLP tasks. For each sentence, we first retrieve a flexible number of images either from a light topic-image lookup table extracted over the existing sentence-image pairs or a shared cross-modal embedding space that is pre-trained on out-of-shelf text-image pairs. Then, the text and images are encoded by a Transformer encoder and convolutional neural network, respectively. The two sequences of representations are further fused by an attention layer for the interaction of the two modalities. In this study, the retrieval process is controllable and flexible. The universal visual representation overcomes the lack of large-scale bilingual sentence-image pairs. Our method can be easily applied to text-only tasks without manually annotated multimodal parallel corpora. We apply the proposed method to a wide range of natural language generation and understanding tasks, including neural machine translation, natural language inference, and semantic similarity. Experimental results show that our method is generally effective for different tasks and languages. Analysis indicates that the visual signals enrich textual representations of content words, provide fine-grained grounding information about the relationship between concepts and events, and potentially conduce to disambiguation.

preprint2023arXiv

Workload Failure Prediction for Data Centers

Failed workloads that consumed significant computational resources in time and space affect the efficiency of data centers significantly and thus limit the amount of scientific work that can be achieved. While the computational power has increased significantly over the years, detection and prediction of workload failures have lagged far behind and will become increasingly critical as the system scale and complexity further increase. In this study, we analyze workload traces collected from a production cluster and train machine learning models on a large amount of data sets to predict workload failures. Our prediction models consist of a queue-time model that estimates the probability of workload failures before execution and a runtime model that predicts failures at runtime. Evaluation results show that the queue-time model and runtime model can predict workload failures with a maximum precision score of 90.61% and 97.75%, respectively. By integrating the runtime model with the job scheduler, it helps reduce CPU time, and memory usage by up to 16.7% and 14.53%, respectively.

preprint2022arXiv

A new class of bilayer kagome lattice compounds with Dirac nodal lines and pressure-induced superconductivity

Kagome lattice composed of transition-metal ions provides a great opportunity to explore the intertwining between geometry, electronic orders and band topology. The discovery of multiple competing orders that connect intimately with the underlying topological band structure in nonmagnetic kagome metals $A$V$_3$Sb$_5$ ($A$ = K, Rb, Cs) further pushes this topic to the quantum frontier. Here we report the discovery and characterization of a new class of vanadium-based compounds with kagome bilayers, namely $A$V$_6$Sb$_6$ ($A$ = K, Rb, Cs) and V$_6$Sb$_4$, which, together with $A$V$_3$Sb$_5$, compose a series of kagome compounds with a generic chemical formula ($A_{m-1}$Sb$_{2m}$)(V$_3$Sb)$_n$ (m = 1, 2; n = 1, 2). Theoretical calculations combined with angle-resolved photoemission measurements reveal that these compounds feature Dirac nodal lines in close vicinity to the Fermi level. Pressure-induced superconductivity in $A$V$_6$Sb$_6$ further suggests promising emergent phenomena in these materials. The establishment of a new family of layered kagome materials paves the way for designer of fascinating kagome systems with diverse topological nontrivialities and collective ground states.

preprint2022arXiv

A novel method for data augmentation: Nine Dot Moving Least Square (ND-MLS)

Data augmentation greatly increases the amount of data obtained based on labeled data to save on expenses and labor for data collection and labeling. We present a new approach for data augmentation called nine-dot MLS (ND-MLS). This approach is proposed based on the idea of image defor-mation. Images are deformed based on control points, which are calculated by ND-MLS. The method can generate over 2000 images for one exist-ing dataset in a short time. To verify this data augmentation method, extensive tests were performed covering 3 main tasks of computer vision, namely, classification, detection and segmentation. The results show that 1) in classification, 10 images per category were used for training, and VGGNet can obtain 92% top-1 acc on the MNIST dataset of handwritten digits by ND-MLS. In the Omniglot dataset, the few-shot accuracy usu-ally decreases with the increase in character categories. However, the ND-MLS method has stable performance and obtains 96.5 top-1 acc in Res-Net on 100 different handwritten character classification tasks; 2) in segmentation, under the premise of only ten original images, DeepLab obtains 93.5%, 85%, and 73.3% m_IOU(10) on the bottle, horse, and grass test datasets, respectively, while the cat test dataset obtains 86.7% m_IOU(10) with the SegNet model; 3) with only 10 original images from each category in object detection, YOLO v4 obtains 100% and 97.2% bottle and horse detection, respectively, while the cat dataset obtains 93.6% with YOLO v3. In summary, ND-MLS can perform well on classification, object detec-tion, and semantic segmentation tasks by using only a few data.

preprint2022arXiv

A Study of Syntactic Multi-Modality in Non-Autoregressive Machine Translation

It is difficult for non-autoregressive translation (NAT) models to capture the multi-modal distribution of target translations due to their conditional independence assumption, which is known as the "multi-modality problem", including the lexical multi-modality and the syntactic multi-modality. While the first one has been well studied, the syntactic multi-modality brings severe challenge to the standard cross entropy (XE) loss in NAT and is under studied. In this paper, we conduct a systematic study on the syntactic multi-modality problem. Specifically, we decompose it into short- and long-range syntactic multi-modalities and evaluate several recent NAT algorithms with advanced loss functions on both carefully designed synthesized datasets and real datasets. We find that the Connectionist Temporal Classification (CTC) loss and the Order-Agnostic Cross Entropy (OAXE) loss can better handle short- and long-range syntactic multi-modalities respectively. Furthermore, we take the best of both and design a new loss function to better handle the complicated syntactic multi-modality in real-world datasets. To facilitate practical usage, we provide a guide to use different loss functions for different kinds of syntactic multi-modality.

preprint2022arXiv

Accelerating Edge Intelligence via Integrated Sensing and Communication

Realizing edge intelligence consists of sensing, communication, training, and inference stages. Conventionally, the sensing and communication stages are executed sequentially, which results in excessive amount of dataset generation and uploading time. This paper proposes to accelerate edge intelligence via integrated sensing and communication (ISAC). As such, the sensing and communication stages are merged so as to make the best use of the wireless signals for the dual purpose of dataset generation and uploading. However, ISAC also introduces additional interference between sensing and communication functionalities. To address this challenge, this paper proposes a classification error minimization formulation to design the ISAC beamforming and time allocation. The globally optimal solution is derived via the rank-1 guaranteed semidefinite relaxation, and performance analysis is performed to quantify the ISAC gain over that of conventional edge intelligence. Simulation results are provided to verify the effectiveness of the proposed ISAC-assisted edge intelligence system. Interestingly, we find that ISAC is always beneficial, when the duration of generating a sample is more than the duration of uploading a sample. Otherwise, the ISAC gain can vanish or even be negative. Nevertheless, we still derive a sufficient condition, under which a positive ISAC gain is feasible.

preprint2022arXiv

Accelerating Federated Edge Learning via Topology Optimization

Federated edge learning (FEEL) is envisioned as a promising paradigm to achieve privacy-preserving distributed learning. However, it consumes excessive learning time due to the existence of straggler devices. In this paper, a novel topology-optimized federated edge learning (TOFEL) scheme is proposed to tackle the heterogeneity issue in federated learning and to improve the communication-and-computation efficiency. Specifically, a problem of jointly optimizing the aggregation topology and computing speed is formulated to minimize the weighted summation of energy consumption and latency. To solve the mixed-integer nonlinear problem, we propose a novel solution method of penalty-based successive convex approximation, which converges to a stationary point of the primal problem under mild conditions. To facilitate real-time decision making, an imitation-learning based method is developed, where deep neural networks (DNNs) are trained offline to mimic the penalty-based method, and the trained imitation DNNs are deployed at the edge devices for online inference. Thereby, an efficient imitate-learning based approach is seamlessly integrated into the TOFEL framework. Simulation results demonstrate that the proposed TOFEL scheme accelerates the federated learning process, and achieves a higher energy efficiency. Moreover, we apply the scheme to 3D object detection with multi-vehicle point cloud datasets in the CARLA simulator. The results confirm the superior learning performance of the TOFEL scheme over conventional designs with the same resource and deadline constraints.

preprint2022arXiv

An approximate randomization test for high-dimensional two-sample Behrens-Fisher problem under arbitrary covariances

This paper is concerned with the problem of comparing the population means of two groups of independent observations. An approximate randomization test procedure based on the test statistic of Chen and Qin (2010) is proposed. The asymptotic behavior of the test statistic as well as the randomized statistic is studied under weak conditions. In our theoretical framework, observations are not assumed to be identically distributed even within groups. No condition on the eigenstructure of the covariance matrices is imposed. And the sample sizes of the two groups are allowed to be unbalanced. Under general conditions, all possible asymptotic distributions of the test statistic are obtained. We derive the asymptotic level and local power of the approximate randomization test procedure. Our theoretical results show that the proposed test procedure can adapt to all possible asymptotic distributions of the test statistic and always has correct test level asymptotically. Also, the proposed test procedure has good power behavior. Our numerical experiments show that the proposed test procedure has favorable performance compared with several alternative test procedures.

preprint2022arXiv

An Interactive Image-based Modeling System

This paper propose a interactive 3D modeling method and corresponding system based on single or multiple uncalibrated images. The main feature of this method is that, according to the modeling habits of ordinary people, the 3D model of the target is reconstructed from coarse to fine images. On the basis of determining the approximate shape, the user adds or modify projection constraints and spatial constraints, and apply topology modification, gradually realize camera calibration, refine rough model, and finally complete the reconstruction of objects with arbitrary geometry and topology. During the interactive process, the geometric parameters and camera projection matrix are solved in real time, and the reconstruction results are displayed in a 3D window.

preprint2022arXiv

Analysis of the distribution, rotation and scale characteristics of solar wind switchbacks: comparison between the first and second encounters of Parker Solar Probe

The S-shaped magnetic structure in the solar wind formed by the twisting of magnetic field lines is called a switchback, whose main characteristics are the reversal of the magnetic field and the significant increase in the solar wind radial velocity. We identify 242 switchbacks during the first two encounters of Parker Solar Probe (PSP). Statistics methods are applied to analyze the distribution and the rotation angle and direction of the magnetic field rotation of the switchbacks. The diameter of switchbacks is estimated with a minimum variance analysis (MVA) method based on the assumption of a cylindrical magnetic tube. We also make a comparison between switchbacks from inside and the boundary of coronal holes. The main conclusions are as follows: (1) the rotation angles of switchbacks observed during the first encounter seem larger than those of the switchbacks observed during the second encounter in general; (2) the tangential component of the velocity inside the switchbacks tends to be more positive (westward) than in the ambient solar wind; (3) switchbacks are more likely to rotate clockwise than anticlockwise, and the number of switchbacks with clockwise rotation is 1.48 and 2.65 times of those with anticlockwise rotation during the first and second encounters, respectively; (4) the diameter of switchbacks is about 10^5 km on average and across five orders of magnitude (10^3 -- 10^7 km).

preprint2022arXiv

Approximately Equivariant Networks for Imperfectly Symmetric Dynamics

Incorporating symmetry as an inductive bias into neural network architecture has led to improvements in generalization, data efficiency, and physical consistency in dynamics modeling. Methods such as CNNs or equivariant neural networks use weight tying to enforce symmetries such as shift invariance or rotational equivariance. However, despite the fact that physical laws obey many symmetries, real-world dynamical data rarely conforms to strict mathematical symmetry either due to noisy or incomplete data or to symmetry breaking features in the underlying dynamical system. We explore approximately equivariant networks which are biased towards preserving symmetry but are not strictly constrained to do so. By relaxing equivariance constraints, we find that our models can outperform both baselines with no symmetry bias and baselines with overly strict symmetry in both simulated turbulence domains and real-world multi-stream jet flow.

preprint2022arXiv

Beamforming Design and Performance Evaluation for Reconfigurable Intelligent Surface Assisted Wireless Communication Systems With Non-Ideal Hardware

Reconfigurable intelligent surface (RIS) can effectively control the wavefront of the impinging signals and has emerged as a cost-effective promising solution to improve the spectrum and energy efficiency of wireless systems. Most existing researches on RIS assume that the hardware operations are perfect. However, both physical transceiver and RIS suffer from inevitable hardware impairments in practice, which can lead to severe system performance degradation and increase the complexity of beamforming optimization. Consequently, the existing researches on RIS, including channel estimation, beamforming optimization, spectrum and energy efficiency analysis, etc., cannot directly apply to the case of hardware impairments. In this paper, by taking hardware impairments into consideration, we conduct the joint transmit and reflect beamforming optimization, and reevaluate the system performance. First, we characterize the closed-form estimators of direct and cascaded channels in both single-user and multi-user cases, and analyze the impact of hardware impairments on channel estimation accuracy. Then, the optimal transmit beamforming solution is derived, and a gradient descent method-based algorithm is also proposed to optimize the reflect beamforming. Moreover, we analyze the three types of asymptotic channel capacities with respect to the transmit power, the antenna number, and the reflecting element number. Finally, in terms of the system energy consumption, we analyze the power scaling law and the energy efficiency. Our experimental results also reveal an encouraging phenomenon that the RIS-assisted wireless system with massive reflecting elements can achieve both high spectrum and energy efficiency without the need for massive antennas and without allocating too many resources to optimize the reflect beamforming.

preprint2022arXiv

BEVT: BERT Pretraining of Video Transformers

This paper studies the BERT pretraining of video transformers. It is a straightforward but worth-studying extension given the recent success from BERT pretraining of image transformers. We introduce BEVT which decouples video representation learning into spatial representation learning and temporal dynamics learning. In particular, BEVT first performs masked image modeling on image data, and then conducts masked image modeling jointly with masked video modeling on video data. This design is motivated by two observations: 1) transformers learned on image datasets provide decent spatial priors that can ease the learning of video transformers, which are often times computationally-intensive if trained from scratch; 2) discriminative clues, i.e., spatial and temporal information, needed to make correct predictions vary among different videos due to large intra-class and inter-class variations. We conduct extensive experiments on three challenging video benchmarks where BEVT achieves very promising results. On Kinetics 400, for which recognition mostly relies on discriminative spatial representations, BEVT achieves comparable results to strong supervised baselines. On Something-Something-V2 and Diving 48, which contain videos relying on temporal dynamics, BEVT outperforms by clear margins all alternative baselines and achieves state-of-the-art performance with a 71.4\% and 87.2\% Top-1 accuracy respectively. Code will be made available at \url{https://github.com/xyzforever/BEVT}.

preprint2022arXiv

Bridging the Data Gap between Training and Inference for Unsupervised Neural Machine Translation

Back-translation is a critical component of Unsupervised Neural Machine Translation (UNMT), which generates pseudo parallel data from target monolingual data. A UNMT model is trained on the pseudo parallel data with translated source, and translates natural source sentences in inference. The source discrepancy between training and inference hinders the translation performance of UNMT models. By carefully designing experiments, we identify two representative characteristics of the data gap in source: (1) style gap (i.e., translated vs. natural text style) that leads to poor generalization capability; (2) content gap that induces the model to produce hallucination content biased towards the target language. To narrow the data gap, we propose an online self-training approach, which simultaneously uses the pseudo parallel data {natural source, translated target} to mimic the inference scenario. Experimental results on several widely-used language pairs show that our approach outperforms two strong baselines (XLM and MASS) by remedying the style and content gaps.

preprint2022arXiv

Buildup of the Magnetic Flux Ropes in Homologous Solar Eruptions

Homologous coronal mass ejections (CMEs) are an interesting phenomenon, and it is possible to investigate the formation of CMEs by comparing multi-CMEs under a homologous physical condition. AR 11283 had been present on the solar surface for several days when a bipole emerged on 2011 September 4. Its positive polarity collided with the pre-existing negative polarity belonging to a different bipole, producing recurrent solar activities along the polarity inversion line (PIL) between the colliding polarities, namely the so-called collisional PIL (cPIL). Our results show that a large amount of energy and helicity were built up in the form of magnetic flux ropes (MFRs), with recurrent release and accumulation processes. These MFRs were built up along the cPIL. A flux deficit method is adopted and shows that magnetic cancellation happens along the cPIL due to the collisional shearing scenario proposed by Chintzoglou et al. The total amount of canceled flux was $\sim$0.7$\times$10$^{21}$ Mx with an uncertainty of $\sim$13.2$\%$ within the confidence region of the 30$^\circ$ sun-center distance. The canceled flux amounts to 24$\%$ of the total unsigned flux of the bipolar magnetic region. The results show that the magnetic fields beside the cPIL are very sheared, and the average shear angle is above 70$^\circ$ after the collision. The fast expansion of the twist kernels of the MFRs and the continuous eruptive activities are both driven by the collisional shearing process. These results are important for better understanding the buildup process of the MFRs associated with homologous solar eruptions.

preprint2022arXiv

CCP: Correlated Clustering and Projection for Dimensionality Reduction

Most dimensionality reduction methods employ frequency domain representations obtained from matrix diagonalization and may not be efficient for large datasets with relatively high intrinsic dimensions. To address this challenge, Correlated Clustering and Projection (CCP) offers a novel data domain strategy that does not need to solve any matrix. CCP partitions high-dimensional features into correlated clusters and then projects correlated features in each cluster into a one-dimensional representation based on sample correlations. Residue-Similarity (R-S) scores and indexes, the shape of data in Riemannian manifolds, and algebraic topology-based persistent Laplacian are introduced for visualization and analysis. Proposed methods are validated with benchmark datasets associated with various machine learning algorithms.

preprint2022arXiv

Chern-Simons superconductors and their instabilities

Two-dimensional quantum antiferromagnets host rich physics, including long-range ordering, high-$T_c$ superconductivity, quantum spin liquid behavior, topological ordering, a variety of other exotic phases, and quantum criticalities. Frustrating perturbations in antiferromagnets may give rise to strong quantum fluctuations, challenging the theoretical understanding of the many-body ground state. Here we develop a method to describe the quantum antiferromagnets using fermionic degrees of freedom. The method is based on a formally exact mapping between spin exchange models and theories describing fermionic matter with the emergent $U(1)$ Chern-Simons gauge field. For the planar Néel state, this mapping self-consistently generates the Chern-Simons superconductor mean-field ground state of introduced spinless fermions. We systematically compare the Chern-Simons superconductor state with the planar Néel state at the level of collective modes as well as order parameters. We reveal qualitative and quantitative correspondences between these two states. We demonstrate that such a construction using the fractionalized excitations and Chern-Simons gauge field can not only describe the Néel order but can also be applied to study quantum spin liquids. Furthermore, we show that the confinement-deconfinement transitions from the Néel order to quantum spin liquids are signaled and characterized by the instabilities of Chern-Simons superconductors, driven by strong frustration. The results suggest observing and classifying the descendants of antiferromagnets, including other ordered states and unconventional superconductors, as well as emergent quantum spin liquids.

preprint2022arXiv

Collaborative Representation for SPD Matrices with Application to Image-Set Classification

Collaborative representation-based classification (CRC) has demonstrated remarkable progress in the past few years because of its closed-form analytical solutions. However, the existing CRC methods are incapable of processing the nonlinear variational information directly. Recent advances illustrate that how to effectively model these nonlinear variational information and learn invariant representations is an open challenge in the community of computer vision and pattern recognition To this end, we try to design a new algorithm to handle this problem. Firstly, the second-order statistic, i.e., covariance matrix is applied to model the original image sets. Due to the space formed by a set of nonsingular covariance matrices is a well-known Symmetric Positive Definite (SPD) manifold, generalising the Euclidean collaborative representation to the SPD manifold is not an easy task. Then, we devise two strategies to cope with this issue. One attempts to embed the SPD manifold-valued data representations into an associated tangent space via the matrix logarithm map. Another is to embed them into a Reproducing Kernel Hilbert Space (RKHS) by utilizing the Riemannian kernel function. After these two treatments, CRC is applicable to the SPD manifold-valued features. The evaluations on four banchmarking datasets justify its effectiveness.

preprint2022arXiv

Cross-domain Contrastive Learning for Unsupervised Domain Adaptation

Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a fully-labeled source domain to a different unlabeled target domain. Most existing UDA methods learn domain-invariant feature representations by minimizing feature distances across domains. In this work, we build upon contrastive self-supervised learning to align features so as to reduce the domain discrepancy between training and testing sets. Exploring the same set of categories shared by both domains, we introduce a simple yet effective framework CDCL, for domain alignment. In particular, given an anchor image from one domain, we minimize its distances to cross-domain samples from the same class relative to those from different categories. Since target labels are unavailable, we use a clustering-based approach with carefully initialized centers to produce pseudo labels. In addition, we demonstrate that CDCL is a general framework and can be adapted to the data-free setting, where the source data are unavailable during training, with minimal modification. We conduct experiments on two widely used domain adaptation benchmarks, i.e., Office-31 and VisDA-2017, for image classification tasks, and demonstrate that CDCL achieves state-of-the-art performance on both datasets.

preprint2022arXiv

Data Augmentation vs. Equivariant Networks: A Theory of Generalization on Dynamics Forecasting

Exploiting symmetry in dynamical systems is a powerful way to improve the generalization of deep learning. The model learns to be invariant to transformation and hence is more robust to distribution shift. Data augmentation and equivariant networks are two major approaches to injecting symmetry into learning. However, their exact role in improving generalization is not well understood. In this work, we derive the generalization bounds for data augmentation and equivariant networks, characterizing their effect on learning in a unified framework. Unlike most prior theories for the i.i.d. setting, we focus on non-stationary dynamics forecasting with complex temporal dependencies.

preprint2022arXiv

Deep Reinforcement Learning for Online Routing of Unmanned Aerial Vehicles with Wireless Power Transfer

The unmanned aerial vehicle (UAV) plays an vital role in various applications such as delivery, military mission, disaster rescue, communication, etc., due to its flexibility and versatility. This paper proposes a deep reinforcement learning method to solve the UAV online routing problem with wireless power transfer, which can charge the UAV remotely without wires, thus extending the capability of the battery-limited UAV. Our study considers the power consumption of the UAV and the wireless charging process. Unlike the previous works, we solve the problem by a designed deep neural network. The model is trained using a deep reinforcement learning method offline, and is used to optimize the UAV routing problem online. On small and large scale instances, the proposed model runs from four times to 500 times faster than Google OR-tools, the state-of-the-art combinatorial optimization solver, with identical solution quality. It also outperforms different types of heuristic and local search methods in terms of both run-time and optimality. In addition, once the model is trained, it can scale to new generated problem instances with arbitrary topology that are not seen during training. The proposed method is practically applicable when the problem scale is large and the response time is crucial.

preprint2022arXiv

Determining the number of factors in a large-dimensional generalised factor model

This paper proposes new estimators of the number of factors for a generalised factor model with more relaxed assumptions than the strict factor model. Under the framework of large cross-sections $N$ and large time dimensions $T$, we first derive the bias-corrected estimator $\hat σ^2_*$ of the noise variance in a generalised factor model by random matrix theory. Then we construct three information criteria based on $\hat σ^2_*$, further propose the consistent estimators of the number of factors. Finally, simulations and real data analysis illustrate that our proposed estimations are more accurate and avoid the overestimation in some existing works.

preprint2022arXiv

DreamNet: A Deep Riemannian Network based on SPD Manifold Learning for Visual Classification

