Researcher profile

Jun Wang

Jun Wang contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author

160works

0followers

47topics

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

SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory

Existing benchmarks for multimodal memory reasoning largely evaluate systems within pre-assembled contexts, but under-evaluate whether agents can use evidence distributed across independently originated sources. We argue that source-distributed memory composition is an important and under-examined bottleneck in multimodal agent memory, especially when relevant evidence is fragmented across heterogeneous artifacts such as conversations, profiles, screenshots, tables, images, and documents. To address this gap, we introduce Source-distributed Multimodal Memory Benchmark(SMMBench), which measures whether agents can retrieve, align, and compose multimodal evidence scattered across multiple sources rather than reason within a single curated context. SMMBench evaluates four core capabilities: (1) cross-source multimodal reasoning; (2) conflict resolution; (3) preference reasoning; (4) memory-grounded action prediction. The benchmark contains 1877 samples grounded in 264 sources. Experiments on representative memory-style and retrieval-based baselines show that current systems still struggle on these capabilities, positioning source-distributed multimodal memory as an important and still under-evaluated challenge for multimodal agents. Our data are available at https://huggingface.co/datasets/HuacanChai/SMMBench.

preprint2026arXiv

The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design

Visual perception in modern Vision-Language Models (VLMs) is constrained by a perceptual bandwidth bottleneck: a broad field of view preserves global context but sacrifices the fine-grained details required for complex reasoning. We argue that high-resolution visual reasoning is therefore not only semantic reasoning but also task-relevant evidence acquisition under limited perceptual bandwidth. Inspired by active vision and information foraging, we formalise this process as sequential Bayesian optimal experimental design (S-BOED), where an agent decides which visual evidence to acquire before answering. Since exact Bayesian inference is intractable in continuous gigapixel spaces, we derive a tractable coverage--resolution objective as a proxy for task-relevant information gain. We instantiate this framework with FOVEA, a training-free procedure that refines VLM crop proposals through evidence-oriented probing. Experiments on high-resolution benchmarks show consistent gains over direct and ReAct-style baselines, with particularly strong improvements in search-dominated remote-sensing settings.

preprint2026arXiv

Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction

Agentic web search increasingly faces two distinct demands: deep reasoning over a single target, and structured aggregation across many entities and heterogeneous sources. Current systems struggle on both fronts. Breadth-oriented tasks demand schema-aligned outputs with wide coverage and cross-entity consistency, while depth-oriented tasks require coherent reasoning over long, branching search trajectories. We introduce \textbf{Web2BigTable}, a multi-agent framework for web-to-table search that supports both regimes. Web2BigTable adopts a bi-level architecture in which an upper-level orchestrator decomposes the task into sub-problems and lower-level worker agents solve them in parallel. Through a closed-loop run--verify--reflect process, the framework jointly improves decomposition and execution over time via persistent, human-readable external memory, with self-evolving updates to each single-agent. During execution, workers coordinate through a shared workspace that makes partial findings visible, allowing them to reduce redundant exploration, reconcile conflicting evidence, and adapt to emerging coverage gaps. Web2BigTable sets a new state of the art on WideSearch, reaching an Avg@4 Success Rate of \textbf{38.50} ($7.5\times$ the second best at 5.10), Row F1 of \textbf{63.53} (+25.03 over the second best), and Item F1 of \textbf{80.12} (+14.42 over the second best). It also generalises to depth-oriented search on XBench-DeepSearch, achieving 73.0 accuracy. Code is available at https://github.com/web2bigtable/web2bigtable.

preprint2025arXiv

Constrained Language Model Policy Optimization via Risk-aware Stepwise Alignment

When fine-tuning pre-trained Language Models (LMs) to exhibit desired behaviors, maintaining control over risk is critical for ensuring both safety and trustworthiness. Most existing safety alignment methods, such as Safe RLHF and SACPO, typically operate under a risk-neutral paradigm that is insufficient to address the risks arising from deviations from the reference policy and offers limited robustness against rare but potentially catastrophic harmful behaviors. To address this limitation, we propose Risk-aware Stepwise Alignment (RSA), a novel alignment method that explicitly incorporates risk awareness into the policy optimization process by leveraging a class of nested risk measures. Specifically, RSA formulates safety alignment as a token-level risk-aware constrained policy optimization problem and solves it through a stepwise alignment procedure that yields token-level policy updates derived from the nested risk measures. This design offers two key benefits: (1) it mitigates risks induced by excessive model shift away from a reference policy, and (2) it explicitly suppresses low-probability yet high-impact harmful behaviors. Moreover, we provide theoretical analysis on policy optimality under mild assumptions. Experimental results demonstrate that our method achieves high levels of helpfulness while ensuring strong safety and significantly suppresses tail risks, namely low-probability yet high-impact unsafe responses.