Image set-based visual classification methods have achieved remarkable performance, via characterising the image set in terms of a non-singular covariance matrix on a symmetric positive definite (SPD) manifold. To adapt to complicated visual scenarios better, several Riemannian networks (RiemNets) for SPD matrix nonlinear processing have recently been studied. However, it is pertinent to ask, whether greater accuracy gains can be achieved by simply increasing the depth of RiemNets. The answer appears to be negative, as deeper RiemNets tend to lose generalization ability. To explore a possible solution to this issue, we propose a new architecture for SPD matrix learning. Specifically, to enrich the deep representations, we adopt SPDNet [1] as the backbone, with a stacked Riemannian autoencoder (SRAE) built on the tail. The associated reconstruction error term can make the embedding functions of both SRAE and of each RAE an approximate identity mapping, which helps to prevent the degradation of statistical information. We then insert several residual-like blocks with shortcut connections to augment the representational capacity of SRAE, and to simplify the training of a deeper network. The experimental evidence demonstrates that our DreamNet can achieve improved accuracy with increased depth of the network.

preprint2022arXiv

Edge Federated Learning Via Unit-Modulus Over-The-Air Computation

Edge federated learning (FL) is an emerging paradigm that trains a global parametric model from distributed datasets based on wireless communications. This paper proposes a unit-modulus over-the-air computation (UMAirComp) framework to facilitate efficient edge federated learning, which simultaneously uploads local model parameters and updates global model parameters via analog beamforming. The proposed framework avoids sophisticated baseband signal processing, leading to low communication delays and implementation costs. Training loss bounds of UMAirComp FL systems are derived and two low-complexity large-scale optimization algorithms, termed penalty alternating minimization (PAM) and accelerated gradient projection (AGP), are proposed to minimize the nonconvex nonsmooth loss bound. Simulation results show that the proposed UMAirComp framework with PAM algorithm achieves a smaller mean square error of model parameters' estimation, training loss, and test error compared with other benchmark schemes. Moreover, the proposed UMAirComp framework with AGP algorithm achieves satisfactory performance while reduces the computational complexity by orders of magnitude compared with existing optimization algorithms. Finally, we demonstrate the implementation of UMAirComp in a vehicle-to-everything autonomous driving simulation platform. It is found that autonomous driving tasks are more sensitive to model parameter errors than other tasks since the neural networks for autonomous driving contain sparser model parameters.

preprint2022arXiv

Effect of Homomorphic Encryption on the Performance of Training Federated Learning Generative Adversarial Networks

A Generative Adversarial Network (GAN) is a deep-learning generative model in the field of Machine Learning (ML) that involves training two Neural Networks (NN) using a sizable data set. In certain fields, such as medicine, the training data may be hospital patient records that are stored across different hospitals. The classic centralized approach would involve sending the data to a centralized server where the model would be trained. However, that would involve breaching the privacy and confidentiality of the patients and their data, which would be unacceptable. Therefore, Federated Learning (FL), an ML technique that trains ML models in a distributed setting without data ever leaving the host device, would be a better alternative to the centralized option. In this ML technique, only parameters and certain metadata would be communicated. In spite of that, there still exist attacks that can infer user data using the parameters and metadata. A fully privacy-preserving solution involves homomorphically encrypting (HE) the data communicated. This paper will focus on the performance loss of training an FL-GAN with three different types of Homomorphic Encryption: Partial Homomorphic Encryption (PHE), Somewhat Homomorphic Encryption (SHE), and Fully Homomorphic Encryption (FHE). We will also test the performance loss of Multi-Party Computations (MPC), as it has homomorphic properties. The performances will be compared to the performance of training an FL-GAN without encryption as well. Our experiments show that the more complex the encryption method is, the longer it takes, with the extra time taken for HE is quite significant in comparison to the base case of FL.

preprint2022arXiv

Efficient and High-quality Prehensile Rearrangement in Cluttered and Confined Spaces

Prehensile object rearrangement in cluttered and confined spaces has broad applications but is also challenging. For instance, rearranging products in a grocery shelf means that the robot cannot directly access all objects and has limited free space. This is harder than tabletop rearrangement where objects are easily accessible with top-down grasps, which simplifies robot-object interactions. This work focuses on problems where such interactions are critical for completing tasks. It proposes a new efficient and complete solver under general constraints for monotone instances, which can be solved by moving each object at most once. The monotone solver reasons about robot-object constraints and uses them to effectively prune the search space. The new monotone solver is integrated with a global planner to solve non-monotone instances with high-quality solutions fast. Furthermore, this work contributes an effective pre-processing tool to significantly speed up online motion planning queries for rearrangement in confined spaces. Experiments further demonstrate that the proposed monotone solver, equipped with the pre-processing tool, results in 57.3% faster computation and 3 times higher success rate than state-of-the-art methods. Similarly, the resulting global planner is computationally more efficient and has a higher success rate, while producing high-quality solutions for non-monotone instances (i.e., only 1.3 additional actions are needed on average). Videos of demonstrating solutions on a real robotic system and codes can be found at https://github.com/Rui1223/uniform_object_rearrangement.

preprint2022arXiv

Efficient conditioned face animation using frontally-viewed embedding

As the quality of few shot facial animation from landmarks increases, new applications become possible, such as ultra low bandwidth video chat compression with a high degree of realism. However, there are some important challenges to tackle in order to improve the experience in real world conditions. In particular, the current approaches fail to represent profile views without distortions, while running in a low compute regime. We focus on this key problem by introducing a multi-frames embedding dubbed Frontalizer to improve profile views rendering. In addition to this core improvement, we explore the learning of a latent code conditioning generations along with landmarks to better convey facial expressions. Our dense models achieves 22% of improvement in perceptual quality and 73% reduction of landmark error over the first order model baseline on a subset of DFDC videos containing head movements. Declined with mobile architectures, our models outperform the previous state-of-the-art (improving perceptual quality by more than 16% and reducing landmark error by more than 47% on two datasets) while running on real time on iPhone 8 with very low bandwidth requirements.

preprint2022arXiv

EfficientTDNN: Efficient Architecture Search for Speaker Recognition

Convolutional neural networks (CNNs), such as the time-delay neural network (TDNN), have shown their remarkable capability in learning speaker embedding. However, they meanwhile bring a huge computational cost in storage size, processing, and memory. Discovering the specialized CNN that meets a specific constraint requires a substantial effort of human experts. Compared with hand-designed approaches, neural architecture search (NAS) appears as a practical technique in automating the manual architecture design process and has attracted increasing interest in spoken language processing tasks such as speaker recognition. In this paper, we propose EfficientTDNN, an efficient architecture search framework consisting of a TDNN-based supernet and a TDNN-NAS algorithm. The proposed supernet introduces temporal convolution of different ranges of the receptive field and feature aggregation of various resolutions from different layers to TDNN. On top of it, the TDNN-NAS algorithm quickly searches for the desired TDNN architecture via weight-sharing subnets, which surprisingly reduces computation while handling the vast number of devices with various resources requirements. Experimental results on the VoxCeleb dataset show the proposed EfficientTDNN enables approximate $10^{13}$ architectures concerning depth, kernel, and width. Considering different computation constraints, it achieves a 2.20% equal error rate (EER) with 204M multiply-accumulate operations (MACs), 1.41% EER with 571M MACs as well as 0.94% EER with 1.45G MACs. Comprehensive investigations suggest that the trained supernet generalizes subnets not sampled during training and obtains a favorable trade-off between accuracy and efficiency.

preprint2022arXiv

Evaluation of Four Black-box Adversarial Attacks and Some Query-efficient Improvement Analysis

With the fast development of machine learning technologies, deep learning models have been deployed in almost every aspect of everyday life. However, the privacy and security of these models are threatened by adversarial attacks. Among which black-box attack is closer to reality, where limited knowledge can be acquired from the model. In this paper, we provided basic background knowledge about adversarial attack and analyzed four black-box attack algorithms: Bandits, NES, Square Attack and ZOsignSGD comprehensively. We also explored the newly proposed Square Attack method with respect to square size, hoping to improve its query efficiency.

preprint2022arXiv

Exact solutions of Kondo problems in higher-order fermions

The conformal field theory (CFT) approach to Kondo problems, originally developed by Affleck and Ludwig (AL), has greatly advanced the fundamental knowledge of Kondo physics. The CFT approach to Kondo impurities is based on a necessary approximation, i.e., the linearization of the low-lying excitations in a narrow energy window about the Fermi surface. This treatment works well in normal metal baths, but encounters fundamental difficulties in systems with Fermi points and high-order dispersion relations. Prominent examples of such systems are the recently-proposed topological semimetals with emergent higher-order fermions. Here, we develop a new CFT technique that yields exact solutions to the Kondo problems in higher-order fermion systems. Our approach does not require any linearization of the low-lying excitations, and more importantly, it rigorously bosonizes the entire energy spectrum of the higher-order fermions. Therefore, it provides a more solid theoretical base for evaluating the thermodynamic quantities at finite temperatures. Our work significantly broadens the scope of CFT techniques and brings about unprecedented applications beyond the reach of conventional methods.

preprint2022arXiv

Fano Interference in a Single-Molecule Junction

Trends of miniaturized devices and quantum interference electronics lead to the long desire of Fano interference in single-molecule junctions, here, which is successfully demonstrated using the 2,7-di(4-pyridyl)-9,9'-spirobifluorene molecule with a long backbone group and a short side group. Experimentally, the two electrically coupled groups are found to contribute to two blurred degenerate points in the differential conductance mapping. This forms a characteristic non-centrosymmetric double-crossing feature, with distinct temperature response for each crossing. Theoretically, we describe the practical in-junction electron transmission using a new two-tunnelling-channel coupling model and obtain a working formula with a Fano term and a Breit-Wigner term. The formula is shown to provide a good fit for all the mapping data and their temperature dependence in three dimensions, identifying the Fano component. Our work thus forms a complete set of evidence of the Fano interference in a single-molecule junction induced by two-tunnelling-channel coupling transport. Density functional theory calculations are used to corroborate this new physics.

preprint2022arXiv

FLVoogd: Robust And Privacy Preserving Federated Learning

In this work, we propose FLVoogd, an updated federated learning method in which servers and clients collaboratively eliminate Byzantine attacks while preserving privacy. In particular, servers use automatic Density-based Spatial Clustering of Applications with Noise (DBSCAN) combined with S2PC to cluster the benign majority without acquiring sensitive personal information. Meanwhile, clients build dual models and perform test-based distance controlling to adjust their local models toward the global one to achieve personalizing. Our framework is automatic and adaptive that servers/clients don't need to tune the parameters during the training. In addition, our framework leverages Secure Multi-party Computation (SMPC) operations, including multiplications, additions, and comparison, where costly operations, like division and square root, are not required. Evaluations are carried out on some conventional datasets from the image classification field. The result shows that FLVoogd can effectively reject malicious uploads in most scenarios; meanwhile, it avoids data leakage from the server-side.

preprint2022arXiv

Grassmannian Discriminant Maps (GDM) for Manifold Dimensionality Reduction with Application to Image Set Classification

In image set classification, a considerable progress has been made by representing original image sets on Grassmann manifolds. In order to extend the advantages of the Euclidean based dimensionality reduction methods to the Grassmann Manifold, several methods have been suggested recently which jointly perform dimensionality reduction and metric learning on Grassmann manifold to improve performance. Nevertheless, when applied to complex datasets, the learned features do not exhibit enough discriminatory power. To overcome this problem, we propose a new method named Grassmannian Discriminant Maps (GDM) for manifold dimensionality reduction problems. The core of the method is a new discriminant function for metric learning and dimensionality reduction. For comparison and better understanding, we also study a simple variations to GDM. The key difference between them is the discriminant function. We experiment on data sets corresponding to three tasks: face recognition, object categorization, and hand gesture recognition to evaluate the proposed method and its simple extensions. Compared with the state of the art, the results achieved show the effectiveness of the proposed algorithm.

preprint2022arXiv

High quality entanglement distribution through telecommunication fiber using near-infrared non-degenerate photon pairs

For practical quantum communications, the efficiency of the entire system (source, quantum channel and detectors) must be taken into account. In many urban environments, the quantum channel in the form of telecommunication optical fiber (confirming to ITU G.652D standards) are available, but the detectors in this range typically have low efficiency. We investigate the possibility that for campus-type communications, entangled photons prepared in the Near-Infrared Range (NIR) can be transmitted successfully while preserving polarization entanglement. We demonstrate the distribution of degenerate and non-degenerate entangled photon pairs of wavelength around 810 nm through standard telecommunication fiber. This technique benefits from the high efficiency of the NIR single photon detectors and the mature design of setups around 810 nm.. In this work, we obtain high quality entanglement (visibility is 94.8\% based on the raw data) after an overall distance of 12 km, corresponding to about -36 dB of fiber induced loss.

preprint2022arXiv

Hybridization of evolutionary algorithm and deep reinforcement learning for multi-objective orienteering optimization

Multi-objective orienteering problems (MO-OPs) are classical multi-objective routing problems and have received a lot of attention in the past decades. This study seeks to solve MO-OPs through a problem-decomposition framework, that is, a MO-OP is decomposed into a multi-objective knapsack problem (MOKP) and a travelling salesman problem (TSP). The MOKP and TSP are then solved by a multi-objective evolutionary algorithm (MOEA) and a deep reinforcement learning (DRL) method, respectively. While the MOEA module is for selecting cities, the DRL module is for planning a Hamiltonian path for these cities. An iterative use of these two modules drives the population towards the Pareto front of MO-OPs. The effectiveness of the proposed method is compared against NSGA-II and NSGA-III on various types of MO-OP instances. Experimental results show that our method exhibits the best performance on almost all the test instances, and has shown strong generalization ability.

preprint2022arXiv

Hyperspectral Unmixing Based on Nonnegative Matrix Factorization: A Comprehensive Review

Hyperspectral unmixing has been an important technique that estimates a set of endmembers and their corresponding abundances from a hyperspectral image (HSI). Nonnegative matrix factorization (NMF) plays an increasingly significant role in solving this problem. In this article, we present a comprehensive survey of the NMF-based methods proposed for hyperspectral unmixing. Taking the NMF model as a baseline, we show how to improve NMF by utilizing the main properties of HSIs (e.g., spectral, spatial, and structural information). We categorize three important development directions including constrained NMF, structured NMF, and generalized NMF. Furthermore, several experiments are conducted to illustrate the effectiveness of associated algorithms. Finally, we conclude the article with possible future directions with the purposes of providing guidelines and inspiration to promote the development of hyperspectral unmixing.

preprint2022arXiv

Improving Deep Image Matting via Local Smoothness Assumption

Natural image matting is a fundamental and challenging computer vision task. Conventionally, the problem is formulated as an underconstrained problem. Since the problem is ill-posed, further assumptions on the data distribution are required to make the problem well-posed. For classical matting methods, a commonly adopted assumption is the local smoothness assumption on foreground and background colors. However, the use of such assumptions was not systematically considered for deep learning based matting methods. In this work, we consider two local smoothness assumptions which can help improving deep image matting models. Based on the local smoothness assumptions, we propose three techniques, i.e., training set refinement, color augmentation and backpropagating refinement, which can improve the performance of the deep image matting model significantly. We conduct experiments to examine the effectiveness of the proposed algorithm. The experimental results show that the proposed method has favorable performance compared with existing matting methods.

preprint2022arXiv

LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT

Self-supervised speech representation learning has shown promising results in various speech processing tasks. However, the pre-trained models, e.g., HuBERT, are storage-intensive Transformers, limiting their scope of applications under low-resource settings. To this end, we propose LightHuBERT, a once-for-all Transformer compression framework, to find the desired architectures automatically by pruning structured parameters. More precisely, we create a Transformer-based supernet that is nested with thousands of weight-sharing subnets and design a two-stage distillation strategy to leverage the contextualized latent representations from HuBERT. Experiments on automatic speech recognition (ASR) and the SUPERB benchmark show the proposed LightHuBERT enables over $10^9$ architectures concerning the embedding dimension, attention dimension, head number, feed-forward network ratio, and network depth. LightHuBERT outperforms the original HuBERT on ASR and five SUPERB tasks with the HuBERT size, achieves comparable performance to the teacher model in most tasks with a reduction of 29% parameters, and obtains a $3.5\times$ compression ratio in three SUPERB tasks, e.g., automatic speaker verification, keyword spotting, and intent classification, with a slight accuracy loss. The code and pre-trained models are available at https://github.com/mechanicalsea/lighthubert.

preprint2022arXiv

M Subdwarf Research III. Spectroscopic Diagnostics for Breaking Parameter Degeneracy

To understand the parameter degeneracy of M subdwarf spectra at low resolution, we assemble a large number of spectral features in the wavelength range of 0.6-2.5 μm with band strength quantified by narrowband indices. Based on the index trends of BT-Settl model sequences, we illustrate how the main atmospheric parameters (Teff, log g, [M/H], and [alpha/Fe]) affect each spectral feature differently. Furthermore, we propose a four-step process to determine the four parameters sequentially, which extends the basic idea proposed by Jao et al. Each step contains several spectral features that break the degeneracy effect when determining a specific stellar parameter. Finally, the feasibility of each spectroscopic diagnostic with different spectral qualities is investigated. The result is resolution-independent down to R~200.

preprint2022arXiv

MINERVAS: Massive INterior EnviRonments VirtuAl Synthesis

With the rapid development of data-driven techniques, data has played an essential role in various computer vision tasks. Many realistic and synthetic datasets have been proposed to address different problems. However, there are lots of unresolved challenges: (1) the creation of dataset is usually a tedious process with manual annotations, (2) most datasets are only designed for a single specific task, (3) the modification or randomization of the 3D scene is difficult, and (4) the release of commercial 3D data may encounter copyright issue. This paper presents MINERVAS, a Massive INterior EnviRonments VirtuAl Synthesis system, to facilitate the 3D scene modification and the 2D image synthesis for various vision tasks. In particular, we design a programmable pipeline with Domain-Specific Language, allowing users to (1) select scenes from the commercial indoor scene database, (2) synthesize scenes for different tasks with customized rules, and (3) render various imagery data, such as visual color, geometric structures, semantic label. Our system eases the difficulty of customizing massive numbers of scenes for different tasks and relieves users from manipulating fine-grained scene configurations by providing user-controllable randomness using multi-level samplers. Most importantly, it empowers users to access commercial scene databases with millions of indoor scenes and protects the copyright of core data assets, e.g., 3D CAD models. We demonstrate the validity and flexibility of our system by using our synthesized data to improve the performance on different kinds of computer vision tasks.

preprint2022arXiv

Model Pruning Based on Quantified Similarity of Feature Maps

Convolutional Neural Networks (CNNs) has been applied in numerous Internet of Things (IoT) devices for multifarious downstream tasks. However, with the increasing amount of data on edge devices, CNNs can hardly complete some tasks in time with limited computing and storage resources. Recently, filter pruning has been regarded as an effective technique to compress and accelerate CNNs, but existing methods rarely prune CNNs from the perspective of compressing high-dimensional tensors. In this paper, we propose a novel theory to find redundant information in three-dimensional tensors, namely Quantified Similarity between Feature Maps (QSFM), and utilize this theory to guide the filter pruning procedure. We perform QSFM on datasets (CIFAR-10, CIFAR-100 and ILSVRC-12) and edge devices, demonstrate that the proposed method can find the redundant information in the neural networks effectively with comparable compression and tolerable drop of accuracy. Without any fine-tuning operation, QSFM can compress ResNet-56 on CIFAR-10 significantly (48.7% FLOPs and 57.9% parameters are reduced) with only a loss of 0.54% in the top-1 accuracy. For the practical application of edge devices, QSFM can accelerate MobileNet-V2 inference speed by 1.53 times with only a loss of 1.23% in the ILSVRC-12 top-1 accuracy.

preprint2022arXiv

Morphological Anti-Aliasing Method for Boundary Slope Prediction

Image pixel aliasing caused by insufficient sampling is a long-standing problem in the field of computer graphics. It has always been the goal of researchers to seek anti-aliasing algorithms with high speed and good effect. Due to the deficiencies in local detection and reconstruction of sloping line boundaries, a morphological anti-aliasing method for boundary slope prediction is proposed. This method uses the information of the local line boundary slope to predict and test the end positions of the line boundary in the global scope, thereby reconstructing The boundary information more consistent with the actual boundary is obtained, and a more accurate linear boundary shape is obtained with only a small increase in the amount of calculation. Compared with the previous morphological anti-aliasing algorithm, the proposed method is based on the global morphological boundary. , can reconstruct the straight line boundary more accurately, and apply it to the anti-aliasing calculation, which can further improve the color transition of the straight line boundary, make the inclined straight line boundary have higher continuity, and obtain a better anti-aliasing effect.

preprint2022arXiv

MULTI-FLGANs: Multi-Distributed Adversarial Networks for Non-IID distribution

Federated learning is an emerging concept in the domain of distributed machine learning. This concept has enabled GANs to benefit from the rich distributed training data while preserving privacy. However, in a non-iid setting, current federated GAN architectures are unstable, struggling to learn the distinct features and vulnerable to mode collapse. In this paper, we propose a novel architecture MULTI-FLGAN to solve the problem of low-quality images, mode collapse and instability for non-iid datasets. Our results show that MULTI-FLGAN is four times as stable and performant (i.e. high inception score) on average over 20 clients compared to baseline FLGAN.

preprint2022arXiv

Multi-objective Pointer Network for Combinatorial Optimization

Multi-objective combinatorial optimization problems (MOCOPs), one type of complex optimization problems, widely exist in various real applications. Although meta-heuristics have been successfully applied to address MOCOPs, the calculation time is often much longer. Recently, a number of deep reinforcement learning (DRL) methods have been proposed to generate approximate optimal solutions to the combinatorial optimization problems. However, the existing studies on DRL have seldom focused on MOCOPs. This study proposes a single-model deep reinforcement learning framework, called multi-objective Pointer Network (MOPN), where the input structure of PN is effectively improved so that the single PN is capable of solving MOCOPs. In addition, two training strategies, based on representative model and transfer learning, respectively, are proposed to further enhance the performance of MOPN in different application scenarios. Moreover, compared to classical meta-heuristics, MOPN only consumes much less time on forward propagation to obtain the Pareto front. Meanwhile, MOPN is insensitive to problem scale, meaning that a trained MOPN is able to address MOCOPs with different scales. To verify the performance of MOPN, extensive experiments are conducted on three multi-objective traveling salesman problems, in comparison with one state-of-the-art model DRL-MOA and three classical multi-objective meta-heuristics. Experimental results demonstrate that the proposed model outperforms all the comparative methods with only 20\% to 40\% training time of DRL-MOA.

preprint2022arXiv

Multi-View Self-Attention Based Transformer for Speaker Recognition

Initially developed for natural language processing (NLP), Transformer model is now widely used for speech processing tasks such as speaker recognition, due to its powerful sequence modeling capabilities. However, conventional self-attention mechanisms are originally designed for modeling textual sequence without considering the characteristics of speech and speaker modeling. Besides, different Transformer variants for speaker recognition have not been well studied. In this work, we propose a novel multi-view self-attention mechanism and present an empirical study of different Transformer variants with or without the proposed attention mechanism for speaker recognition. Specifically, to balance the capabilities of capturing global dependencies and modeling the locality, we propose a multi-view self-attention mechanism for speaker Transformer, in which different attention heads can attend to different ranges of the receptive field. Furthermore, we introduce and compare five Transformer variants with different network architectures, embedding locations, and pooling methods to learn speaker embeddings. Experimental results on the VoxCeleb1 and VoxCeleb2 datasets show that the proposed multi-view self-attention mechanism achieves improvement in the performance of speaker recognition, and the proposed speaker Transformer network attains excellent results compared with state-of-the-art models.

preprint2022arXiv

Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios

Due to the complex attention mechanisms and model design, most existing vision Transformers (ViTs) can not perform as efficiently as convolutional neural networks (CNNs) in realistic industrial deployment scenarios, e.g. TensorRT and CoreML. This poses a distinct challenge: Can a visual neural network be designed to infer as fast as CNNs and perform as powerful as ViTs? Recent works have tried to design CNN-Transformer hybrid architectures to address this issue, yet the overall performance of these works is far away from satisfactory. To end these, we propose a next generation vision Transformer for efficient deployment in realistic industrial scenarios, namely Next-ViT, which dominates both CNNs and ViTs from the perspective of latency/accuracy trade-off. In this work, the Next Convolution Block (NCB) and Next Transformer Block (NTB) are respectively developed to capture local and global information with deployment-friendly mechanisms. Then, Next Hybrid Strategy (NHS) is designed to stack NCB and NTB in an efficient hybrid paradigm, which boosts performance in various downstream tasks. Extensive experiments show that Next-ViT significantly outperforms existing CNNs, ViTs and CNN-Transformer hybrid architectures with respect to the latency/accuracy trade-off across various vision tasks. On TensorRT, Next-ViT surpasses ResNet by 5.5 mAP (from 40.4 to 45.9) on COCO detection and 7.7% mIoU (from 38.8% to 46.5%) on ADE20K segmentation under similar latency. Meanwhile, it achieves comparable performance with CSWin, while the inference speed is accelerated by 3.6x. On CoreML, Next-ViT surpasses EfficientFormer by 4.6 mAP (from 42.6 to 47.2) on COCO detection and 3.5% mIoU (from 45.1% to 48.6%) on ADE20K segmentation under similar latency. Our code and models are made public at: https://github.com/bytedance/Next-ViT

preprint2022arXiv

Normal and Visibility Estimation of Human Face from a Single Image

Recent work on the intrinsic image of humans starts to consider the visibility of incident illumination and encodes the light transfer function by spherical harmonics. In this paper, we show that such a light transfer function can be further decomposed into visibility and cosine terms related to surface normal. Such decomposition allows us to recover the surface normal in addition to visibility. We propose a deep learning-based approach with a reconstruction loss for training on real-world images. Results show that compared with previous works, the reconstruction of human face from our method better reveals the surface normal and shading details especially around regions where visibility effect is strong.

preprint2022arXiv

On the Effectiveness of Pinyin-Character Dual-Decoding for End-to-End Mandarin Chinese ASR

End-to-end automatic speech recognition (ASR) has achieved promising results. However, most existing end-to-end ASR methods neglect the use of specific language characteristics. For Mandarin Chinese ASR tasks, there exist mutual promotion relationship between Pinyin and Character where Chinese characters can be romanized by Pinyin. Based on the above intuition, we first investigate types of end-to-end encoder-decoder based models in the single-input dual-output (SIDO) multi-task framework, after which a novel asynchronous decoding with fuzzy Pinyin sampling method is proposed according to the one-to-one correspondence characteristics between Pinyin and Character. Furthermore, we proposed a two-stage training strategy to make training more stable and converge faster. The results on the test sets of AISHELL-1 dataset show that the proposed enhanced dual-decoder model without a language model is improved by a big margin compared to strong baseline models.

preprint2022arXiv

Online Object Model Reconstruction and Reuse for Lifelong Improvement of Robot Manipulation

This work proposes a robotic pipeline for picking and constrained placement of objects without geometric shape priors. Compared to recent efforts developed for similar tasks, where every object was assumed to be novel, the proposed system recognizes previously manipulated objects and performs online model reconstruction and reuse. Over a lifelong manipulation process, the system keeps learning features of objects it has interacted with and updates their reconstructed models. Whenever an instance of a previously manipulated object reappears, the system aims to first recognize it and then register its previously reconstructed model given the current observation. This step greatly reduces object shape uncertainty allowing the system to even reason for parts of objects, which are currently not observable. This also results in better manipulation efficiency as it reduces the need for active perception of the target object during manipulation. To get a reusable reconstructed model, the proposed pipeline adopts: i) TSDF for object representation, and ii) a variant of the standard particle filter algorithm for pose estimation and tracking of the partial object model. Furthermore, an effective way to construct and maintain a dataset of manipulated objects is presented. A sequence of real-world manipulation experiments is performed. They show how future manipulation tasks become more effective and efficient by reusing reconstructed models of previously manipulated objects, which were generated during their prior manipulation, instead of treating objects as novel every time.

preprint2022arXiv

Parallel Pre-trained Transformers (PPT) for Synthetic Data-based Instance Segmentation

Recently, Synthetic data-based Instance Segmentation has become an exceedingly favorable optimization paradigm since it leverages simulation rendering and physics to generate high-quality image-annotation pairs. In this paper, we propose a Parallel Pre-trained Transformers (PPT) framework to accomplish the synthetic data-based Instance Segmentation task. Specifically, we leverage the off-the-shelf pre-trained vision Transformers to alleviate the gap between natural and synthetic data, which helps to provide good generalization in the downstream synthetic data scene with few samples. Swin-B-based CBNet V2, SwinL-based CBNet V2 and Swin-L-based Uniformer are employed for parallel feature learning, and the results of these three models are fused by pixel-level Non-maximum Suppression (NMS) algorithm to obtain more robust results. The experimental results reveal that PPT ranks first in the CVPR2022 AVA Accessibility Vision and Autonomy Challenge, with a 65.155% mAP.

preprint2022arXiv

Parameter Choices for Sparse Regularization with the $\ell_1$ Norm

We consider a regularization problem whose objective function consists of a convex fidelity term and a regularization term determined by the $\ell_1$ norm composed with a linear transform. Empirical results show that the regularization with the $\ell_1$ norm can promote sparsity of a regularized solution. It is the goal of this paper to understand theoretically the effect of the regularization parameter on the sparsity of the regularized solutions. We establish a characterization of the sparsity under the transform matrix of the solution. When the fidelity term has a special structure and the transform matrix coincides with a identity matrix, the resulting characterization can be taken as a regularization parameter choice strategy with which the regularization problem has a solution having a sparsity of a certain level. We study choices of the regularization parameter so that the regularization term alleviates the ill-posedness and promote sparsity of the resulting regularized solution. Numerical experiments demonstrate that choices of the regularization parameters can balance the sparsity of the solutions of the regularization problem and its approximation to the minimizer of the fidelity function.

preprint2022arXiv

Passive Motion Detection via mmWave Communication System

In this paper, an integrated passive sensing and communication system working in 60 GHz band is elaborated, and the sensing performance is investigated in an application of hand gesture recognition. Specifically, in this integrated system, there are two radio frequency (RF) chains at the receiver and one at the transmitter. Each RF chain is connected with one phased array for analog beamforming. To facilitate simultaneous sensing and communication, the transmitter delivers one stream of information-bearing signals via two beam lobes, one is aligned with the main signal propagation path and the other is directed to the sensing target. Signals from the two lobes are received by the two RF chains at the receiver, respectively. By cross ambiguity coherent processing, the time-Doppler spectrograms of hand gestures can be obtained. Relying on the passive sensing system, a dataset of received signals, where three types of hand gestures are sensed, is collected by using Line-of-Sight (LoS) and Non-Line-of-Sight (NLoS) paths as the reference channel respectively. Then a neural network is trained by the dataset for motion detection. It is shown that the classification accuracy rate is high as long as sufficient sensing time is assured. Finally, an empirical model characterizing the relation between the classification accuracy and sensing duration is derived analytically.

preprint2022arXiv

Persistent Homology for Effective Non-Prehensile Manipulation

This work explores the use of topological tools for achieving effective non-prehensile manipulation in cluttered, constrained workspaces. In particular, it proposes the use of persistent homology as a guiding principle in identifying the appropriate non-prehensile actions, such as pushing, to clean a cluttered space with a robotic arm so as to allow the retrieval of a target object. Persistent homology enables the automatic identification of connected components of blocking objects in the space without the need for manual input or tuning of parameters. The proposed algorithm uses this information to push groups of cylindrical objects together and aims to minimize the number of pushing actions needed to reach to the target. Simulated experiments in a physics engine using a model of the Baxter robot show that the proposed topology-driven solution is achieving significantly higher success rate in solving such constrained problems relatively to state-of-the-art alternatives from the literature. It manages to keep the number of pushing actions low, is computationally efficient and the resulting decisions and motion appear natural for effectively solving such tasks.

preprint2022arXiv

Persistent Path Laplacian

Path homology proposed by S.-T.Yau and his co-workers provides a new mathematical model for directed graphs and networks. Persistent path homology (PPH) extends the path homology with filtration to deal with asymmetry structures. However, PPH is constrained to purely topological persistence and cannot track the homotopic shape evolution of data during filtration. To overcome the limitation of PPH, persistent path Laplacian (PPL) is introduced to capture the shape evolution of data. PPL's harmonic spectra fully recover PPH's topological persistence and its non-harmonic spectra reveal the homotopic shape evolution of data during filtration.

preprint2022arXiv

PriFit: Learning to Fit Primitives Improves Few Shot Point Cloud Segmentation

We present PriFit, a semi-supervised approach for label-efficient learning of 3D point cloud segmentation networks. PriFit combines geometric primitive fitting with point-based representation learning. Its key idea is to learn point representations whose clustering reveals shape regions that can be approximated well by basic geometric primitives, such as cuboids and ellipsoids. The learned point representations can then be re-used in existing network architectures for 3D point cloud segmentation, and improves their performance in the few-shot setting. According to our experiments on the widely used ShapeNet and PartNet benchmarks, PriFit outperforms several state-of-the-art methods in this setting, suggesting that decomposability into primitives is a useful prior for learning representations predictive of semantic parts. We present a number of ablative experiments varying the choice of geometric primitives and downstream tasks to demonstrate the effectiveness of the method.

preprint2022arXiv

Q-balls Formation and the Production of Gravitational Waves With Non-minimal Gravitational Coupling

We propose to introduce non-minimal couplings of Affleck-Dine (AD) field to gravity by adding the coupling of AD field to the Ricci scalar curvature. As the Jordan frame supergravity always predict $|Φ|^2 {\cal R}/6$ type coupling for scalars with canonical kinetic terms, we propose a way to realize the required $c_0|Φ|^2 {\cal R}$-type couplings with generic $c_0$ for canonical complex scalar fields after SUSY breaking. The impacts of such non-minimal gravitational couplings for AD field is shown, especially on the Q-balls formation and the associated gravitational wave (GW) productions. New form of scalar potential for AD field in the Einstein frame is obtained. By numerical simulations, we find that, with non-minimal gravitational coupling to AD field, Q-balls can successfully form even with the choice of non-negative $K$ parameter for $ξ>0$. The associated GW productions as well as their dependences on the $ξ$ parameter are also discussed.

preprint2022arXiv

R2: A Distributed Remote Function Execution Mechanism With Built-in Metadata

Named data networking (NDN) constructs a network by names, providing a flexible and decentralized way to manage resources within the edge computing continuum. This paper aims to solve the question, "Given a function with its parameters and metadata, how to select the executor in a distributed manner and obtain the result in NDN?" To answer it, we design R2 that involves the following stages. First, we design a name structure including data, function names, and other function parameters. Second, we develop a 2-phase mechanism, where in the first phase, the function request from a client-first reaches the data source and retrieves the metadata, then the best node is selected while the metadata is responding to the client. In the second phase, the chosen node directly retrieves the data, executes the function, and provides the result to the client. Furthermore, we propose a stop condition to intelligently reduce the processing time of the first phase and provide a simple proof and range analysis. Simulations confirm that R2 outperforms the current solutions in terms of resource allocation, especially when the data volume and the function complexity are high. In the experiments, when the data size is 100 KiB and the function complexity is $\mathcal{O}(n^2)$, the speedup ratio is 4.61. To further evaluate R2, we also implement a general intermediate data processing logic named ``Bolt'' implemented on an app-level in ndnSIM. We believe that R2 shall help the researchers and developers to verify their ideas smoothly.

preprint2022arXiv

RAW-GNN: RAndom Walk Aggregation based Graph Neural Network

Graph-Convolution-based methods have been successfully applied to representation learning on homophily graphs where nodes with the same label or similar attributes tend to connect with one another. Due to the homophily assumption of Graph Convolutional Networks (GCNs) that these methods use, they are not suitable for heterophily graphs where nodes with different labels or dissimilar attributes tend to be adjacent. Several methods have attempted to address this heterophily problem, but they do not change the fundamental aggregation mechanism of GCNs because they rely on summation operators to aggregate information from neighboring nodes, which is implicitly subject to the homophily assumption. Here, we introduce a novel aggregation mechanism and develop a RAndom Walk Aggregation-based Graph Neural Network (called RAW-GNN) method. The proposed approach integrates the random walk strategy with graph neural networks. The new method utilizes breadth-first random walk search to capture homophily information and depth-first search to collect heterophily information. It replaces the conventional neighborhoods with path-based neighborhoods and introduces a new path-based aggregator based on Recurrent Neural Networks. These designs make RAW-GNN suitable for both homophily and heterophily graphs. Extensive experimental results showed that the new method achieved state-of-the-art performance on a variety of homophily and heterophily graphs.

preprint2022arXiv

Real-time Monte Carlo Denoising with Weight Sharing Kernel Prediction Network

Real-time Monte Carlo denoising aims at removing severe noise under low samples per pixel (spp) in a strict time budget. Recently, kernel-prediction methods use a neural network to predict each pixel's filtering kernel and have shown a great potential to remove Monte Carlo noise. However, the heavy computation overhead blocks these methods from real-time applications. This paper expands the kernel-prediction method and proposes a novel approach to denoise very low spp (e.g., 1-spp) Monte Carlo path traced images at real-time frame rates. Instead of using the neural network to directly predict the kernel map, i.e., the complete weights of each per-pixel filtering kernel, we predict an encoding of the kernel map, followed by a high-efficiency decoder with unfolding operations for a high-quality reconstruction of the filtering kernels. The kernel map encoding yields a compact single-channel representation of the kernel map, which can significantly reduce the kernel-prediction network's throughput. In addition, we adopt a scalable kernel fusion module to improve denoising quality. The proposed approach preserves kernel prediction methods' denoising quality while roughly halving its denoising time for 1-spp noisy inputs. In addition, compared with the recent neural bilateral grid-based real-time denoiser, our approach benefits from the high parallelism of kernel-based reconstruction and produces better denoising results at equal time.

preprint2022arXiv

Real-time Rendering and Editing of Scattering Effects for Translucent Objects

The photorealistic rendering of the transparent effect of translucent objects is a hot research topic in recent years. A real-time photorealistic rendering and material dynamic editing method for the diffuse scattering effect of translucent objects is proposed based on the bidirectional surface scattering reflectance function's (BSSRDF) Dipole approximation. The diffuse scattering material function in the Dipo le approximation is decomposed into the product form of the shape-related function and the translucent material-related function through principal component analysis; using this decomposition representation, under the real-time photorealistic rendering framework of pre-radiative transmission and the scattering transmission to realize real-time editing of translucent object materials under various light sources. In addition, a method for quadratic wavelet compression of precomputed radiative transfer data in the spatial domain is also proposed. Using the correlation of surface points in the spatial distribution position, on the premise of ensuring the rendering quality, the data is greatly compressed and the rendering is efficiently improved. The experimental results show that the method in this paper can generate a highly realistic translucent effect and ensure the real-time rendering speed.

preprint2022arXiv

Reinforcement Learning Based Robust Policy Design for Relay and Power Optimization in DF Relaying Networks

In this paper, we study the outage minimization problem in a decode-and-forward cooperative network with relay uncertainty. To reduce the outage probability and improve the quality of service, existing researches usually rely on the assumption of both exact instantaneous channel state information (CSI) and environmental uncertainty. However, it is difficult to obtain perfect instantaneous CSI immediately under practical situations where channel states change rapidly, and the uncertainty in communication environments may not be observed, which makes traditional methods not applicable. Therefore, we turn to reinforcement learning (RL) methods for solutions, which do not need any prior knowledge of underlying channel or assumptions of environmental uncertainty. RL method is to learn from the interaction with communication environment, optimize its action policy, and then propose relay selection and power allocation schemes. We first analyse the robustness of RL action policy by giving the lower bound of the worst-case performance, when RL methods are applied to communication scenarios with environment uncertainty. Then, we propose a robust algorithm for outage probability minimization based on RL. Simulation results reveal that compared with traditional RL methods, our approach has better generalization ability and can improve the worst-case performance by about 6% when evaluated in unseen environments.

preprint2022arXiv

Relationship between Successive Flares in the Same Active Region and Space-Weather HMI Active Region Patch (SHARP) Parameters

A solar active region (AR) may produce multiple notable flares during its passage across the solar disk. We investigate successive flares from flare-eruptive active regions, and explore their relationship with solar magnetic parameters. We examine six ARs in this study, each with at least one major flare above X1.0. The Space-Weather HMI Active Region Patch (SHARP) is employed in this study to parameterize the ARs. We aim to identify the most flare-related SHARP parameters and lay foundation for future practical flare forecasts. We first evaluate the correlation coefficients between the SHARP parameters and the successive flare production. Then we adopt a Natural Gradient Boost (NGBoost) method to analyze the relationship between the SHARP parameters and the successive flare bursts. Based on the correlation analysis and the importance distribution returned from NGBoost, we select 8 most flare-related SHARP parameters. Finally, we discuss the physical meanings of the 8 selected parameters and their relationship with flare production.

preprint2022arXiv

Robins-Monro Augmented Lagrangian Method for Stochastic Convex Optimization

In this paper, we propose a Robbins-Monro augmented Lagrangian method (RMALM) to solve a class of constrained stochastic convex optimization, which can be regarded as a hybrid of the Robbins-Monro type stochastic approximation method and the augmented Lagrangian method of convex optimizations. Under mild conditions, we show that the proposed algorithm exhibits a linear convergence rate. Moreover, instead of verifying a computationally intractable stopping criteria, we show that the RMALM with the increasing subproblem iteration number has a global complexity $\mathcal{O}(1/\varepsilon^{1+q})$ for the $\varepsilon$-solution (i.e., $\mathbb{E}\left(\|x^k-x^*\|^2\right) < \varepsilon$), where $q$ is any positive number. Numerical results on synthetic and real data demonstrate that the proposed algorithm outperforms the existing algorithms.

preprint2022arXiv

Rule-based Procedural Tree Modeling Approach

In some entertainment and virtual reality applications, it is necessary to model and draw the real world realistically, so as to improve the fidelity of natural scenes and make users have a better sense of immersion. However, due to the morphological structure of trees The complexity and variety present many challenges for photorealistic modeling and rendering of trees. This paper reviews the progress achieved in photorealistic modeling and rendering of tree branches, leaves, and bark over the past few decades. The main achievement is mainly a rule-based procedural tree modeling method.

preprint2022arXiv

S-type stars discovered in Medium-Resolution Spectra of LAMOST DR9

In this paper, we report on 606 S-type stars identified from Data Release 9 of the LAMOST medium-resolution spectroscopic (MRS) survey, and 539 of them are reported for the first time. The discovery of these stars is a three-step process, i.e., selecting with the ZrO band indices greater than 0.25, excluding non-S-type stars with the iterative Support Vector Machine method, and finally retaining stars with absolute bolometric magnitude larger than -7.1. The 606 stars are consistent with the distribution of known S-type stars in the color-magnitude diagram. We estimated the C/Os using the [C/Fe] and [O/Fe] provided by APOGEE and the MARCS model for S-type stars, respectively, and the results of the two methods show that C/Os of all stars are larger than 0.5. Both the locations on the color-magnitude diagram and C/Os further verify the nature of our S-type sample. Investigating the effect of TiO and atmospheric parameters on ZrO with the sample, we found that log g has a more significant impact on ZrO than Teff and [Fe/H], and both TiO and log g may negatively correlate with ZrO. According to the criterion of Tian et al. (2020), a total of 238 binary candidates were found by the zero-point-calibrated radial velocities from the officially released catalog of LAMOST MRS and the catalog of Zhang et al. (2021). A catalog of these 606 S-type stars is available from the following link https://doi.org/10.12149/101097.

preprint2022arXiv

Secure Rate-Splitting for MIMO Broadcast Channel with Imperfect CSIT and a Jammer

In this paper, we investigate the secure rate-splitting for the two-user multiple-input multiple-output (MIMO) broadcast channel with imperfect channel state information at the transmitter (CSIT) and a multiple-antenna jammer, where each receiver has an equal number of antennas and the jammer has perfect channel state information (CSI). Specifically, we design a secure rate-splitting multiple-access strategy, where the security of split private and common messages is ensured by precoder design with joint nulling and aligning the leakage information, regarding different antenna configurations. Moreover, we show that the sum-secure degrees-of-freedom (SDoF) achieved by secure rate-splitting is optimal and outperforms that by conventional zero-forcing. Therefore, we reveal the sum-SDoF of the two-user MIMO broadcast channel with imperfect CSIT and a jammer, and validate the superiority of rate-splitting for the security purpose in this scenario with emphasis of MIMO.

preprint2022arXiv

Self Punishment and Reward Backfill for Deep Q-Learning

Reinforcement learning agents learn by encouraging behaviours which maximize their total reward, usually provided by the environment. In many environments, however, the reward is provided after a series of actions rather than each single action, leading the agent to experience ambiguity in terms of whether those actions are effective, an issue known as the credit assignment problem. In this paper, we propose two strategies inspired by behavioural psychology to enable the agent to intrinsically estimate more informative reward values for actions with no reward. The first strategy, called self-punishment (SP), discourages the agent from making mistakes that lead to undesirable terminal states. The second strategy, called the rewards backfill (RB), backpropagates the rewards between two rewarded actions. We prove that, under certain assumptions and regardless of the reinforcement learning algorithm used, these two strategies maintain the order of policies in the space of all possible policies in terms of their total reward, and, by extension, maintain the optimal policy. Hence, our proposed strategies integrate with any reinforcement learning algorithm that learns a value or action-value function through experience. We incorporated these two strategies into three popular deep reinforcement learning approaches and evaluated the results on thirty Atari games. After parameter tuning, our results indicate that the proposed strategies improve the tested methods in over 65 percent of tested games by up to over 25 times performance improvement.

preprint2022arXiv

SenseCare: A Research Platform for Medical Image Informatics and Interactive 3D Visualization

Clinical research on smart health has an increasing demand for intelligent and clinic-oriented medical image computing algorithms and platforms that support various applications. To this end, we have developed SenseCare research platform, which is designed to facilitate translational research on intelligent diagnosis and treatment planning in various clinical scenarios. To enable clinical research with Artificial Intelligence (AI), SenseCare provides a range of AI toolkits for different tasks, including image segmentation, registration, lesion and landmark detection from various image modalities ranging from radiology to pathology. In addition, SenseCare is clinic-oriented and supports a wide range of clinical applications such as diagnosis and surgical planning for lung cancer, pelvic tumor, coronary artery disease, etc. SenseCare provides several appealing functions and features such as advanced 3D visualization, concurrent and efficient web-based access, fast data synchronization and high data security, multi-center deployment, support for collaborative research, etc. In this report, we present an overview of SenseCare as an efficient platform providing comprehensive toolkits and high extensibility for intelligent image analysis and clinical research in different application scenarios. We also summarize the research outcome through the collaboration with multiple hospitals.

preprint2022arXiv

Sparse Sampling and Completion for Light Transport in VPL-based Rendering

The many-light formulation provides a general framework for rendering various illumination effects using hundreds of thousands of virtual point lights (VPLs). To efficiently gather the contributions of the VPLs, lightcuts and its extensions cluster the VPLs, which implicitly approximates the lighting matrix with some representative blocks similar to vector quantization. In this paper, we propose a new approximation method based on the previous lightcut method and a low-rank matrix factorization model. As many researchers pointed out, the lighting matrix is low rank, which implies that it can be completed from a small set of known entries. We first generate a conservative global light cut with bounded error and partition the lighting matrix into slices by the coordinate and normal of the surface points using the method of lightslice. Then we perform two passes of randomly sampling on each matrix slice. In the first pass, uniformly distributed random entries are sampled to coarsen the global light cut, further clustering the similar light for the spatially localized surface points of the slices. In the second pass, more entries are sampled according to the possibility distribution function estimated from the first sampling result. Then each matrix slice is factorized into a product of two smaller low-rank matrices constrained by the sampled entries, which delivers a completion of the lighting matrix. The factorized form provides an additional speedup for adding up the matrix columns which is more GPU friendly. Compared with the previous lightcut based methods, we approximate the lighting matrix with some signal specialized bases via factorization. The experimental results shows that we can achieve significant acceleration than the state of the art many-light methods.

preprint2022arXiv

SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing

Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-modal SpeechT5 framework that explores the encoder-decoder pre-training for self-supervised speech/text representation learning. The SpeechT5 framework consists of a shared encoder-decoder network and six modal-specific (speech/text) pre/post-nets. After preprocessing the input speech/text through the pre-nets, the shared encoder-decoder network models the sequence-to-sequence transformation, and then the post-nets generate the output in the speech/text modality based on the output of the decoder. Leveraging large-scale unlabeled speech and text data, we pre-train SpeechT5 to learn a unified-modal representation, hoping to improve the modeling capability for both speech and text. To align the textual and speech information into this unified semantic space, we propose a cross-modal vector quantization approach that randomly mixes up speech/text states with latent units as the interface between encoder and decoder. Extensive evaluations show the superiority of the proposed SpeechT5 framework on a wide variety of spoken language processing tasks, including automatic speech recognition, speech synthesis, speech translation, voice conversion, speech enhancement, and speaker identification. We release our code and model at https://github.com/microsoft/SpeechT5.

preprint2022arXiv

Spinodal Enhancement of Light Nuclei Yield Ratio in Relativistic Heavy Ion Collisions

Using a relativistic transport model to describe the evolution of the quantum chromodynamic matter produced in Au+Au collisions at $\sqrt{s_{NN}}=3-200$ GeV, we study the effect of a first-order phase transition in the equation of state of this matter on the yield ratio $N_tN_p/ N_d^2$ ($tp/d^2$) of produced proton ($p$), deuteron ($d$), and triton ($t$). We find that the large density inhomogeneities generated by the spinodal instability during the first-order phase transition can survive the fast expansion of the subsequent hadronic matter and lead to an enhanced $tp/d^2$ in central collisions at $\sqrt{s_{NN}}=3-5$ GeV as seen in the experiments by the STAR Collaboration and the E864 Collaboration. However, this enhancement subsides with increasing collision centrality, and the resulting almost flat centrality dependence of $tp/d^2$ at $\sqrt{s_{NN}}=3$ GeV can also be used as a signal for the first-order phase transition.

preprint2022arXiv

Supervised ML Solution for Band Assignment in Dual-Band Systems with Omnidirectional and Directional Antennas

Many wireless networks, including 5G NR (New Radio) and future beyond 5G cellular systems, are expected to operate on multiple frequency bands. This paper considers the band assignment (BA) problem in dual-band systems, where the basestation (BS) chooses one of the two available frequency bands (centimeter-wave and millimeter-wave bands) to communicate with the user equipment (UE). While the millimeter-wave band might offer higher data rate, there is a significant probability of outage during which the communication should be carried on the (more reliable) centimeter-wave band. With mobility, the BA can be perceived as a sequential problem, where the BS uses previously observed information to predict the best band for a future time step. We formulate the BA as a binary classification problem and propose supervised Machine Learning (ML) solutions. We study the problem when both the BS and the UE use (i) omnidirectional antennas and (ii) both use directional antennas. In the omnidirectional case, we derive analytical benchmark solutions based on the Gaussian Process (GP) assumption for the inter-band shadow fading. In the directional case, where the labeling is shown to be complex, we propose an efficient labeling approach based on the Viterbi Algorithm (VA). We compare the performances for two channel models: (i) a stochastic channel and (ii) a ray-tracing based channel.

preprint2022arXiv

Tailoring Quadrupole Topological Insulators with Periodic Driving and Disorder

The quadrupole topological insulator (QTI) has attracted intense studies as a prototype of symmetry-protected higher-order topological phases of matter with a quantized quadrupole moment. The realization of QTIs has been reported in various static settings with periodic structures. Here, we theoretically investigate topological phase transitions and establish the QTI phase in a periodically driven system with disorder. In the clean limit, the Floquet QTI phase emerges from a topologically trivial band structure driven by elliptically polarized irradiation. More strikingly, starting from a pure and static system with trivial topology, we unveil an intriguing QTI phase which necessitates the simultaneous presence of disorder and periodic driving. Furthermore, we reveal that particle-hole symmetry is sufficient to protect the QTI. Our work not only establishes a new strategy to design QTIs but also enriches the symmetry-protected mechanism of higher-order topology.

preprint2022arXiv

The generality of uncooperative and cooperative effects in elementary hydrogen-bonded systems

The cooperative effect plays a significant role in understanding the intermolecular donor-acceptor interactions of hydrogen bonds (H-bonds, D-H...A). Herein, using the benchmark method of high-precision ab initio, the well-known cooperative effect is reproduced in elementary H-bonded systems with different D and A atoms. That is, with the decreasing of intermolecular distance, the D-H bond length first increases and then decreases, while the H...A bond length decreases. On the contrary, when D and A are the same, as the intermolecular distance decreases, the D-H bond length decreases without increasing, which is referred to as the uncooperative effect. Further analyses conclude that compared to cooperative H-bonded systems, uncooperative systems at their respective equilibrium position have a larger core-valence bifurcation (CVB) index (>0.022) and lower binding energies (<0.25 eV), showing a clear linear inverse relationship related to H-bond strength. Therefore, the intermolecular non-H-bonding interactions are predicted to reflect the uncooperative characteristics, which is confirmed by high-precision ab initio calculations. These findings provide a direction for the comprehensive understanding of H-bonds.

preprint2022arXiv

TOSE: A Fast Capacity Estimation Algorithm Based on Spike Approximations

Capacity is one of the most important performance metrics for wireless communication networks. It describes the maximum rate at which the information can be transmitted of a wireless communication system. To support the growing demand for wireless traffic, wireless networks are becoming more dense and complicated, leading to a higher difficulty to derive the capacity. Unfortunately, most existing methods for the capacity calculation take a polynomial time complexity. This will become unaffordable for future ultra-dense networks, where both the number of base stations (BSs) and the number of users are extremely large. In this paper, we propose a fast algorithm TOSE to estimate the capacity for ultra-dense wireless networks. Based on the spiked model of random matrix theory (RMT), our algorithm can avoid the exact eigenvalue derivations of large dimensional matrices, which are complicated and inevitable in conventional capacity calculation methods. Instead, fast eigenvalue estimations can be realized based on the spike approximations in our TOSE algorithm. Our simulation results show that TOSE is an accurate and fast capacity approximation algorithm. Its estimation error is below 5%, and it runs in linear time, which is much lower than the polynomial time complexity of existing methods. In addition, TOSE has superior generality, since it is independent of the distributions of BSs and users, and the shape of network areas.

preprint2022arXiv

Transport Model Comparison Studies of Intermediate-Energy Heavy-Ion Collisions

Transport models are the main method to obtain physics information from low to relativistic-energy heavy-ion collisions. The Transport Model Evaluation Project (TMEP) has been pursued to test the robustness of transport model predictions in reaching consistent conclusions from the same type of physical model. Calculations under controlled conditions of physical input and set-up were performed with various participating codes. These included both calculations of nuclear matter in a box with periodic boundary conditions, and more realistic calculations of heavy-ion collisions. In this intermediate review, we summarize and discuss the present status of the project. We also provide condensed descriptions of the 26 participating codes, which contributed to some part of the project. These include the major codes in use today. We review the main results of the studies completed so far. They show, that in box calculations the differences between the codes can be well understood and a convergence of the results can be reached. These studies also highlight the systematic differences between the two families of transport codes, known as BUU and QMD type codes. However, when the codes were compared in full heavy-ion collisions using different physical models, as recently for pion production, they still yielded substantially different results. This calls for further comparisons of heavy-ion collisions with controlled models and of box comparisons of important ingredients, like momentum-dependent fields, which are currently underway. We often indicate improved strategies in performing transport simulations and thus provide guidance to code developers. Results of transport simulations of heavy-ion collisions from a given code will have more significance if the code can be validated against benchmark calculations such as the ones summarized in this review.

preprint2022arXiv

TRT-ViT: TensorRT-oriented Vision Transformer

We revisit the existing excellent Transformers from the perspective of practical application. Most of them are not even as efficient as the basic ResNets series and deviate from the realistic deployment scenario. It may be due to the current criterion to measure computation efficiency, such as FLOPs or parameters is one-sided, sub-optimal, and hardware-insensitive. Thus, this paper directly treats the TensorRT latency on the specific hardware as an efficiency metric, which provides more comprehensive feedback involving computational capacity, memory cost, and bandwidth. Based on a series of controlled experiments, this work derives four practical guidelines for TensorRT-oriented and deployment-friendly network design, e.g., early CNN and late Transformer at stage-level, early Transformer and late CNN at block-level. Accordingly, a family of TensortRT-oriented Transformers is presented, abbreviated as TRT-ViT. Extensive experiments demonstrate that TRT-ViT significantly outperforms existing ConvNets and vision Transformers with respect to the latency/accuracy trade-off across diverse visual tasks, e.g., image classification, object detection and semantic segmentation. For example, at 82.7% ImageNet-1k top-1 accuracy, TRT-ViT is 2.7$\times$ faster than CSWin and 2.0$\times$ faster than Twins. On the MS-COCO object detection task, TRT-ViT achieves comparable performance with Twins, while the inference speed is increased by 2.8$\times$.

preprint2022arXiv

Turning Channel Noise into an Accelerator for Over-the-Air Principal Component Analysis

Recently years, the attempts on distilling mobile data into useful knowledge has been led to the deployment of machine learning algorithms at the network edge. Principal component analysis (PCA) is a classic technique for extracting the linear structure of a dataset, which is useful for feature extraction and data compression. In this work, we propose the deployment of distributed PCA over a multi-access channel based on the algorithm of stochastic gradient descent to learn the dominant feature space of a distributed dataset at multiple devices. Over-the-air aggregation is adopted to reduce the multi-access latency, giving the name over-the-air PCA. The novelty of this design lies in exploiting channel noise to accelerate the descent in the region around each saddle point encountered by gradient descent, thereby increasing the convergence speed of over-the-air PCA. The idea is materialized by proposing a power-control scheme which detects the type of descent region and controlling the level of channel noise accordingly. The scheme is proved to achieve a faster convergence rate than in the case without power control.

preprint2022arXiv

Uniform Object Rearrangement: From Complete Monotone Primitives to Efficient Non-Monotone Informed Search

Object rearrangement is a widely-applicable and challenging task for robots. Geometric constraints must be carefully examined to avoid collisions and combinatorial issues arise as the number of objects increases. This work studies the algorithmic structure of rearranging uniform objects, where robot-object collisions do not occur but object-object collisions have to be avoided. The objective is minimizing the number of object transfers under the assumption that the robot can manipulate one object at a time. An efficiently computable decomposition of the configuration space is used to create a "region graph", which classifies all continuous paths of equivalent collision possibilities. Based on this compact but rich representation, a complete dynamic programming primitive DFSDP performs a recursive depth first search to solve monotone problems quickly, i.e., those instances that do not require objects to be moved first to an intermediate buffer. DFSDP is extended to solve single-buffer, non-monotone instances, given a choice of an object and a buffer. This work utilizes these primitives as local planners in an informed search framework for more general, non-monotone instances. The search utilizes partial solutions from the primitives to identify the most promising choice of objects and buffers. Experiments demonstrate that the proposed solution returns near-optimal paths with higher success rate, even for challenging non-monotone instances, than other leading alternatives.

preprint2022arXiv

Unique quantum impurity states driven by a vortex in topological superconductors

The interplay of magnetic impurity and vortex in a topological superconductor is of fundamental interest with major implications for implementing quantum computation. There are multiple degrees of freedom interacting with the impurity in the system, including the Majorana zero mode (MZM), the Caroli de Gennes Matricon (CdGM) states, and the electron bulk states that form Cooper pairs, which makes the impurity pinned vortex state elusive to date in topological superconductors. Here, we present an accurate solution of the problem, based on a generalized mapping scheme and the density-matrix renormalization group (DMRG) method. We identify in-gap states that are distinct from the established Yu-Shiba-Rusinov (YSR) states. The newly found in-gap physics is driven by three prominent mechanisms: (i) the coupling of impurity and bulk states leading to competition between Kondo screening and Cooper pairing, resulting in a singlet-doublet quantum phase transition, (ii) the coupling of impurity and CdGM states introducing an effective Zeeman splitting to the doublet state, and (iii) the coupling of impurity and MZM turning the singlet-doublet transition into a crossover. These mechanisms cooperatively produce a unique spin-resolved local density of states. Despite the MZM, a robust nearly zero-energy peak is generated, with comparable height but opposite spin polarization as that of the MZM. These results signify novel emergent physics and offer insights to elucidate intriguing experimental phenomena.

preprint2022arXiv

Unveiling the dynamics of nucleosynthesis in relativistic heavy-ion collisions

Like nucleosynthesis during the early universe, light nuclei are also produced in relativistic heavy-ion collisions. Although the deuteron ($d$) yields in these collisions can be well described by the statistical hadronization model (SHM), which assumes that particle yields are fixed at a common chemical freezeout near the phase boundary between the quark-gluon plasma and the hadron gas, the recently measured triton ($^3\text{H}$) yields in Au+Au collisions at $\sqrt{s_{NN}}=7.7-200$ GeV are overestimated systematically by this model. Here, we develop a comprehensive kinetic approach to study the effects of hadronic re-scatterings, such as $πNN\leftrightarrowπd$ and $πNNN\leftrightarrowπ^3\text{H}~(^3\text{He})$, on $d$, $^3\text{H}$, and $^3\text{He}$ production in these collisions. We find that these reactions have little effects on the deuteron yield but reduce the $^3\text{H}$ and $^3\text{He}$ yields by about a factor of 1.8 from their initial values given by the SHM. This finding helps resolve the overestimation of triton production in the SHM and provides the evidence for hadronic re-scattering effects on nucleosynthesis in relativistic heavy-ion collisions.

preprint2022arXiv

Using Autoencoders on Differentially Private Federated Learning GANs

Machine learning has been applied to almost all fields of computer science over the past decades. The introduction of GANs allowed for new possibilities in fields of medical research and text prediction. However, these new fields work with ever more privacy-sensitive data. In order to maintain user privacy, a combination of federated learning, differential privacy and GANs can be used to work with private data without giving away a users' privacy. Recently, two implementations of such combinations have been published: DP-Fed-Avg GAN and GS-WGAN. This paper compares their performance and introduces an alternative version of DP-Fed-Avg GAN that makes use of denoising techniques to combat the loss in accuracy that generally occurs when applying differential privacy and federated learning to GANs. We also compare the novel adaptation of denoised DP-Fed-Avg GAN to the state-of-the-art implementations in this field.

preprint2022arXiv

Variational Hierarchical Directed Bounding Box Construction for Solid Mesh Models

Object oriented bounding box tree (OBB-Tree for short) has many applications in collision detection, real-time rendering, etc. It has a wide range of applications. The construction of the hierarchical directed bounding box of the solid mesh model is studied, and a new optimization solution method is proposed. But this part of the external space volume that does not belong to the solid mesh model is used as the error, and an error calculation method based on hardware acceleration is given. Secondly, the hierarchical bounding box construction problem is transformed into a variational approximation problem, and the optimal hierarchical directed bounding box is obtained by solving the global error minimum. In the optimization calculation, we propose that combining Lloyd clustering iteration in the same layer and MultiGrid-like reciprocating iteration between layers. Compared with previous results, this method can generate aired original solid mesh models are more tightly packed with hierarchical directed bounding box approximation. In the practical application of collision detection, the results constructed using this method can reduce the computational time of collision detection and improve detection efficiency.

preprint2022arXiv

Video Mobile-Former: Video Recognition with Efficient Global Spatial-temporal Modeling

Transformer-based models have achieved top performance on major video recognition benchmarks. Benefiting from the self-attention mechanism, these models show stronger ability of modeling long-range dependencies compared to CNN-based models. However, significant computation overheads, resulted from the quadratic complexity of self-attention on top of a tremendous number of tokens, limit the use of existing video transformers in applications with limited resources like mobile devices. In this paper, we extend Mobile-Former to Video Mobile-Former, which decouples the video architecture into a lightweight 3D-CNNs for local context modeling and a Transformer modules for global interaction modeling in a parallel fashion. To avoid significant computational cost incurred by computing self-attention between the large number of local patches in videos, we propose to use very few global tokens (e.g., 6) for a whole video in Transformers to exchange information with 3D-CNNs with a cross-attention mechanism. Through efficient global spatial-temporal modeling, Video Mobile-Former significantly improves the video recognition performance of alternative lightweight baselines, and outperforms other efficient CNN-based models at the low FLOP regime from 500M to 6G total FLOPs on various video recognition tasks. It is worth noting that Video Mobile-Former is the first Transformer-based video model which constrains the computational budget within 1G FLOPs.

preprint2022arXiv

VU-BERT: A Unified framework for Visual Dialog

The visual dialog task attempts to train an agent to answer multi-turn questions given an image, which requires the deep understanding of interactions between the image and dialog history. Existing researches tend to employ the modality-specific modules to model the interactions, which might be troublesome to use. To fill in this gap, we propose a unified framework for image-text joint embedding, named VU-BERT, and apply patch projection to obtain vision embedding firstly in visual dialog tasks to simplify the model. The model is trained over two tasks: masked language modeling and next utterance retrieval. These tasks help in learning visual concepts, utterances dependence, and the relationships between these two modalities. Finally, our VU-BERT achieves competitive performance (0.7287 NDCG scores) on VisDial v1.0 Datasets.

preprint2022arXiv

Weyl nodes with higher-order topology in an optically driven nodal-line semimetal

Creating and manipulating topological states is a key goal of condensed matter physics. Periodic driving offers a powerful method to manipulate electronic states, and even to create topological states in solids. Here, we investigate the tunable Floquet states in a periodically driven higher-order nodal line semimetal with both spatial inversion and time-reversal symmetries. We found that the Floquet Weyl semimetal states, which support both one-dimensional hinge Fermi arc and two-dimensional surface Fermi arc states, can be induced in the higher-order nodal-line semimetal by shining circularly polarized light. Moreover, we show that the location of Weyl nodes and the curvature of surface Fermi arcs can be tuned by adjusting the propagation direction and incident angle of light.

preprint2022arXiv

WikiDiverse: A Multimodal Entity Linking Dataset with Diversified Contextual Topics and Entity Types

Multimodal Entity Linking (MEL) which aims at linking mentions with multimodal contexts to the referent entities from a knowledge base (e.g., Wikipedia), is an essential task for many multimodal applications. Although much attention has been paid to MEL, the shortcomings of existing MEL datasets including limited contextual topics and entity types, simplified mention ambiguity, and restricted availability, have caused great obstacles to the research and application of MEL. In this paper, we present WikiDiverse, a high-quality human-annotated MEL dataset with diversified contextual topics and entity types from Wikinews, which uses Wikipedia as the corresponding knowledge base. A well-tailored annotation procedure is adopted to ensure the quality of the dataset. Based on WikiDiverse, a sequence of well-designed MEL models with intra-modality and inter-modality attentions are implemented, which utilize the visual information of images more adequately than existing MEL models do. Extensive experimental analyses are conducted to investigate the contributions of different modalities in terms of MEL, facilitating the future research on this task. The dataset and baseline models are available at https://github.com/wangxw5/wikiDiverse.

preprint2021arXiv

Bayesian User Localization and Tracking for Reconfigurable Intelligent Surface Aided MIMO Systems

In this paper, we study the user localization and tracking problem in the reconfigurable intelligent surface (RIS) aided multiple-input multiple-output (MIMO) system, where a multi-antenna base station (BS) and multiple RISs are deployed to assist the localization and tracking of a multi-antenna user. By establishing a probability transition model for user mobility, we develop a message-passing algorithm, termed the Bayesian user localization and tracking (BULT) algorithm, to estimate and track the user position and the angle-of-arrival (AoAs) at the user in an online fashion. We also derive Bayesian Cramér Rao bound (BCRB) to characterize the fundamental performance limit of the considered tracking problem. To improve the tracking performance, we optimize the beamforming design at the BS and the RISs to minimize the derived BCRB. Simulation results show that our BULT algorithm can perform close to the derived BCRB, and significantly outperforms the counterpart algorithms without exploiting the temporal correlation of the user location.

preprint2021arXiv

Blockchain-Based Federated Learning in Mobile Edge Networks with Application in Internet of Vehicles

The rapid increase of the data scale in Internet of Vehicles (IoV) system paradigm, hews out new possibilities in boosting the service quality for the emerging applications through data sharing. Nevertheless, privacy concerns are major bottlenecks for data providers to share private data in traditional IoV networks. To this end, federated learning (FL) as an emerging learning paradigm, where data providers only send local model updates trained on their local raw data rather than upload any raw data, has been recently proposed to build a privacy-preserving data sharing models. Unfortunately, by analyzing on the differences of uploaded local model updates from data providers, private information can still be divulged, and performance of the system cannot be guaranteed when partial federated nodes executes malicious behavior. Additionally, traditional cloud-based FL poses challenges to the communication overhead with the rapid increase of terminal equipment in IoV system. All these issues inspire us to propose an autonomous blockchain empowered privacy-preserving FL framework in this paper, where the mobile edge computing (MEC) technology was naturally integrated in IoV system.

preprint2021arXiv

Cache Placement Optimization in Mobile Edge Computing Networks with Unaware Environment -- An Extended Multi-armed Bandit Approach

Caching high-frequency reuse contents at the edge servers in the mobile edge computing (MEC) network omits the part of backhaul transmission and further releases the pressure of data traffic. However, how to efficiently decide the caching contents for edge servers is still an open problem, which refers to the cache capacity of edge servers, the popularity of each content, and the wireless channel quality during transmission. In this paper, we discuss the influence of unknown user density and popularity of content on the cache placement solution at the edge server. Specifically, towards the implementation of the cache placement solution in the practical network, there are two problems needing to be solved. First, the estimation of unknown users' preference needs a huge amount of records of users' previous requests. Second, the overlapping serving regions among edge servers cause the wrong estimation of users' preference, which hinders the individual decision of caching placement. To address the first issue, we propose a learning-based solution to adaptively optimize the cache placement policy. We develop the extended multi-armed bandit (Extended MAB), which combines the generalized global bandit (GGB) and Standard Multi-armed bandit (MAB). For the second problem, a multi-agent Extended MAB-based solution is presented to avoid the mis-estimation of parameters and achieve the decentralized cache placement policy. The proposed solution determines the primary time slot and secondary time slot for each edge server. The proposed strategies are proven to achieve the bounded regret according to the mathematical analysis. Extensive simulations verify the optimality of the proposed strategies when comparing with baselines.

preprint2021arXiv

Color Contrast Enhanced Rendering for Optical See-through Head-mounted Displays

Most commercially available optical see-through head-mounted displays (OST-HMDs) utilize optical combiners to simultaneously visualize the physical background and virtual objects. The displayed images perceived by users are a blend of rendered pixels and background colors. Enabling high fidelity color perception in mixed reality (MR) scenarios using OST-HMDs is an important but challenging task. We propose a real-time rendering scheme to enhance the color contrast between virtual objects and the surrounding background for OST-HMDs. Inspired by the discovery of color perception in psychophysics, we first formulate the color contrast enhancement as a constrained optimization problem. We then design an end-to-end algorithm to search the optimal complementary shift in both chromaticity and luminance of the displayed color. This aims at enhancing the contrast between virtual objects and the real background as well as keeping the consistency with the original color. We assess the performance of our approach using a simulated OST-HMD environment and an off-the-shelf OST-HMD. Experimental results from objective evaluations and subjective user studies demonstrate that the proposed approach makes rendered virtual objects more distinguishable from the surrounding background, thereby bringing a better visual experience.

preprint2021arXiv

Deep reinforcement learning for universal quantum state preparation via dynamic pulse control

Accurate and efficient preparation of quantum state is a core issue in building a quantum computer. In this paper, we investigate how to prepare a certain single- or two-qubit target state from arbitrary initial states in semiconductor double quantum dots with the aid of deep reinforcement learning. Our method is based on the training of the network over numerous preparing tasks. The results show that once the network is well trained, it works for any initial states in the continuous Hilbert space. Thus repeated training for new preparation tasks is avoided. Our scheme outperforms the traditional optimization approaches based on gradient with both the higher designing efficiency and the preparation quality in discrete control space. Moreover, we find that the control trajectories designed by our scheme are robust against static and dynamic fluctuations, such as charge and nuclear noises.

preprint2021arXiv

Electric and magnetic fields tuned spin-polarized topological phases in two-dimensional ferromagnetic MnBi$_4$Te$_7$

Applying electric or magnetic fields is widely used to not only create and manipulate topological states but also facilitate their observations in experiments. In this work, we show by first-principles calculations and topological analysis that the time-reversal (TR) symmetry-broken quantum spin Hall (QSH) state emerges in a two-dimensional ferromagnetic MnBi$_4$Te$_7$ monolayer. This TR-symmetry broken QSH phase possesses a highly tunable nontrivial band gap under an external electric field (or tuning interlayer distance). Furthermore, based on the Wannier-function-based tight-binding approach, we reveal that a topological phase transition from the TR-symmetry broken QSH phase to the quantum anomalous Hall (QAH) phase occurs with the increase of magnetic fields. Besides, we also find that a reverse electric fields can facilitate the realization of QAH phase. Our work not only uncovers the ferromagnetic topological properties the MnBi$_4$Te$_7$ monolayer tuned by electric and magnetic fields, but also can stimulate further applications to spintronics and topological devices.

preprint2021arXiv

Floquet Valley-Polarized Quantum Anomalous Hall State in Nonmagnetic Heterobilayers

The valley-polarized quantum anomalous Hall (VQAH) state, which forwards a strategy for combining valleytronics and spintronics with nontrivial topology, attracts intensive interest in condensed-matter physics. So far, the explored VQAH states have still been limited to magnetic systems. Here, using the low-energy effective model and Floquet theorem, we propose a different mechanism to realize the Floquet VQAH state in nonmagnetic heterobilayers under light irradiation. We then realize this proposal via first-principles calculations in transition metal dichalcogenide heterobilayers, which initially possess the time-reversal invariant valley quantum spin Hall (VQSH) state. By irradiating circularly polarized light, the time-reversal invariant VQSH state can evolve into the VQAH state, behaving as an optically switchable topological spin-valley filter. These findings not only offer a rational scheme to realize the VQAH state without magnetic orders, but also pave a fascinating path for designing topological spintronic and valleytronic devices.

preprint2021arXiv

Hierarchical Reinforcement Learning for Relay Selection and Power Optimization in Two-Hop Cooperative Relay Network

Cooperative communication is an effective approach to improve spectrum utilization. In order to reduce outage probability of communication system, most studies propose various schemes for relay selection and power allocation, which are based on the assumption of channel state information (CSI). However, it is difficult to get an accurate CSI in practice. In this paper, we study the outage probability minimizing problem subjected to a total transmission power constraint in a two-hop cooperative relay network. We use reinforcement learning (RL) methods to learn strategies for relay selection and power allocation, which do not need any prior knowledge of CSI but simply rely on the interaction with communication environment. It is noted that conventional RL methods, including most deep reinforcement learning (DRL) methods, cannot perform well when the search space is too large. Therefore, we first propose a DRL framework with an outage-based reward function, which is then used as a baseline. Then, we further propose a hierarchical reinforcement learning (HRL) framework and training algorithm. A key difference from other RL-based methods in existing literatures is that, our proposed HRL approach decomposes relay selection and power allocation into two hierarchical optimization objectives, which are trained in different levels. With the simplification of search space, the HRL approach can solve the problem of sparse reward, while the conventional RL method fails. Simulation results reveal that compared with traditional DRL method, the HRL training algorithm can reach convergence 30 training iterations earlier and reduce the outage probability by 5% in two-hop relay network with the same outage threshold.

preprint2021arXiv

Joint Location and Communication Study for Intelligent Reflecting Surface Aided Wireless Communication System

Intelligent reflecting surface (IRS) is a novel burgeoning concept, which possesses advantages in enhancing wireless communication and user localization, while maintaining low hardware cost and energy consumption. Herein, we establish an IRS-aided mmWave-MIMO based joint localization and communication system (IMM-JLCS), and probe into its performance evaluation and optimization design. Specifically, first, we provide the signal, channel and estimation error models, and contrive the working process of the IMM-JLCS in detail. Then, by configuring appropriate IRS phase shifts, we derive the closed-form expressions of the Cramer-Rao Lower Bound (CRLB) of the position/orientation estimation errors and the effective achievable data rate (EADR), with respect to the time allocation ratio of the beam alignment and localization stage (BALS). Subsequently, we investigate the trade-off between the two performance metrics, for which we propose a joint optimization algorithm. Finally, we carry out simulations and comparisons to view the trade-off and validate the effectiveness of the proposed algorithm, in the presence of distinct levels of estimation uncertainty and user mobility. Our results demonstrate that the proposed algorithm can find the joint optimal solution for the position/orientation estimation accuracy and EADR, with its optimization performance being robust to slight localization or channel estimation errors and user mobility.

preprint2021arXiv

LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search

Text to speech (TTS) has been broadly used to synthesize natural and intelligible speech in different scenarios. Deploying TTS in various end devices such as mobile phones or embedded devices requires extremely small memory usage and inference latency. While non-autoregressive TTS models such as FastSpeech have achieved significantly faster inference speed than autoregressive models, their model size and inference latency are still large for the deployment in resource constrained devices. In this paper, we propose LightSpeech, which leverages neural architecture search~(NAS) to automatically design more lightweight and efficient models based on FastSpeech. We first profile the components of current FastSpeech model and carefully design a novel search space containing various lightweight and potentially effective architectures. Then NAS is utilized to automatically discover well performing architectures within the search space. Experiments show that the model discovered by our method achieves 15x model compression ratio and 6.5x inference speedup on CPU with on par voice quality. Audio demos are provided at https://speechresearch.github.io/lightspeech.

preprint2021arXiv

Magnetic field induced Valley-Polarized Quantum Anomalous Hall Effects in Ferromagnetic van der Waals Heterostructures

The valley-polarized quantum anomalous Hall effect (VQAHE) attracts intensive interest since it uniquely combines valleytronics and spintronics with nontrivial band topology. Here, based on first-principles calculations and Wannier-function-based tight-binding (WFTB) model, we reveal that valley-based Hall effects and especially the VQAHE induced by external magnetic fields can occur in two-dimensional (2D) ferromagnetic van der Waals heterostructures (vdWHs). The results show that considerable valley-splitting derived from the Zeeman exchange energy drives these vdWHs generating the valley anomalous Hall effect and then the VQAHE. The chiral edge states and quantized Hall conductance are utilized to confirm the presence of VQAHE. Besides, it is also found that external electric fields (or tuning interlayer distances) can facilitate the realization of VQAHE, and thus we present a phase diagram in a broad parameter regime of magnetic fields and electric fields (or interlayer distances). Our work not only offers a class of ferromagnetic vdWHs to realize various valley-based Hall phases, but also can guide advancements for designing topological devices with spin-valley filtering effects based on the VQAHE.

preprint2021arXiv

Methodology-centered review of molecular modeling, simulation, and prediction of SARS-CoV-2

The deadly coronavirus disease 2019 (COVID-19) pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has gone out of control globally. Despite much effort by scientists, medical experts, and society in general, the slow progress on drug discovery and antibody therapeutic development, the unknown possible side effects of the existing vaccines, and the high transmission rate of the SARS-CoV-2, remind us of the sad reality that our current understanding of the transmission, infectivity, and evolution of SARS-CoV-2 is unfortunately very limited. The major limitation is the lack of mechanistic understanding of viral-host cell interactions, the viral regulation, protein-protein interactions, including antibody-antigen binding, protein-drug binding, host immune response, etc. This limitation will likely haunt the scientific community for a long time and have a devastating consequence in combating COVID-19 and other pathogens. Notably, compared to the long-cycle, highly cost, and safety-demanding molecular-level experiments, the theoretical and computational studies are economical, speedy, and easy to perform. There exists a tsunami of the literature on molecular modeling, simulation, and prediction of SARS-CoV-2 that has become impossible to fully be covered in a review. To provide the reader a quick update about the status of molecular modeling, simulation, and prediction of SARS-CoV-2, we present a comprehensive and systematic methodology-centered narrative in the nick of time. Aspects such as molecular modeling, Monte Carlo (MC) methods, structural bioinformatics, machine learning, deep learning, and mathematical approaches are included in this review. This review will be beneficial to researchers who are looking for ways to contribute to SARS-CoV-2 studies and those who are assessing the current status in the field.

preprint2021arXiv

Mimicing the Kane-Mele type spin orbit interaction by spin-flexual phonon coupling in graphene devices

On the efforts of enhancing the spin orbit interaction (SOI) of graphene for seeking the dissipationless quantum spin Hall devices, unique Kane-Mele type SOI and high mobility samples are desired. However, common external decoration often introduces extrinsic Rashba-type SOI and simultaneous impurity scattering. Here we show, by the EDTA-Dy molecule decorating, the Kane-Mele type SOI is mimicked with even improved carrier mobility. It is evidenced by the suppressed weak localization at equal carrier densities and simultaneous Elliot-Yafet spin relaxation. The extracted spin scattering time is monotonically dependent on the carrier elastic scattering time, where the Elliot-Yafet plot gives the interaction strength of 3.3 meV. Improved quantum Hall plateaus can be even seen after the external operation. This is attributed to the spin-flexural phonon coupling induced by the enhanced graphene ripples, as revealed by the in-plane magnetotransport measurement.

preprint2021arXiv

On Secure Degrees of Freedom of the MIMO Interference Channel with Local Output Feedback

This paper studies the problem of sum-secure degrees of freedom (SDoF) of the (M,M,N,N) multiple-input multiple-output (MIMO) interference channel with local output feedback, so as to build an information-theoretic foundation and provide practical transmission schemes for 6G-enabled vehicles-to-vehicles (V2V). For this problem, we propose two novel transmission schemes, i.e., the interference decoding scheme and the interference alignment scheme, and thus establish a sum-SDoF lower bound. In particular, to optimize the phase duration, we analyze the security and decoding constraints and formulate a linear-fractional optimization problem. Furthermore, we show that the derived sum-SDoF lower bound is the sum-SDoF for M <= N/2, N=M, and 2N <= M antenna configurations, and reveal that for a fixed N, the optimal M to maximize the sum-SDoF is not less than 2N. Through simulations, we examine the secure sum-rate performance of proposed transmission schemes, and reveal that using local output feedback can lead to a higher secure sum-rate than that by using delayed channel state information at the transmitter.

preprint2021arXiv

Passive Beamforming Design and Channel Estimation for IRS Communication System with Few-Bit ADCs

Utilizing intelligent reflecting surface (IRS) was proven to be efficient in improving the energy efficiency for wireless networks. In this paper, we investigate the passive beamforming and channel estimation for IRS assisted wireless communications with low-resolution analog-to-digital converters (ADCs) at the receiver. We derive the approximate achievable rate by using the Bussgang theorem. Based on the derived analytical achievable rate expression, we maximize the achievable rate by using semidefinite programming (SDP), branch-and-bound (BB), and gradient-based approaches. A maximum likelihood (ML) estimator is then proposed for channel estimation by considering the $\mathrm{1}$-bit quantization ADC. Numerical result shows that the proposed beamforming design and channel estimation method significantly outperforms the existing methods.

preprint2021arXiv

Photoinduced Quantum Anomalous Hall States in the Topological Anderson Insulator

The realization of the quantum anomalous Hall (QAH) effect without magnetic doping attracts intensive interest since magnetically doped topological insulators usually possess inhomogeneity of ferromagnetic order. Here, we propose a different strategy to realize intriguing QAH states arising from the interplay of light and non-magnetic disorder in two-dimensional topologically trivial systems. By combining the Born approximation and Floquet theory, we show that a time-reversal invariant disorder-induced topological insulator, known as the topological Anderson insulator (TAI), would evolve into a time-reversal broken TAI and then into a QAH insulator by shining circularly polarized light. We utilize spin and charge Hall conductivities, which can be measured in experiments directly, to distinguish these three different topological phases. This work not only offers an exciting opportunity to realize the high-temperature QAH effect without magnetic orders, but also is important for applications of topological states to spintronics.

preprint2021arXiv

Prediction and mitigation of mutation threats to COVID-19 vaccines and antibody therapies

Antibody therapeutics and vaccines are among our last resort to end the raging COVID-19 pandemic. They, however, are prone to over 5,000 mutations on the spike (S) protein uncovered by a Mutation Tracker based on over 200,000 genome isolates. It is imperative to understand how mutations would impact vaccines and antibodies in the development. In this work, we study the mechanism, frequency, and ratio of mutations on the S protein. Additionally, we use 56 antibody structures and analyze their 2D and 3D characteristics. Moreover, we predict the mutation-induced binding free energy (BFE) changes for the complexes of S protein and antibodies or ACE2. By integrating genetics, biophysics, deep learning, and algebraic topology, we reveal that most of 462 mutations on the receptor-binding domain (RBD) will weaken the binding of S protein and antibodies and disrupt the efficacy and reliability of antibody therapies and vaccines. A list of 31 vaccine escape mutants is identified, while many other disruptive mutations are detailed as well. We also unveil that about 65\% existing RBD mutations, including those variants recently found in the United Kingdom (UK) and South Africa, are binding-strengthen mutations, resulting in more infectious COVID-19 variants. We discover the disparity between the extreme values of RBD mutation-induced BFE strengthening and weakening of the bindings with antibodies and ACE2, suggesting that SARS-CoV-2 is at an advanced stage of evolution for human infection, while the human immune system is able to produce optimized antibodies. This discovery implies the vulnerability of current vaccines and antibody drugs to new mutations. Our predictions were validated by comparison with more than 1,400 deep mutations on the S protein RBD. Our results show the urgent need to develop new mutation-resistant vaccines and antibodies and to prepare for seasonal vaccinations.

preprint2021arXiv

QoS-Driven Resource Optimization for Intelligent Fog Radio Access Network: A Dynamic Power Allocation Perspective

The fog radio access network (Fog-RAN) has been considered a promising wireless access architecture to help shorten the communication delay and relieve the large data delivery burden over the backhaul links. However, limited by conventional inflexible communication design, Fog-RAN cannot be used in some complex communication scenarios. In this study, we focus on investigating a more intelligent Fog-RAN to assist the communication in a high-speed railway environment. Due to the train's continuously moving, the communication should be designed intelligently to adapt to channel variation. Specifically, we dynamically optimize the power allocation in the remote radio heads (RRHs) to minimize the total network power cost considering multiple quality-of-service (QoS) requirements and channel variation. The impact of caching on the power allocation is considered. The dynamic power optimization is analyzed to obtain a closed-form solution in certain cases. The inherent tradeoff among the total network cost, delay and delivery content size is further discussed. To evaluate the performance of the proposed dynamic power allocation, we present an invariant power allocation counterpart as a performance comparison benchmark. The result of our simulation reveals that dynamic power allocation can significantly outperform the invariant power allocation scheme, especially with a random caching strategy or limited caching resources at the RRHs.

preprint2021arXiv

Reconfigurable Intelligent Surface Assisted Edge Machine Learning

The ever-growing popularity and rapid improving of artificial intelligence (AI) have raised rethinking on the evolution of wireless networks. Mobile edge computing (MEC) provides a natural platform for AI applications since it provides rich computation resources to train AI models, as well as low-latency access to the data generated by mobile and Internet of Things devices. In this paper, we present an infrastructure to perform machine learning tasks at an MEC server with the assistance of a reconfigurable intelligent surface (RIS). In contrast to conventional communication systems where the principal criteria are to maximize the throughput, we aim at optimizing the learning performance. Specifically, we minimize the maximum learning error of all users by jointly optimizing the beamforming vectors of the base station and the phase-shift matrix of the RIS. An alternating optimization-based framework is proposed to optimize the two terms iteratively, where closed-form expressions of the beamforming vectors are derived, and an alternating direction method of multipliers (ADMM)-based algorithm is designed together with an error level searching framework to effectively solve the nonconvex optimization problem of the phase-shift matrix. Simulation results demonstrate significant gains of deploying an RIS and validate the advantages of our proposed algorithms over various benchmarks.

preprint2021arXiv

Remote Sensing Image Super-resolution and Object Detection: Benchmark and State of the Art

For the past two decades, there have been significant efforts to develop methods for object detection in Remote Sensing (RS) images. In most cases, the datasets for small object detection in remote sensing images are inadequate. Many researchers used scene classification datasets for object detection, which has its limitations; for example, the large-sized objects outnumber the small objects in object categories. Thus, they lack diversity; this further affects the detection performance of small object detectors in RS images. This paper reviews current datasets and object detection methods (deep learning-based) for remote sensing images. We also propose a large-scale, publicly available benchmark Remote Sensing Super-resolution Object Detection (RSSOD) dataset. The RSSOD dataset consists of 1,759 hand-annotated images with 22,091 instances of very high resolution (VHR) images with a spatial resolution of ~0.05 m. There are five classes with varying frequencies of labels per class. The image patches are extracted from satellite images, including real image distortions such as tangential scale distortion and skew distortion. We also propose a novel Multi-class Cyclic super-resolution Generative adversarial network with Residual feature aggregation (MCGR) and auxiliary YOLOv5 detector to benchmark image super-resolution-based object detection and compare with the existing state-of-the-art methods based on image super-resolution (SR). The proposed MCGR achieved state-of-the-art performance for image SR with an improvement of 1.2dB PSNR compared to the current state-of-the-art NLSN method. MCGR achieved best object detection mAPs of 0.758, 0.881, 0.841, and 0.983, respectively, for five-class, four-class, two-class, and single classes, respectively surpassing the performance of the state-of-the-art object detectors YOLOv5, EfficientDet, Faster RCNN, SSD, and RetinaNet.

preprint2021arXiv

SG-Net: Syntax Guided Transformer for Language Representation

Understanding human language is one of the key themes of artificial intelligence. For language representation, the capacity of effectively modeling the linguistic knowledge from the detail-riddled and lengthy texts and getting rid of the noises is essential to improve its performance. Traditional attentive models attend to all words without explicit constraint, which results in inaccurate concentration on some dispensable words. In this work, we propose using syntax to guide the text modeling by incorporating explicit syntactic constraints into attention mechanisms for better linguistically motivated word representations. In detail, for self-attention network (SAN) sponsored Transformer-based encoder, we introduce syntactic dependency of interest (SDOI) design into the SAN to form an SDOI-SAN with syntax-guided self-attention. Syntax-guided network (SG-Net) is then composed of this extra SDOI-SAN and the SAN from the original Transformer encoder through a dual contextual architecture for better linguistics inspired representation. The proposed SG-Net is applied to typical Transformer encoders. Extensive experiments on popular benchmark tasks, including machine reading comprehension, natural language inference, and neural machine translation show the effectiveness of the proposed SG-Net design.

preprint2021arXiv

Text Compression-aided Transformer Encoding

Text encoding is one of the most important steps in Natural Language Processing (NLP). It has been done well by the self-attention mechanism in the current state-of-the-art Transformer encoder, which has brought about significant improvements in the performance of many NLP tasks. Though the Transformer encoder may effectively capture general information in its resulting representations, the backbone information, meaning the gist of the input text, is not specifically focused on. In this paper, we propose explicit and implicit text compression approaches to enhance the Transformer encoding and evaluate models using this approach on several typical downstream tasks that rely on the encoding heavily. Our explicit text compression approaches use dedicated models to compress text, while our implicit text compression approach simply adds an additional module to the main model to handle text compression. We propose three ways of integration, namely backbone source-side fusion, target-side fusion, and both-side fusion, to integrate the backbone information into Transformer-based models for various downstream tasks. Our evaluation on benchmark datasets shows that the proposed explicit and implicit text compression approaches improve results in comparison to strong baselines. We therefore conclude, when comparing the encodings to the baseline models, text compression helps the encoders to learn better language representations.

preprint2021arXiv

Unsupervised heart abnormality detection based on phonocardiogram analysis with Beta Variational Auto-Encoders

Heart Sound (also known as phonocardiogram (PCG)) analysis is a popular way that detects cardiovascular diseases (CVDs). Most PCG analysis uses supervised way, which demands both normal and abnormal samples. This paper proposes a method of unsupervised PCG analysis that uses beta variational auto-encoder ($β-\text{VAE}$) to model the normal PCG signals. The best performed model reaches an AUC (Area Under Curve) value of 0.91 in ROC (Receiver Operating Characteristic) test for PCG signals collected from the same source. Unlike majority of $β-\text{VAE}$s that are used as generative models, the best-performed $β-\text{VAE}$ has a $β$ value smaller than 1. Further experiments then find that the introduction of a light weighted KL divergence between distribution of latent space and normal distribution improves the performance of anomaly PCG detection based on anomaly scores resulted by reconstruction loss. The fact suggests that anomaly score based on reconstruction loss may be better than anomaly scores based on latent vectors of samples

preprint2020arXiv

Accurate Word Representations with Universal Visual Guidance

Word representation is a fundamental component in neural language understanding models. Recently, pre-trained language models (PrLMs) offer a new performant method of contextualized word representations by leveraging the sequence-level context for modeling. Although the PrLMs generally give more accurate contextualized word representations than non-contextualized models do, they are still subject to a sequence of text contexts without diverse hints for word representation from multimodality. This paper thus proposes a visual representation method to explicitly enhance conventional word embedding with multiple-aspect senses from visual guidance. In detail, we build a small-scale word-image dictionary from a multimodal seed dataset where each word corresponds to diverse related images. The texts and paired images are encoded in parallel, followed by an attention layer to integrate the multimodal representations. We show that the method substantially improves the accuracy of disambiguation. Experiments on 12 natural language understanding and machine translation tasks further verify the effectiveness and the generalization capability of the proposed approach.

preprint2020arXiv

Achievable DoF Regions of Three-User MIMO Broadcast Channel with Delayed CSIT

For the two-user multiple-input multiple-output (MIMO) broadcast channel with delayed channel state information at the transmitter (CSIT) and arbitrary antenna configurations, all the degrees-of-freedom (DoF) regions are obtained. However, for the three-user MIMO broadcast channel with delayed CSIT and arbitrary antenna configurations, the DoF region of order-2 messages is still unclear and only a partial achievable DoF region of order-1 messages is obtained, where the order-2 messages and order-1 messages are desired by two receivers and one receiver, respectively. In this paper, for the three-user MIMO broadcast channel with delayed CSIT and arbitrary antenna configurations, we first design transmission schemes for order-2 messages and order-1 messages. Next, we propose to analyze the achievable DoF region of transmission scheme by transformation approach. In particular, we transform the decoding condition of transmission scheme w.r.t. phase duration into the achievable DoF region w.r.t. achievable DoF, through achievable DoF tuple expression connecting phase duration and achievable DoF. As a result, the DoF region of order-2 messages is characterized and an achievable DoF region of order-1 messages is completely expressed. Besides, for order-1 messages, we derive the sufficient condition, under which the proposed achievable DoF region is the DoF region.

preprint2020arXiv

Angle Aware User Cooperation for Secure Massive MIMO in Rician Fading Channel

Massive multiple-input multiple-output communications can achieve high-level security by concentrating radio frequency signals towards the legitimate users. However, this system is vulnerable in a Rician fading environment if the eavesdropper positions itself such that its channel is highly "similar" to the channel of a legitimate user. To address this problem, this paper proposes an angle aware user cooperation (AAUC) scheme, which avoids direct transmission to the attacked user and relies on other users for cooperative relaying. The proposed scheme only requires the eavesdropper's angle information, and adopts an angular secrecy model to represent the average secrecy rate of the attacked system. With this angular model, the AAUC problem turns out to be nonconvex, and a successive convex optimization algorithm, which converges to a Karush-Kuhn-Tucker solution, is proposed. Furthermore, a closed-form solution and a Bregman first-order method are derived for the cases of large-scale antennas and large-scale users, respectively. Extension to the intelligent reflecting surfaces based scheme is also discussed. Simulation results demonstrate the effectiveness of the proposed successive convex optimization based AAUC scheme, and also validate the low-complexity nature of the proposed large-scale optimization algorithms.

preprint2020arXiv

Channel Estimation and Power Scaling Law of Large Reflecting Surface with Non-Ideal Hardware

Large reflecting surface (LRS) has emerged as a new solution to improve the energy and spectrum efficiency of wireless communication system. Most existing studies were conducted with an assumption of ideal hardware, and the impact of hardware impairments receives little attention. However, the non-negligible hardware impairments should be taken into consideration when we evaluate the system performance. In this paper, we consider an LRS assisted communication system with hardware impairments, and focus on the channel estimation study and the power scaling law analysis. First, with linear minimum mean square error estimation, we theoretically characterize the relationship between channel estimation performance and impairment level, number of reflecting elements, and pilot power. After that, we analyze the power scaling law and reveal that if the base station (BS) has perfect channel state information, the transmit power of user can be made inversely proportional to the number of BS antennas and the square of the number of reflecting elements with no reduction in performance; If the BS has imperfectly estimated channel state information, to achieve the same performance, the transmit power of user can be made inversely proportional to the square-root of the number of BS antennas and the square of the number of reflecting elements.

preprint2020arXiv

Characterizing SARS-CoV-2 mutations in the United States

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has been mutating since it was first sequenced in early January 2020. The genetic variants have developed into a few distinct clusters with different properties. Since the United States (US) has the highest number of viral infected patients globally, it is essential to understand the US SARS-CoV-2. Using genotyping, sequence-alignment, time-evolution, $k$-means clustering, protein-folding stability, algebraic topology, and network theory, we reveal that the US SARS-CoV-2 has four substrains and five top US SARS-CoV-2 mutations were first detected in China (2 cases), Singapore (2 cases), and the United Kingdom (1 case). The next three top US SARS-CoV-2 mutations were first detected in the US. These eight top mutations belong to two disconnected groups. The first group consisting of 5 concurrent mutations is prevailing, while the other group with three concurrent mutations gradually fades out. Our analysis suggests that female immune systems are more active than those of males in responding to SARS-CoV-2 infections. We identify that one of the top mutations, 27964C$>$T-(S24L) on ORF8, has an unusually strong gender dependence. Based on the analysis of all mutations on the spike protein, we further uncover that three of four US SASR-CoV-2 substrains become more infectious. Our study calls for effective viral control and containing strategies in the US.

preprint2020arXiv

Constraining the in-medium nucleon-nucleon cross section from the width of nuclear giant dipole resonance

We develop a new lattice Hamiltonian method for solving the Boltzmann-Uehling-Uhlenbeck (BUU) equation. Adopting the stochastic approach to treat the collision term and using the GPU parallel computing to carry out the calculations allows for a rather high accuracy in evaluating the collision term, especially its Pauli blocking, leading thus to a new level of precision in solving the BUU equation. Applying this lattice BUU method to study the width of giant dipole resonance (GDR) in nuclei, where the accurate treatment of the collision term is crucial, we find that the obtained GDR width of $^{208}{\rm Pb}$ shows a strong dependence on the in-medium nucleon-nucleon cross section $σ_{\rm NN}^*$. A very large medium reduction of $σ_{\rm NN}^*$ is needed to reproduce the measured value of the GDR width of $^{208}{\rm Pb}$ at the Research Center for Nuclear Physics in Osaka, Japan.

preprint2020arXiv

Cooperative Multi-Point Vehicular Positioning Using Millimeter-Wave Surface Reflection (Extended version)

Multi-point vehicular positioning is one essential operation for autonomous vehicles. However, the state-of-the-art positioning technologies, relying on reflected signals from a target (i.e., RADAR and LIDAR), cannot work without line-of-sight. Besides, it takes significant time for environment scanning and object recognition with potential detection inaccuracy, especially in complex urban situations. Some recent fatal accidents involving autonomous vehicles further expose such limitations. In this paper, we aim at overcoming these limitations by proposing a novel relative positioning approach, called Cooperative Multi-point Positioning (COMPOP). The COMPOP establishes cooperation between a target vehicle (TV) and a sensing vehicle (SV) if a LoS path exists, where a TV explicitly lets an SV to know the TV's existence by transmitting positioning waveforms. This cooperation makes it possible to remove the time-consuming scanning and target recognizing processes, facilitating real-time positioning. One prerequisite for the cooperation is a clock synchronization between a pair of TV and SV. To this end, we use a phase-differential-of-arrival based approach to remove the TV-SV clock difference from the received signal. With clock difference correction, the TV's position can be obtained via peak detection over a 3D power spectrum constructed by a Fourier transform (FT) based algorithm. The COMPOP also incorporates nearby vehicles, without knowing their locations, into the above cooperation for the case without a LoS path. The effectiveness of the COMPOP is verified by several simulations concerning practical channel parameters.

preprint2020arXiv

Correlators in the supereigenvalue model in the Ramond sector

We investigate the supereigenvalue model in the Ramond sector. We prove that its partition function can be obtained by acting on elementary functions with exponents of the given operators. The Virasoro constraints for this supereigenvalue model are presented. The remarkable property of these bosonic constraint operators is that they obey the Witt algebra and null 3-algebra. The compact expression of correlators can be derived from these Virasoro constraints.

preprint2020arXiv

D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry

We propose D3VO as a novel framework for monocular visual odometry that exploits deep networks on three levels -- deep depth, pose and uncertainty estimation. We first propose a novel self-supervised monocular depth estimation network trained on stereo videos without any external supervision. In particular, it aligns the training image pairs into similar lighting condition with predictive brightness transformation parameters. Besides, we model the photometric uncertainties of pixels on the input images, which improves the depth estimation accuracy and provides a learned weighting function for the photometric residuals in direct (feature-less) visual odometry. Evaluation results show that the proposed network outperforms state-of-the-art self-supervised depth estimation networks. D3VO tightly incorporates the predicted depth, pose and uncertainty into a direct visual odometry method to boost both the front-end tracking as well as the back-end non-linear optimization. We evaluate D3VO in terms of monocular visual odometry on both the KITTI odometry benchmark and the EuRoC MAV dataset.The results show that D3VO outperforms state-of-the-art traditional monocular VO methods by a large margin. It also achieves comparable results to state-of-the-art stereo/LiDAR odometry on KITTI and to the state-of-the-art visual-inertial odometry on EuRoC MAV, while using only a single camera.

preprint2020arXiv

Decoding asymptomatic COVID-19 infection and transmission

Coronavirus disease 2019 (COVID-19) is a continuously devastating public health and the world economy. One of the major challenges in controlling the COVID-19 outbreak is its asymptomatic infection and transmission, which are elusive and defenseless in most situations. The pathogenicity and virulence of asymptomatic COVID-19 remain mysterious. Based on the genotyping of 20656 Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) genome isolates, we reveal that asymptomatic infection is linked to SARS-CoV-2 11083G>T mutation, i.e., leucine (L) to phenylalanine (F) substitution at the residue 37 (L37F) of nonstructure protein 6 (NSP6). By analyzing the distribution of 11083G>T in various countries, we unveil that 11083G>T may correlate with the hypotoxicity of SARS-CoV-2. Moreover, we show a global decaying tendency of the 11083G>T mutation ratio indicating that 11083G>T hinders SARS-CoV-2 transmission capacity. Sequence alignment found both NSP6 and residue 37 neighborhoods are relatively conservative over a few coronaviral species, indicating their importance in regulating host cell autophagy to undermine innate cellular defense against viral infection. Using machine learning and topological data analysis, we demonstrate that mutation L37F has made NSP6 energetically less stable. The rigidity and flexibility index and several network models suggest that mutation L37F may have compromised the NSP6 function, leading to a relatively weak SARS-CoV subtype. This assessment is a good agreement with our genotyping of SARS-CoV-2 evolution and transmission across various countries and regions over the past few months.

preprint2020arXiv

Decoding SARS-CoV-2 transmission, evolution and ramification on COVID-19 diagnosis, vaccine, and medicine

Tremendous effort has been given to the development of diagnostic tests, preventive vaccines, and therapeutic medicines for coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Much of this development has been based on the reference genome collected on January 5, 2020. Based on the genotyping of 6156 genome samples collected up to April 24, 2020, we report that SARS-CoV-2 has had 4459 alarmingly mutations which can be clustered into five subtypes. We introduce mutation ratio and mutation $h$-index to characterize the protein conservativeness and unveil that SARS-CoV-2 envelope protein, main protease, and endoribonuclease protein are relatively conservative, while SARS-CoV-2 nucleocapsid protein, spike protein, and papain-like protease are relatively non-conservative. In particular, the nucleocapsid protein has more than half its genes changed in the past few months, signaling devastating impacts on the ongoing development of COVID-19 diagnosis, vaccines, and drugs.

preprint2020arXiv

Deep Audio-Visual Learning: A Survey

Audio-visual learning, aimed at exploiting the relationship between audio and visual modalities, has drawn considerable attention since deep learning started to be used successfully. Researchers tend to leverage these two modalities either to improve the performance of previously considered single-modality tasks or to address new challenging problems. In this paper, we provide a comprehensive survey of recent audio-visual learning development. We divide the current audio-visual learning tasks into four different subfields: audio-visual separation and localization, audio-visual correspondence learning, audio-visual generation, and audio-visual representation learning. State-of-the-art methods as well as the remaining challenges of each subfield are further discussed. Finally, we summarize the commonly used datasets and performance metrics.

preprint2020arXiv

Deep Manifold Prior

We present a prior for manifold structured data, such as surfaces of 3D shapes, where deep neural networks are adopted to reconstruct a target shape using gradient descent starting from a random initialization. We show that surfaces generated this way are smooth, with limiting behavior characterized by Gaussian processes, and we mathematically derive such properties for fully-connected as well as convolutional networks. We demonstrate our method in a variety of manifold reconstruction applications, such as point cloud denoising and interpolation, achieving considerably better results against competitive baselines while requiring no training data. We also show that when training data is available, our method allows developing alternate parametrizations of surfaces under the framework of AtlasNet, leading to a compact network architecture and better reconstruction results on standard image to shape reconstruction benchmarks.

preprint2020arXiv

Deep Reinforcement Learning for Multi-objective Optimization

This study proposes an end-to-end framework for solving multi-objective optimization problems (MOPs) using Deep Reinforcement Learning (DRL), that we call DRL-MOA. The idea of decomposition is adopted to decompose the MOP into a set of scalar optimization subproblems. Then each subproblem is modelled as a neural network. Model parameters of all the subproblems are optimized collaboratively according to a neighborhood-based parameter-transfer strategy and the DRL training algorithm. Pareto optimal solutions can be directly obtained through the trained neural network models. In specific, the multi-objective travelling salesman problem (MOTSP) is solved in this work using the DRL-MOA method by modelling the subproblem as a Pointer Network. Extensive experiments have been conducted to study the DRL-MOA and various benchmark methods are compared with it. It is found that, once the trained model is available, it can scale to newly encountered problems with no need of re-training the model. The solutions can be directly obtained by a simple forward calculation of the neural network; thereby, no iteration is required and the MOP can be always solved in a reasonable time. The proposed method provides a new way of solving the MOP by means of DRL. It has shown a set of new characteristics, e.g., strong generalization ability and fast solving speed in comparison with the existing methods for multi-objective optimizations. Experimental results show the effectiveness and competitiveness of the proposed method in terms of model performance and running time.

preprint2020arXiv

DeepNetQoE: Self-adaptive QoE Optimization Framework of Deep Networks

Future advances in deep learning and its impact on the development of artificial intelligence (AI) in all fields depends heavily on data size and computational power. Sacrificing massive computing resources in exchange for better precision rates of the network model is recognized by many researchers. This leads to huge computing consumption and satisfactory results are not always expected when computing resources are limited. Therefore, it is necessary to find a balance between resources and model performance to achieve satisfactory results. This article proposes a self-adaptive quality of experience (QoE) framework, DeepNetQoE, to guide the training of deep networks. A self-adaptive QoE model is set up that relates the model's accuracy with the computing resources required for training which will allow the experience value of the model to improve. To maximize the experience value when computer resources are limited, a resource allocation model and solutions need to be established. In addition, we carry out experiments based on four network models to analyze the experience values with respect to the crowd counting example. Experimental results show that the proposed DeepNetQoE is capable of adaptively obtaining a high experience value according to user needs and therefore guiding users to determine the computational resources allocated to the network models.

preprint2020arXiv

DH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DoF Relocalization

For relocalization in large-scale point clouds, we propose the first approach that unifies global place recognition and local 6DoF pose refinement. To this end, we design a Siamese network that jointly learns 3D local feature detection and description directly from raw 3D points. It integrates FlexConv and Squeeze-and-Excitation (SE) to assure that the learned local descriptor captures multi-level geometric information and channel-wise relations. For detecting 3D keypoints we predict the discriminativeness of the local descriptors in an unsupervised manner. We generate the global descriptor by directly aggregating the learned local descriptors with an effective attention mechanism. In this way, local and global 3D descriptors are inferred in one single forward pass. Experiments on various benchmarks demonstrate that our method achieves competitive results for both global point cloud retrieval and local point cloud registration in comparison to state-of-the-art approaches. To validate the generalizability and robustness of our 3D keypoints, we demonstrate that our method also performs favorably without fine-tuning on the registration of point clouds that were generated by a visual SLAM system. Code and related materials are available at https://vision.in.tum.de/research/vslam/dh3d.

preprint2020arXiv

DirectShape: Direct Photometric Alignment of Shape Priors for Visual Vehicle Pose and Shape Estimation

Scene understanding from images is a challenging problem encountered in autonomous driving. On the object level, while 2D methods have gradually evolved from computing simple bounding boxes to delivering finer grained results like instance segmentations, the 3D family is still dominated by estimating 3D bounding boxes. In this paper, we propose a novel approach to jointly infer the 3D rigid-body poses and shapes of vehicles from a stereo image pair using shape priors. Unlike previous works that geometrically align shapes to point clouds from dense stereo reconstruction, our approach works directly on images by combining a photometric and a silhouette alignment term in the energy function. An adaptive sparse point selection scheme is proposed to efficiently measure the consistency with both terms. In experiments, we show superior performance of our method on 3D pose and shape estimation over the previous geometric approach and demonstrate that our method can also be applied as a refinement step and significantly boost the performances of several state-of-the-art deep learning based 3D object detectors. All related materials and demonstration videos are available at the project page https://vision.in.tum.de/research/vslam/direct-shape.

preprint2020arXiv

Double ramification cycles with orbifold targets

In this paper, we consider double ramification cycles with orbifold targets. An explicit formula for double ramification cycles with orbifold targets, which is parallel to and generalizes the one known for the smooth case, is provided. Some applications for orbifold Gromov--Witten theory are also included.

preprint2020arXiv

Energy Efficiency Analysis of Intelligent Reflecting Surface System with Hardware Impairments

Recently, as explosive growth of mobile data traffic, the performance of wireless communication systems requires to be enhanced significantly in future. Intelligent reflecting surface (IRS) can be used as a promising way to improve the energy efficiency of wireless communications with less complexity and hardware cost. Most existing studies consider the cases with ideal hardware, however, both physical transceiver and IRS suffer from non-negligible hardware impairments which may greatly degrade the system performance. In this paper, by taking hardware impairments into consideration, we focus on the energy efficiency analysis of IRS system. Our first contribution is to derive the optimal receive combining and transmit beamforming vectors. After that, we characterize the asymptotic channel capacity. With the derived asymptotic channel capacity and the power consumption model, the analytical upper and lower bounds of energy efficiency are provided. Our results show that an IRS system can achieve both high spectral efficiency and high energy efficiency with moderate number of antennas. This observation is encouraging for that there is no need to cost a lot on expensive high-quality antennas, which corresponds to the requirements of new communication paradigms.

preprint2020arXiv

Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions

Creating open-ended algorithms, which generate their own never-ending stream of novel and appropriately challenging learning opportunities, could help to automate and accelerate progress in machine learning. A recent step in this direction is the Paired Open-Ended Trailblazer (POET), an algorithm that generates and solves its own challenges, and allows solutions to goal-switch between challenges to avoid local optima. However, the original POET was unable to demonstrate its full creative potential because of limitations of the algorithm itself and because of external issues including a limited problem space and lack of a universal progress measure. Importantly, both limitations pose impediments not only for POET, but for the pursuit of open-endedness in general. Here we introduce and empirically validate two new innovations to the original algorithm, as well as two external innovations designed to help elucidate its full potential. Together, these four advances enable the most open-ended algorithmic demonstration to date. The algorithmic innovations are (1) a domain-general measure of how meaningfully novel new challenges are, enabling the system to potentially create and solve interesting challenges endlessly, and (2) an efficient heuristic for determining when agents should goal-switch from one problem to another (helping open-ended search better scale). Outside the algorithm itself, to enable a more definitive demonstration of open-endedness, we introduce (3) a novel, more flexible way to encode environmental challenges, and (4) a generic measure of the extent to which a system continues to exhibit open-ended innovation. Enhanced POET produces a diverse range of sophisticated behaviors that solve a wide range of environmental challenges, many of which cannot be solved through other means.

preprint2020arXiv

Estimating Q(s,s') with Deep Deterministic Dynamics Gradients

In this paper, we introduce a novel form of value function, $Q(s, s')$, that expresses the utility of transitioning from a state $s$ to a neighboring state $s'$ and then acting optimally thereafter. In order to derive an optimal policy, we develop a forward dynamics model that learns to make next-state predictions that maximize this value. This formulation decouples actions from values while still learning off-policy. We highlight the benefits of this approach in terms of value function transfer, learning within redundant action spaces, and learning off-policy from state observations generated by sub-optimal or completely random policies. Code and videos are available at http://sites.google.com/view/qss-paper.

preprint2020arXiv

Explicit Reordering for Neural Machine Translation

In Transformer-based neural machine translation (NMT), the positional encoding mechanism helps the self-attention networks to learn the source representation with order dependency, which makes the Transformer-based NMT achieve state-of-the-art results for various translation tasks. However, Transformer-based NMT only adds representations of positions sequentially to word vectors in the input sentence and does not explicitly consider reordering information in this sentence. In this paper, we first empirically investigate the relationship between source reordering information and translation performance. The empirical findings show that the source input with the target order learned from the bilingual parallel dataset can substantially improve translation performance. Thus, we propose a novel reordering method to explicitly model this reordering information for the Transformer-based NMT. The empirical results on the WMT14 English-to-German, WAT ASPEC Japanese-to-English, and WMT17 Chinese-to-English translation tasks show the effectiveness of the proposed approach.

preprint2020arXiv

Fiber: A Platform for Efficient Development and Distributed Training for Reinforcement Learning and Population-Based Methods

Recent advances in machine learning are consistently enabled by increasing amounts of computation. Reinforcement learning (RL) and population-based methods in particular pose unique challenges for efficiency and flexibility to the underlying distributed computing frameworks. These challenges include frequent interaction with simulations, the need for dynamic scaling, and the need for a user interface with low adoption cost and consistency across different backends. In this paper we address these challenges while still retaining development efficiency and flexibility for both research and practical applications by introducing Fiber, a scalable distributed computing framework for RL and population-based methods. Fiber aims to significantly expand the accessibility of large-scale parallel computation to users of otherwise complicated RL and population-based approaches without the need to for specialized computational expertise.

preprint2020arXiv

First-Order Preconditioning via Hypergradient Descent

Standard gradient descent methods are susceptible to a range of issues that can impede training, such as high correlations and different scaling in parameter space.These difficulties can be addressed by second-order approaches that apply a pre-conditioning matrix to the gradient to improve convergence. Unfortunately, such algorithms typically struggle to scale to high-dimensional problems, in part because the calculation of specific preconditioners such as the inverse Hessian or Fisher information matrix is highly expensive. We introduce first-order preconditioning (FOP), a fast, scalable approach that generalizes previous work on hypergradient descent (Almeida et al., 1998; Maclaurin et al., 2015; Baydin et al.,2017) to learn a preconditioning matrix that only makes use of first-order information. Experiments show that FOP is able to improve the performance of standard deep learning optimizers on visual classification and reinforcement learning tasks with minimal computational overhead. We also investigate the properties of the learned preconditioning matrices and perform a preliminary theoretical analysis of the algorithm.

preprint2020arXiv

Graph-to-Sequence Neural Machine Translation

Neural machine translation (NMT) usually works in a seq2seq learning way by viewing either source or target sentence as a linear sequence of words, which can be regarded as a special case of graph, taking words in the sequence as nodes and relationships between words as edges. In the light of the current NMT models more or less capture graph information among the sequence in a latent way, we present a graph-to-sequence model facilitating explicit graph information capturing. In detail, we propose a graph-based SAN-based NMT model called Graph-Transformer by capturing information of subgraphs of different orders in every layers. Subgraphs are put into different groups according to their orders, and every group of subgraphs respectively reflect different levels of dependency between words. For fusing subgraph representations, we empirically explore three methods which weight different groups of subgraphs of different orders. Results of experiments on WMT14 English-German and IWSLT14 German-English show that our method can effectively boost the Transformer with an improvement of 1.1 BLEU points on WMT14 English-German dataset and 1.0 BLEU points on IWSLT14 German-English dataset.

preprint2020arXiv

Grasp State Assessment of Deformable Objects Using Visual-Tactile Fusion Perception

Humans can quickly determine the force required to grasp a deformable object to prevent its sliding or excessive deformation through vision and touch, which is still a challenging task for robots. To address this issue, we propose a novel 3D convolution-based visual-tactile fusion deep neural network (C3D-VTFN) to evaluate the grasp state of various deformable objects in this paper. Specifically, we divide the grasp states of deformable objects into three categories of sliding, appropriate and excessive. Also, a dataset for training and testing the proposed network is built by extensive grasping and lifting experiments with different widths and forces on 16 various deformable objects with a robotic arm equipped with a wrist camera and a tactile sensor. As a result, a classification accuracy as high as 99.97% is achieved. Furthermore, some delicate grasp experiments based on the proposed network are implemented in this paper. The experimental results demonstrate that the C3D-VTFN is accurate and efficient enough for grasp state assessment, which can be widely applied to automatic force control, adaptive grasping, and other visual-tactile spatiotemporal sequence learning problems.

preprint2020arXiv

Hardware-irrelevant parallel processing system

Parallel processing technology has been a primary tool for achieving high-speed, high-accuracy, and broadband processing for many years across modern information systems and data processing such as optical and radar, synthetic aperture radar imaging, digital beam forming, and digital filtering systems. However, hardware deviations in a parallel processing system (PPS) severely degrade system performance and pose an urgent challenge. We propose a hardware-irrelevant PPS of which the performance is unaffected by hardware deviations. In this system, an embedded convolutional recurrent autoencoder (CRAE), which learns inherent system patterns as well as acquires and removes adverse effects brought by hardware deviations, is adopted. We implement a hardware-irrelevant PPS into a parallel photonic sampling system to accomplish a high-performance analog-to-digital conversion for microwave signals with high frequency and broad bandwidth. Under one system state, a category of signals with two different mismatch degrees is utilized to train the CRAE, which can then compensate for mismatches in various categories of signals with multiple mismatch degrees under random system states. Our approach is extensively applicable to achieving hardware-irrelevant PPSs which are either discrete or integrated in photonic, electric, and other fields.

preprint2020arXiv

Host immune response driving SARS-CoV-2 evolution

The transmission and evolution of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) are of paramount importance to the controlling and combating of coronavirus disease 2019 (COVID-19) pandemic. Currently, near 15,000 SARS-CoV-2 single mutations have been recorded, having a great ramification to the development of diagnostics, vaccines, antibody therapies, and drugs. However, little is known about SARS-CoV-2 evolutionary characteristics and general trend. In this work, we present a comprehensive genotyping analysis of existing SARS-CoV-2 mutations. We reveal that host immune response via APOBEC and ADAR gene editing gives rise to near 65\% of recorded mutations. Additionally, we show that children under age five and the elderly may be at high risk from COVID-19 because of their overreacting to the viral infection. Moreover, we uncover that populations of Oceania and Africa react significantly more intensively to SARS-CoV-2 infection than those of Europe and Asia, which may explain why African Americans were shown to be at increased risk of dying from COVID-19, in addition to their high risk of getting sick from COVID-19 caused by systemic health and social inequities. Finally, our study indicates that for two viral genome sequences of the same origin, their evolution order may be determined from the ratio of mutation type C$>$T over T$>$C.

preprint2020arXiv

Intrinsic quantum anomalous Hall phase induced by proximity in germanene/Cr$_2$Ge$_2$Te$_6$ van der Waals heterostructure

A van der Waals heterostructure combined with intrinsic magnetism and topological orders have recently paved attractive avenues to realize quantum anomalous Hall effects. In this work, using first-principles calculations and effective model analysis, we propose that the robust quantum anomalous Hall states with sizable band gaps emerge in the van der Waals heterostructure of germanene/Cr$_2$Ge$_2$Te$_6$. This heterostructure possesses high thermodynamic stability, thus facilitating its experimental fabrication. Furthermore, we uncover that the proximity effect enhances the coupling between the germanene and Cr$_2$Ge$_2$Te$_6$ layers, inducing the nontrivial band gaps in a wide range from 29 meV to 72 meV. The chiral edge states inside the band gap, leading to Hall conductance quantized to $-e^2/h$, are clearly visible. This findings provide an ideal candidate to detect the quantum anomalous Hall states and realize further applications to nontrivial quantum transport at a high temperature.

preprint2020arXiv

Joint Optimization of File Placement and Delivery in Cache-Assisted Wireless Networks with Limited Lifetime and Cache Space

In this paper, the scheduling of downlink file transmission in one cell with the assistance of cache nodes with finite cache space is studied. Specifically, requesting users arrive randomly and the base station (BS) reactively multicasts files to the requesting users and selected cache nodes. The latter can offload the traffic in their coverage areas from the BS. We consider the joint optimization of the abovementioned file placement and delivery within a finite lifetime subject to the cache space constraint. Within the lifetime, the allocation of multicast power and symbol number for each file transmission at the BS is formulated as a dynamic programming problem with a random stage number. Note that there are no existing solutions to this problem. We develop an asymptotically optimal solution framework by transforming the original problem to an equivalent finite-horizon Markov decision process (MDP) with a fixed stage number. A novel approximation approach is then proposed to address the curse of dimensionality, where the analytical expressions of approximate value functions are provided. We also derive analytical bounds on the exact value function and approximation error. The approximate value functions depend on some system statistics, e.g., requesting users' distribution. One reinforcement learning algorithm is proposed for the scenario where these statistics are unknown.

preprint2020arXiv

Knowledge Distillation for Multilingual Unsupervised Neural Machine Translation

Unsupervised neural machine translation (UNMT) has recently achieved remarkable results for several language pairs. However, it can only translate between a single language pair and cannot produce translation results for multiple language pairs at the same time. That is, research on multilingual UNMT has been limited. In this paper, we empirically introduce a simple method to translate between thirteen languages using a single encoder and a single decoder, making use of multilingual data to improve UNMT for all language pairs. On the basis of the empirical findings, we propose two knowledge distillation methods to further enhance multilingual UNMT performance. Our experiments on a dataset with English translated to and from twelve other languages (including three language families and six language branches) show remarkable results, surpassing strong unsupervised individual baselines while achieving promising performance between non-English language pairs in zero-shot translation scenarios and alleviating poor performance in low-resource language pairs.

preprint2020arXiv

Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions

The problems of shape classification and part segmentation from 3D point clouds have garnered increasing attention in the last few years. Both of these problems, however, suffer from relatively small training sets, creating the need for statistically efficient methods to learn 3D shape representations. In this paper, we investigate the use of Approximate Convex Decompositions (ACD) as a self-supervisory signal for label-efficient learning of point cloud representations. We show that using ACD to approximate ground truth segmentation provides excellent self-supervision for learning 3D point cloud representations that are highly effective on downstream tasks. We report improvements over the state-of-the-art for unsupervised representation learning on the ModelNet40 shape classification dataset and significant gains in few-shot part segmentation on the ShapeNetPart dataset.Code available at https://github.com/matheusgadelha/PointCloudLearningACD

preprint2020arXiv

Learning Centric Power Allocation for Edge Intelligence

While machine-type communication (MTC) devices generate massive data, they often cannot process this data due to limited energy and computation power. To this end, edge intelligence has been proposed, which collects distributed data and performs machine learning at the edge. However, this paradigm needs to maximize the learning performance instead of the communication throughput, for which the celebrated water-filling and max-min fairness algorithms become inefficient since they allocate resources merely according to the quality of wireless channels. This paper proposes a learning centric power allocation (LCPA) method, which allocates radio resources based on an empirical classification error model. To get insights into LCPA, an asymptotic optimal solution is derived. The solution shows that the transmit powers are inversely proportional to the channel gain, and scale exponentially with the learning parameters. Experimental results show that the proposed LCPA algorithm significantly outperforms other power allocation algorithms.

preprint2020arXiv

Learning Generative Models of Shape Handles

We present a generative model to synthesize 3D shapes as sets of handles -- lightweight proxies that approximate the original 3D shape -- for applications in interactive editing, shape parsing, and building compact 3D representations. Our model can generate handle sets with varying cardinality and different types of handles (Figure 1). Key to our approach is a deep architecture that predicts both the parameters and existence of shape handles, and a novel similarity measure that can easily accommodate different types of handles, such as cuboids or sphere-meshes. We leverage the recent advances in semantic 3D annotation as well as automatic shape summarizing techniques to supervise our approach. We show that the resulting shape representations are intuitive and achieve superior quality than previous state-of-the-art. Finally, we demonstrate how our method can be used in applications such as interactive shape editing, completion, and interpolation, leveraging the latent space learned by our model to guide these tasks. Project page: http://mgadelha.me/shapehandles.

preprint2020arXiv

Long-term continuous assessment of SRAM PUF and source of random numbers

The qualities of Physical Unclonable Functions (PUFs) suffer from several noticeable degradations due to silicon aging. In this paper, we investigate the long-term effects of silicon aging on PUFs derived from the start-up behavior of Static Random Access Memories (SRAM). Previous research on SRAM aging is based on transistor-level simulation or accelerated aging test at high temperature and voltage to observe aging effects within a short period of time. In contrast, we have run a long-term continuous power-up test on 16 Arduino Leonardo boards under nominal conditions for two years. In total, we collected around 175 million measurements for reliability, uniqueness and randomness evaluations. Analysis shows that the number of bits that flip with respect to the reference increased by 19.3% while min-entropy of SRAM PUF noise improves by 19.3% on average after two years of aging. The impact of aging on reliability is smaller under nominal conditions than was previously assessed by the accelerated aging test. The test we conduct in this work more closely resembles the conditions of a device in the field, and therefore we more accurately evaluate how silicon aging affects SRAM PUFs.

preprint2020arXiv

M Subdwarf Research. II. Atmospheric Parameters and Kinematics

Applying the revised M subdwarf classification criteria discussed in Paper I to LAMOST DR7, combining the M subdwarf sample from Savcheva et al, a new M subdwarf sample was constructed for further study. The atmospheric parameters for each object were derived fitting with the PHOENIX grid, combining with Gaia DR2, the relationship between the gravity and metallicity were explored according to the locus both in the color-absolute magnitude diagram and the reduced proper motion diagram. Objects that have both the largest gravity and the lowest metallicity are located away from the main-sequence cloud and may be considered as the intrinsic M subdwarfs, which can be classified as luminosity class VI. Another group of objects whose spectra show typical M subdwarf characters have lower gravity and relatively moderate metal deficiency and occupy part of the ordinary M dwarf region in both diagrams. The Galactic U , V , W space velocity components and their dispersion show that the local Galactic halo population sampled in the solar neighborhood is represented by objects of high gravity and an inconspicuous bimodal metallicity distribution, with a fraction of prograde orbits. The other M subdwarfs seem to partly belong to the thick disk component with a significant fraction of thin disk moderately metal-poor objects intricately mixed with them. However, the selection effects, especially the favored anti-center direction of investigation in the LAMOST sub-sample, but also contamination by multiplicity and parameter coupling could play important roles and need to be further investigated.

preprint2020arXiv

Machine Intelligence at the Edge with Learning Centric Power Allocation

While machine-type communication (MTC) devices generate considerable amounts of data, they often cannot process the data due to limited energy and computational power. To empower MTC with intelligence, edge machine learning has been proposed. However, power allocation in this paradigm requires maximizing the learning performance instead of the communication throughput, for which the celebrated water-filling and max-min fairness algorithms become inefficient. To this end, this paper proposes learning centric power allocation (LCPA), which provides a new perspective on radio resource allocation in learning driven scenarios. By employing 1) an empirical classification error model that is supported by learning theory and 2) an uncertainty sampling method that accounts for different distributions at users, LCPA is formulated as a nonconvex nonsmooth optimization problem, and is solved using a majorization minimization (MM) framework. To get deeper insights into LCPA, asymptotic analysis shows that the transmit powers are inversely proportional to the channel gains, and scale exponentially with the learning parameters. This is in contrast to traditional power allocations where quality of wireless channels is the only consideration. Last but not least, a large-scale optimization algorithm termed mirror-prox LCPA is further proposed to enable LCPA in large-scale settings. Extensive numerical results demonstrate that the proposed LCPA algorithms outperform traditional power allocation algorithms, and the large-scale optimization algorithm reduces the computation time by orders of magnitude compared with MM-based LCPA but still achieves competing learning performance.

preprint2020arXiv

Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond

Machine reading comprehension (MRC) aims to teach machines to read and comprehend human languages, which is a long-standing goal of natural language processing (NLP). With the burst of deep neural networks and the evolution of contextualized language models (CLMs), the research of MRC has experienced two significant breakthroughs. MRC and CLM, as a phenomenon, have a great impact on the NLP community. In this survey, we provide a comprehensive and comparative review on MRC covering overall research topics about 1) the origin and development of MRC and CLM, with a particular focus on the role of CLMs; 2) the impact of MRC and CLM to the NLP community; 3) the definition, datasets, and evaluation of MRC; 4) general MRC architecture and technical methods in the view of two-stage Encoder-Decoder solving architecture from the insights of the cognitive process of humans; 5) previous highlights, emerging topics, and our empirical analysis, among which we especially focus on what works in different periods of MRC researches. We propose a full-view categorization and new taxonomies on these topics. The primary views we have arrived at are that 1) MRC boosts the progress from language processing to understanding; 2) the rapid improvement of MRC systems greatly benefits from the development of CLMs; 3) the theme of MRC is gradually moving from shallow text matching to cognitive reasoning.

preprint2020arXiv

Many-body Resonance in a Correlated Topological Kagome Antiferromagnet

We use scanning tunneling microscopy/spectroscopy (STM/S) to elucidate the atomically resolved electronic structure in strongly correlated topological kagome magnet Mn$_3$Sn. In stark contrast to its broad single-particle electronic structure, we observe a pronounced resonance with a Fano line shape at the Fermi level resembling the many-body Kondo resonance. We find that this resonance does not arise from the step edges or atomic impurities, but the intrinsic kagome lattice. Moreover, the resonance is robust against the perturbation of a vector magnetic field, but broadens substantially with increasing temperature, signaling strongly interacting physics. We show that this resonance can be understood as the result of geometrical frustration and strong correlation based on the kagome lattice Hubbard model. Our results point to the emergent many-body resonance behavior in a topological kagome magnet.

preprint2020arXiv

Modeling Future Cost for Neural Machine Translation

Existing neural machine translation (NMT) systems utilize sequence-to-sequence neural networks to generate target translation word by word, and then make the generated word at each time-step and the counterpart in the references as consistent as possible. However, the trained translation model tends to focus on ensuring the accuracy of the generated target word at the current time-step and does not consider its future cost which means the expected cost of generating the subsequent target translation (i.e., the next target word). To respond to this issue, we propose a simple and effective method to model the future cost of each target word for NMT systems. In detail, a time-dependent future cost is estimated based on the current generated target word and its contextual information to boost the training of the NMT model. Furthermore, the learned future context representation at the current time-step is used to help the generation of the next target word in the decoding. Experimental results on three widely-used translation datasets, including the WMT14 German-to-English, WMT14 English-to-French, and WMT17 Chinese-to-English, show that the proposed approach achieves significant improvements over strong Transformer-based NMT baseline.

preprint2020arXiv

Multi-Domain Dialogue Acts and Response Co-Generation

Generating fluent and informative responses is of critical importance for task-oriented dialogue systems. Existing pipeline approaches generally predict multiple dialogue acts first and use them to assist response generation. There are at least two shortcomings with such approaches. First, the inherent structures of multi-domain dialogue acts are neglected. Second, the semantic associations between acts and responses are not taken into account for response generation. To address these issues, we propose a neural co-generation model that generates dialogue acts and responses concurrently. Unlike those pipeline approaches, our act generation module preserves the semantic structures of multi-domain dialogue acts and our response generation module dynamically attends to different acts as needed. We train the two modules jointly using an uncertainty loss to adjust their task weights adaptively. Extensive experiments are conducted on the large-scale MultiWOZ dataset and the results show that our model achieves very favorable improvement over several state-of-the-art models in both automatic and human evaluations.

preprint2020arXiv

Mutations on COVID-19 diagnostic targets

Effective, sensitive, and reliable diagnostic reagents are of paramount importance for combating the ongoing coronavirus disease 2019 (COVID-19) pandemic at a time there is no preventive vaccine nor specific drug available for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). It would be an absolute tragedy if currently used diagnostic reagents are undermined in any manner. Based on the genotyping of 7818 SARS-CoV-2 genome samples collected up to May 1, 2020, we reveal that essentially all of the current COVID-19 diagnostic targets have had mutations. We further show that SARS-CoV-2 has the most devastating mutations on the targets of various nucleocapsid (N) gene primers and probes, which have been unfortunately used by countries around the world to diagnose COVID-19. Our findings explain what has seriously gone wrong with a specific diagnostic reagent made in China. To understand whether SARS-CoV-2 genes have mutated unevenly, we have computed the mutation ratio and mutation $h$-index of all SARS-CoV genes, indicating that the N gene is the most non-conservative gene in the SARS-CoV-2 genome. Our findings enable researchers to target the most conservative SARS-CoV-2 genes and proteins for the design and development of COVID-19 diagnostic reagents, preventive vaccines, and therapeutic medicines.

preprint2020arXiv

Mutations strengthened SARS-CoV-2 infectivity

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infectivity is a major concern in coronavirus disease 2019 (COVID-19) prevention and economic reopening. However, rigorous determination of SARS-COV-2 infectivity is essentially impossible owing to its continuous evolution with over 13752 single nucleotide polymorphisms (SNP) variants in six different subtypes. We develop an advanced machine learning algorithm based on the algebraic topology to quantitatively evaluate the binding affinity changes of SARS-CoV-2 spike glycoprotein (S protein) and host angiotensin-converting enzyme 2 (ACE2) receptor following the mutations. Based on mutation-induced binding affinity changes, we reveal that five out of six SARS-CoV-2 subtypes have become either moderately or slightly more infectious, while one subtype has weakened its infectivity. We find that SARS-CoV-2 is slightly more infectious than SARS-CoV according to computed S protein-ACE2 binding affinity changes. Based on a systematic evaluation of all possible 3686 future mutations on the S protein receptor-binding domain (RBD), we show that most likely future mutations will make SARS-CoV-2 more infectious. Combining sequence alignment, probability analysis, and binding affinity calculation, we predict that a few residues on the receptor-binding motif (RBM), i.e., 452, 489, 500, 501, and 505, have very high chances to mutate into significantly more infectious COVID-19 strains.

preprint2020arXiv

Neural Topic Modeling with Bidirectional Adversarial Training

Recent years have witnessed a surge of interests of using neural topic models for automatic topic extraction from text, since they avoid the complicated mathematical derivations for model inference as in traditional topic models such as Latent Dirichlet Allocation (LDA). However, these models either typically assume improper prior (e.g. Gaussian or Logistic Normal) over latent topic space or could not infer topic distribution for a given document. To address these limitations, we propose a neural topic modeling approach, called Bidirectional Adversarial Topic (BAT) model, which represents the first attempt of applying bidirectional adversarial training for neural topic modeling. The proposed BAT builds a two-way projection between the document-topic distribution and the document-word distribution. It uses a generator to capture the semantic patterns from texts and an encoder for topic inference. Furthermore, to incorporate word relatedness information, the Bidirectional Adversarial Topic model with Gaussian (Gaussian-BAT) is extended from BAT. To verify the effectiveness of BAT and Gaussian-BAT, three benchmark corpora are used in our experiments. The experimental results show that BAT and Gaussian-BAT obtain more coherent topics, outperforming several competitive baselines. Moreover, when performing text clustering based on the extracted topics, our models outperform all the baselines, with more significant improvements achieved by Gaussian-BAT where an increase of near 6\% is observed in accuracy.

preprint2020arXiv

Orbifold Gromov--Witten theory of weighted blowups

Consider a compact symplectic sub-orbifold groupoid $\sf S$ of a compact symplectic orbifold groupoid $(\mathsf X,ω)$. Let $\mathsf X_{\mathfrak a}$ be the weight-$\mathfrak a$ blowup of $\sf X$ along $\sf S$, and $\mathsf D_{\mathfrak a}=\mathsf{PN}_{\mathfrak a}$ be the exceptional divisor, where $\sf N$ is the normal bundle of $\sf S$ in $\sf X$. In this paper we show that the absolute orbifold Gromov--Witten theory of $\mathsf X_{\mathfrak a}$ can be effectively and uniquely reconstructed from the absolute orbifold Gromov--Witten theories of $\sf X$, $\sf S$ and $\mathsf D_{\mathfrak a}$, the natural restriction homomorphism $H^*_{\text{CR}}({\sf X})\rightarrow H^*_{\text{CR}}({\sf S})$ and the first Chern class of the tautological line bundle over $\mathsf D_{\mathfrak a}$. To achieve this we first prove similar results for the relative orbifold Gromov--Witten theories of $(\mathsf X_{\mathfrak a}|\mathsf D_{\mathfrak a})$ and $(\mathsf N_{\mathfrak a}|\mathsf D_{\mathfrak a})$. As applications of these results, we prove an orbifold version of a conjecture of Maulik--Pandharipande on the Gromov--Witten theory of blowups along complete intersections, a conjecture on the Gromov--Witten theory of root constructions and a conjecture on Leray--Hirsch result for orbifold Gromov--Witten theory of Tseng--You.

preprint2020arXiv

Propensity Score Weighting for Covariate Adjustment in Randomized Clinical Trials

Chance imbalance in baseline characteristics is common in randomized clinical trials. Regression adjustment such as the analysis of covariance (ANCOVA) is often used to account for imbalance and increase precision of the treatment effect estimate. An objective alternative is through inverse probability weighting (IPW) of the propensity scores. Although IPW and ANCOVA are asymptotically equivalent, the former may demonstrate inferior performance in finite samples. In this article, we point out that IPW is a special case of the general class of balancing weights, and advocate to use overlap weighting (OW) for covariate adjustment. The OW method has a unique advantage of completely removing chance imbalance when the propensity score is estimated by logistic regression. We show that the OW estimator attains the same semiparametric variance lower bound as the most efficient ANCOVA estimator and the IPW estimator for a continuous outcome, and derive closed-form variance estimators for OW when estimating additive and ratio estimands. Through extensive simulations, we demonstrate OW consistently outperforms IPW in finite samples and improves the efficiency over ANCOVA and augmented IPW when the degree of treatment effect heterogeneity is moderate or when the outcome model is incorrectly specified. We apply the proposed OW estimator to the Best Apnea Interventions for Research (BestAIR) randomized trial to evaluate the effect of continuous positive airway pressure on patient health outcomes. All the discussed propensity score weighting methods are implemented in the R package PSweight.

preprint2020arXiv

Reconfigurable Intelligent Surface Aided Wireless Localization

The advantages of millimeter-wave and large antenna arrays technologies for accurate wireless localization received extensive attentions recently. However, how to further improve the accuracy of wireless localization, even in the case of obstructed line-of-sight, is largely undiscovered. In this paper, the reconfigurable intelligent surface (RIS) is introduced into the system to make the positioning more accurate. First, we establish the three-dimensional RIS-assisted wireless localization channel model. After that, we derive the Fisher information matrix and the Cramer-Rao lower bound for evaluating the estimation of absolute mobile station position. Finally, we propose an alternative optimization method and a gradient decent method to optimize the reflect beamforming, which aims to minimize the Cramer-Rao lower bound to obtain a more accurate estimation. Our results show that the proposed methods significantly improve the accuracy of positioning, and decimeter-level or even centimeter-level positioning can be achieved by utilizing the RIS with a large number of reflecting elements.

preprint2020arXiv

Regularized Context Gates on Transformer for Machine Translation

Context gates are effective to control the contributions from the source and target contexts in the recurrent neural network (RNN) based neural machine translation (NMT). However, it is challenging to extend them into the advanced Transformer architecture, which is more complicated than RNN. This paper first provides a method to identify source and target contexts and then introduce a gate mechanism to control the source and target contributions in Transformer. In addition, to further reduce the bias problem in the gate mechanism, this paper proposes a regularization method to guide the learning of the gates with supervision automatically generated using pointwise mutual information. Extensive experiments on 4 translation datasets demonstrate that the proposed model obtains an averaged gain of 1.0 BLEU score over a strong Transformer baseline.

preprint2020arXiv

Relational Graph Attention Network for Aspect-based Sentiment Analysis

Aspect-based sentiment analysis aims to determine the sentiment polarity towards a specific aspect in online reviews. Most recent efforts adopt attention-based neural network models to implicitly connect aspects with opinion words. However, due to the complexity of language and the existence of multiple aspects in a single sentence, these models often confuse the connections. In this paper, we address this problem by means of effective encoding of syntax information. Firstly, we define a unified aspect-oriented dependency tree structure rooted at a target aspect by reshaping and pruning an ordinary dependency parse tree. Then, we propose a relational graph attention network (R-GAT) to encode the new tree structure for sentiment prediction. Extensive experiments are conducted on the SemEval 2014 and Twitter datasets, and the experimental results confirm that the connections between aspects and opinion words can be better established with our approach, and the performance of the graph attention network (GAT) is significantly improved as a consequence.

preprint2020arXiv

Repositioning of 8565 existing drugs for COVID-19

The coronavirus disease 2019 (COVID-19) pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has infected near 5 million people and led to over 0.3 million deaths. Currently, there is no specific anti-SARS-CoV-2 medication. New drug discovery typically takes more than ten years. Drug repositioning becomes one of the most feasible approaches for combating COVID-19. This work curates the largest available experimental dataset for SARS-CoV-2 or SARS-CoV main protease inhibitors. Based on this dataset, we develop validated machine learning models with relatively low root mean square error to screen 1553 FDA-approved drugs as well as other 7012 investigational or off-market drugs in DrugBank. We found that many existing drugs might be potentially potent to SARS-CoV-2. The druggability of many potent SARS-CoV-2 main protease inhibitors is analyzed. This work offers a foundation for further experimental studies of COVID-19 drug repositioning.

preprint2020arXiv

Representer Theorems in Banach Spaces: Minimum Norm Interpolation, Regularized Learning and Semi-Discrete Inverse Problems

Constructing or learning a function from a finite number of sampled data points (measurements) is a fundamental problem in science and engineering. This is often formulated as a minimum norm interpolation problem, regularized learning problem or, in general, a semi-discrete inverse problem, in certain functional spaces. The choice of an appropriate space is crucial for solutions of these problems. Motivated by sparse representations of the reconstructed functions such as compressed sensing and sparse learning, much of the recent research interest has been directed to considering these problems in certain Banach spaces in order to obtain their sparse solutions, which is a feasible approach to overcome challenges coming from the big data nature of most practical applications. It is the goal of this paper to provide a systematic study of the representer theorems for these problems in Banach spaces. There are a few existing results for these problems in a Banach space, with all of them regarding implicit representer theorems. We aim at obtaining explicit representer theorems based on which convenient solution methods will then be developed. For the minimum norm interpolation, the explicit representer theorems enable us to express the infimum in terms of the norm of the linear combination of the interpolation functionals. For the purpose of developing efficient computational algorithms, we establish the fixed-point equation formulation of solutions of these problems. We reveal that unlike in a Hilbert space, in general, solutions of these problems in a Banach space may not be able to be reduced to truly finite dimensional problems (with certain infinite dimensional components hidden). We demonstrate how this obstacle can be removed, reducing the original problem to a truly finite dimensional one, in the special case when the Banach space is $\ell_1(\mathbb{N})$.

preprint2020arXiv

Review of COVID-19 Antibody Therapies

Under the global health emergency caused by coronavirus disease 2019 (COVID-19), efficient and specific therapies are urgently needed. Compared with traditional small-molecular drugs, antibody therapies are relatively easy to develop and as specific as vaccines in targeting severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), and thus attract much attention in the past few months. This work reviews seven existing antibodies for SARS-CoV-2 spike (S) protein with three-dimensional (3D) structures deposited in the Protein Data Bank. Five antibody structures associated with SARS-CoV are evaluated for their potential in neutralizing SARS-CoV-2. The interactions of these antibodies with the S protein receptor-binding domain (RBD) are compared with those of angiotensin-converting enzyme 2 (ACE2) and RBD complexes. Due to the orders of magnitude in the discrepancies of experimental binding affinities, we introduce topological data analysis (TDA), a variety of network models, and deep learning to analyze the binding strength and therapeutic potential of the aforementioned fourteen antibody-antigen complexes. The current COVID-19 antibody clinical trials, which are not limited to the S protein target, are also reviewed.

preprint2020arXiv

Revisiting Simple Domain Adaptation Methods in Unsupervised Neural Machine Translation

Domain adaptation has been well-studied in supervised neural machine translation (SNMT). However, it has not been well-studied for unsupervised neural machine translation (UNMT), although UNMT has recently achieved remarkable results in several domain-specific language pairs. Besides the inconsistent domains between training data and test data for SNMT, there sometimes exists an inconsistent domain between two monolingual training data for UNMT. In this work, we empirically show different scenarios for unsupervised neural machine translation. Based on these scenarios, we revisit the effect of the existing domain adaptation methods including batch weighting and fine tuning methods in UNMT. Finally, we propose modified methods to improve the performances of domain-specific UNMT systems.

preprint2020arXiv

Safe and Effective Picking Paths in Clutter given Discrete Distributions of Object Poses

Picking an item in the presence of other objects can be challenging as it involves occlusions and partial views. Given object models, one approach is to perform object pose estimation and use the most likely candidate pose per object to pick the target without collisions. This approach, however, ignores the uncertainty of the perception process both regarding the target's and the surrounding objects' poses. This work proposes first a perception process for 6D pose estimation, which returns a discrete distribution of object poses in a scene. Then, an open-loop planning pipeline is proposed to return safe and effective solutions for moving a robotic arm to pick, which (a) minimizes the probability of collision with the obstructing objects; and (b) maximizes the probability of reaching the target item. The planning framework models the challenge as a stochastic variant of the Minimum Constraint Removal (MCR) problem. The effectiveness of the methodology is verified given both simulated and real data in different scenarios. The experiments demonstrate the importance of considering the uncertainty of the perception process in terms of safe execution. The results also show that the methodology is more effective than conservative MCR approaches, which avoid all possible object poses regardless of the reported uncertainty.

preprint2020arXiv

Scheduling for Mobile Edge Computing with Random User Arrivals: An Approximate MDP and Reinforcement Learning Approach

In this paper, we investigate the scheduling design of a mobile edge computing (MEC) system, where active mobile devices with computation tasks randomly appear in a cell. Every task can be computed at either the mobile device or the MEC server. We jointly optimize the task offloading decision, uplink transmission device selection and power allocation by formulating the problem as an infinite-horizon Markov decision process (MDP). Compared with most of the existing literature, this is the first attempt to address the transmission and computation optimization with the random device arrivals in an infinite time horizon to our best knowledge. Due to the uncertainty in the device number and location, the conventional approximate MDP approaches addressing the curse of dimensionality cannot be applied. An alternative and suitable low-complexity solution framework is proposed in this work. We first introduce a baseline scheduling policy, whose value function can be derived analytically with the statistics of random mobile device arrivals. Then, one-step policy iteration is adopted to obtain a sub-optimal scheduling policy whose performance can be bounded analytically. The complexity of deriving the sub-optimal policy is reduced dramatically compared with conventional solutions of MDP by eliminating the complicated value iteration. To address a more general scenario where the statistics of random mobile device arrivals are unknown, a novel and efficient algorithm integrating reinforcement learning and stochastic gradient descent (SGD) is proposed to improve the system performance in an online manner. Simulation results show that the gain of the sub-optimal policy over various benchmarks is significant.

preprint2020arXiv

SPCANet: Stellar Parameters and Chemical Abundances Network for LAMOST-II Medium Resolution Survey

The fundamental stellar atmospheric parameters T_eff and log g and 13 chemical abundances are derived for medium-resolution spectroscopy from LAMOST Medium-Resolution Survey (MRS) data sets with a deep-learning method. The neural networks we designed, named as SPCANet, precisely map LAMOST MRS spectra to stellar parameters and chemical abundances. The stellar labels derived by SPCANet are with precisions of 119 K for T_eff and 0.17 dex for log g. The abundance precision of 11 elements including [C/H], [N/H], [O/H], [Mg/H], [Al/H], [Si/H], [S/H], [Ca/H], [Ti/H], [Cr/H], [Fe/H], and [Ni/H] are 0.06~0.12 dex, while of [Cu/H] is 0.19 dex. These precisions can be reached even for spectra with signal-to-noise as low as 10. The results of SPCANet are consistent with those from other surveys such as APOGEE, GALAH and RAVE, and are also validated with the previous literature values including clusters and field stars. The catalog of the estimated parameters is available at \url{http://paperdata.china-vo.org/LAMOST/MRS_parameters_elements.csv}.

preprint2020arXiv

Students Need More Attention: BERT-based AttentionModel for Small Data with Application to AutomaticPatient Message Triage

Small and imbalanced datasets commonly seen in healthcare represent a challenge when training classifiers based on deep learning models. So motivated, we propose a novel framework based on BioBERT (Bidirectional Encoder Representations from Transformers forBiomedical TextMining). Specifically, (i) we introduce Label Embeddings for Self-Attention in each layer of BERT, which we call LESA-BERT, and (ii) by distilling LESA-BERT to smaller variants, we aim to reduce overfitting and model size when working on small datasets. As an application, our framework is utilized to build a model for patient portal message triage that classifies the urgency of a message into three categories: non-urgent, medium and urgent. Experiments demonstrate that our approach can outperform several strong baseline classifiers by a significant margin of 4.3% in terms of macro F1 score. The code for this project is publicly available at \url{https://github.com/shijing001/text_classifiers}.

preprint2020arXiv

Syntax-aware Data Augmentation for Neural Machine Translation

Data augmentation is an effective performance enhancement in neural machine translation (NMT) by generating additional bilingual data. In this paper, we propose a novel data augmentation enhancement strategy for neural machine translation. Different from existing data augmentation methods which simply choose words with the same probability across different sentences for modification, we set sentence-specific probability for word selection by considering their roles in sentence. We use dependency parse tree of input sentence as an effective clue to determine selecting probability for every words in each sentence. Our proposed method is evaluated on WMT14 English-to-German dataset and IWSLT14 German-to-English dataset. The result of extensive experiments show our proposed syntax-aware data augmentation method may effectively boost existing sentence-independent methods for significant translation performance improvement.

preprint2020arXiv

Towards Physics-informed Deep Learning for Turbulent Flow Prediction

While deep learning has shown tremendous success in a wide range of domains, it remains a grand challenge to incorporate physical principles in a systematic manner to the design, training, and inference of such models. In this paper, we aim to predict turbulent flow by learning its highly nonlinear dynamics from spatiotemporal velocity fields of large-scale fluid flow simulations of relevance to turbulence modeling and climate modeling. We adopt a hybrid approach by marrying two well-established turbulent flow simulation techniques with deep learning. Specifically, we introduce trainable spectral filters in a coupled model of Reynolds-averaged Navier-Stokes (RANS) and Large Eddy Simulation (LES), followed by a specialized U-net for prediction. Our approach, which we call turbulent-Flow Net (TF-Net), is grounded in a principled physics model, yet offers the flexibility of learned representations. We compare our model, TF-Net, with state-of-the-art baselines and observe significant reductions in error for predictions 60 frames ahead. Most importantly, our method predicts physical fields that obey desirable physical characteristics, such as conservation of mass, whilst faithfully emulating the turbulent kinetic energy field and spectrum, which are critical for accurate prediction of turbulent flows.

preprint2020arXiv

UMAP-assisted $K$-means clustering of large-scale SARS-CoV-2 mutation datasets

Coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has a worldwide devastating effect. The understanding of evolution and transmission of SARS-CoV-2 is of paramount importance for the COVID-19 control, combating, and prevention. Due to the rapid growth of both the number of SARS-CoV-2 genome sequences and the number of unique mutations, the phylogenetic analysis of SARS-CoV-2 genome isolates faces an emergent large-data challenge. We introduce a dimension-reduced $k$-means clustering strategy to tackle this challenge. We examine the performance and effectiveness of three dimension-reduction algorithms: principal component analysis (PCA), t-distributed stochastic neighbor embedding (t-SNE), and uniform manifold approximation and projection (UMAP). By using four benchmark datasets, we found that UMAP is the best-suited technique due to its stable, reliable, and efficient performance, its ability to improve clustering accuracy, especially for large Jaccard distanced-based datasets, and its superior clustering visualization. The UMAP-assisted $k$-means clustering enables us to shed light on increasingly large datasets from SARS-CoV-2 genome isolates.

preprint2020arXiv

Unveiling the molecular mechanism of SARS-CoV-2 main protease inhibition from 92 crystal structures

Currently, there is no effective antiviral drugs nor vaccine for coronavirus disease 2019 (COVID-19) caused by acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Due to its high conservativeness and low similarity with human genes, SARS-CoV-2 main protease (M$^{\text{pro}}$) is one of the most favorable drug targets. However, the current understanding of the molecular mechanism of M$^{\text{pro}}$ inhibition is limited by the lack of reliable binding affinity ranking and prediction of existing structures of M$^{\text{pro}}$-inhibitor complexes. This work integrates mathematics and deep learning (MathDL) to provide a reliable ranking of the binding affinities of 92 SARS-CoV-2 M$^{\text{pro}}$ inhibitor structures. We reveal that Gly143 residue in M$^{\text{pro}}$ is the most attractive site to form hydrogen bonds, followed by Cys145, Glu166, and His163. We also identify 45 targeted covalent bonding inhibitors. Validation on the PDBbind v2016 core set benchmark shows the MathDL has achieved the top performance with Pearson's correlation coefficient ($R_p$) being 0.858. Most importantly, MathDL is validated on a carefully curated SARS-CoV-2 inhibitor dataset with the averaged $R_p$ as high as 0.751, which endows the reliability of the present binding affinity prediction. The present binding affinity ranking, interaction analysis, and fragment decomposition offer a foundation for future drug discovery efforts.

preprint2020arXiv

What leads to generalization of object proposals?

Object proposal generation is often the first step in many detection models. It is lucrative to train a good proposal model, that generalizes to unseen classes. This could help scaling detection models to larger number of classes with fewer annotations. Motivated by this, we study how a detection model trained on a small set of source classes can provide proposals that generalize to unseen classes. We systematically study the properties of the dataset - visual diversity and label space granularity - required for good generalization. We show the trade-off between using fine-grained labels and coarse labels. We introduce the idea of prototypical classes: a set of sufficient and necessary classes required to train a detection model to obtain generalized proposals in a more data-efficient way. On the Open Images V4 dataset, we show that only 25% of the classes can be selected to form such a prototypical set. The resulting proposals from a model trained with these classes is only 4.3% worse than using all the classes, in terms of average recall (AR). We also demonstrate that Faster R-CNN model leads to better generalization of proposals compared to a single-stage network like RetinaNet.

Rui Wang

Quick read

Decide how to stay connected

How to connect with this researcher

Open a focused conversation when the fit is right

See the researcher in context

Building this graph slice

187 published item(s)

Federated Cross-Client Subgraph Pattern Detection

Large-Small Model Collaboration for Farmland Semantic Change Detection

PrepBench: How Far Are We from Natural-Language-Driven Data Preparation?

SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning

TouchMap-OR: Multi-View 3D Mapping of Hand-Surface Contacts

Towards Backdoor-Based Ownership Verification for Vision-Language-Action Models

Decoupling Constraint from Two Direction in Evolutionary Constrained Multi-objective Optimization

Observation and manipulation of quantum interference in a superconducting Kerr parametric oscillator

Phase Transition Study meets Machine Learning

Structured Learning in Time-dependent Cox Models

A Theory of Human-Like Few-Shot Learning

An Indoor Environment Sensing and Localization System via mmWave Phased Array

Boosting Large Language Model for Speech Synthesis: An Empirical Study

On the nature of overcharging and charge inversion in electrical double layers

PACO: Parts and Attributes of Common Objects

Universal Multimodal Representation for Language Understanding

Workload Failure Prediction for Data Centers

A new class of bilayer kagome lattice compounds with Dirac nodal lines and pressure-induced superconductivity

A novel method for data augmentation: Nine Dot Moving Least Square (ND-MLS)

A Study of Syntactic Multi-Modality in Non-Autoregressive Machine Translation

Accelerating Edge Intelligence via Integrated Sensing and Communication

Accelerating Federated Edge Learning via Topology Optimization

An approximate randomization test for high-dimensional two-sample Behrens-Fisher problem under arbitrary covariances

An Interactive Image-based Modeling System

Analysis of the distribution, rotation and scale characteristics of solar wind switchbacks: comparison between the first and second encounters of Parker Solar Probe

Approximately Equivariant Networks for Imperfectly Symmetric Dynamics

Beamforming Design and Performance Evaluation for Reconfigurable Intelligent Surface Assisted Wireless Communication Systems With Non-Ideal Hardware

BEVT: BERT Pretraining of Video Transformers

Bridging the Data Gap between Training and Inference for Unsupervised Neural Machine Translation

Buildup of the Magnetic Flux Ropes in Homologous Solar Eruptions

CCP: Correlated Clustering and Projection for Dimensionality Reduction

Chern-Simons superconductors and their instabilities

Collaborative Representation for SPD Matrices with Application to Image-Set Classification

Cross-domain Contrastive Learning for Unsupervised Domain Adaptation

Data Augmentation vs. Equivariant Networks: A Theory of Generalization on Dynamics Forecasting

Deep Reinforcement Learning for Online Routing of Unmanned Aerial Vehicles with Wireless Power Transfer

Determining the number of factors in a large-dimensional generalised factor model

DreamNet: A Deep Riemannian Network based on SPD Manifold Learning for Visual Classification

Edge Federated Learning Via Unit-Modulus Over-The-Air Computation

Effect of Homomorphic Encryption on the Performance of Training Federated Learning Generative Adversarial Networks

Efficient and High-quality Prehensile Rearrangement in Cluttered and Confined Spaces

Efficient conditioned face animation using frontally-viewed embedding

EfficientTDNN: Efficient Architecture Search for Speaker Recognition

Evaluation of Four Black-box Adversarial Attacks and Some Query-efficient Improvement Analysis

Exact solutions of Kondo problems in higher-order fermions

Fano Interference in a Single-Molecule Junction

FLVoogd: Robust And Privacy Preserving Federated Learning

Grassmannian Discriminant Maps (GDM) for Manifold Dimensionality Reduction with Application to Image Set Classification

High quality entanglement distribution through telecommunication fiber using near-infrared non-degenerate photon pairs

Hybridization of evolutionary algorithm and deep reinforcement learning for multi-objective orienteering optimization

Hyperspectral Unmixing Based on Nonnegative Matrix Factorization: A Comprehensive Review

Improving Deep Image Matting via Local Smoothness Assumption

LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT

M Subdwarf Research III. Spectroscopic Diagnostics for Breaking Parameter Degeneracy

MINERVAS: Massive INterior EnviRonments VirtuAl Synthesis

Model Pruning Based on Quantified Similarity of Feature Maps

Morphological Anti-Aliasing Method for Boundary Slope Prediction

MULTI-FLGANs: Multi-Distributed Adversarial Networks for Non-IID distribution

Multi-objective Pointer Network for Combinatorial Optimization

Multi-View Self-Attention Based Transformer for Speaker Recognition

Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios

Normal and Visibility Estimation of Human Face from a Single Image

On the Effectiveness of Pinyin-Character Dual-Decoding for End-to-End Mandarin Chinese ASR

Online Object Model Reconstruction and Reuse for Lifelong Improvement of Robot Manipulation

Parallel Pre-trained Transformers (PPT) for Synthetic Data-based Instance Segmentation

Parameter Choices for Sparse Regularization with the $\ell_1$ Norm

Passive Motion Detection via mmWave Communication System

Persistent Homology for Effective Non-Prehensile Manipulation

Persistent Path Laplacian

PriFit: Learning to Fit Primitives Improves Few Shot Point Cloud Segmentation

Q-balls Formation and the Production of Gravitational Waves With Non-minimal Gravitational Coupling

R2: A Distributed Remote Function Execution Mechanism With Built-in Metadata