preprint2024arXiv

Multi-stages attention Breast cancer classification based on nonlinear spiking neural P neurons with autapses

Breast cancer(BC) is a prevalent type of malignant tumor in women. Early diagnosis and treatment are vital for enhancing the patients' survival rate. Downsampling in deep networks may lead to loss of information, so for compensating the detail and edge information and allowing convolutional neural networks to pay more attention to seek the lesion region, we propose a multi-stages attention architecture based on NSNP neurons with autapses. First, unlike the single-scale attention acquisition methods of existing methods, we set up spatial attention acquisition at each feature map scale of the convolutional network to obtain an fusion global information on attention guidance. Then we introduce a new type of NSNP variants called NSNP neurons with autapses. Specifically, NSNP systems are modularized as feature encoders, recoding the features extracted from convolutional neural network as well as the fusion of attention information and preserve the key characteristic elements in feature maps. This ensures the retention of valuable data while gradually transforming high-dimensional complicated info into low-dimensional ones. The proposed method is evaluated on the public dataset BreakHis at various magnifications and classification tasks. It achieves a classification accuracy of 96.32% at all magnification cases, outperforming state-of-the-art methods. Ablation studies are also performed, verifying the proposed model's efficacy. The source code is available at XhuBobYoung/Breast-cancer-Classification.

preprint2024arXiv

SLP-Net:An efficient lightweight network for segmentation of skin lesions

Prompt treatment for melanoma is crucial. To assist physicians in identifying lesion areas precisely in a quick manner, we propose a novel skin lesion segmentation technique namely SLP-Net, an ultra-lightweight segmentation network based on the spiking neural P(SNP) systems type mechanism. Most existing convolutional neural networks achieve high segmentation accuracy while neglecting the high hardware cost. SLP-Net, on the contrary, has a very small number of parameters and a high computation speed. We design a lightweight multi-scale feature extractor without the usual encoder-decoder structure. Rather than a decoder, a feature adaptation module is designed to replace it and implement multi-scale information decoding. Experiments at the ISIC2018 challenge demonstrate that the proposed model has the highest Acc and DSC among the state-of-the-art methods, while experiments on the PH2 dataset also demonstrate a favorable generalization ability. Finally, we compare the computational complexity as well as the computational speed of the models in experiments, where SLP-Net has the highest overall superiority

preprint2023arXiv

A Siamese-based Verification System for Open-set Architecture Attribution of Synthetic Images

Despite the wide variety of methods developed for synthetic image attribution, most of them can only attribute images generated by models or architectures included in the training set and do not work with unknown architectures, hindering their applicability in real-world scenarios. In this paper, we propose a verification framework that relies on a Siamese Network to address the problem of open-set attribution of synthetic images to the architecture that generated them. We consider two different settings. In the first setting, the system determines whether two images have been produced by the same generative architecture or not. In the second setting, the system verifies a claim about the architecture used to generate a synthetic image, utilizing one or multiple reference images generated by the claimed architecture. The main strength of the proposed system is its ability to operate in both closed and open-set scenarios so that the input images, either the query and reference images, can belong to the architectures considered during training or not. Experimental evaluations encompassing various generative architectures such as GANs, diffusion models, and transformers, focusing on synthetic face image generation, confirm the excellent performance of our method in both closed and open-set settings, as well as its strong generalization capabilities.

preprint2023arXiv

AGConv: Adaptive Graph Convolution on 3D Point Clouds

Convolution on 3D point clouds is widely researched yet far from perfect in geometric deep learning. The traditional wisdom of convolution characterises feature correspondences indistinguishably among 3D points, arising an intrinsic limitation of poor distinctive feature learning. In this paper, we propose Adaptive Graph Convolution (AGConv) for wide applications of point cloud analysis. AGConv generates adaptive kernels for points according to their dynamically learned features. Compared with the solution of using fixed/isotropic kernels, AGConv improves the flexibility of point cloud convolutions, effectively and precisely capturing the diverse relations between points from different semantic parts. Unlike the popular attentional weight schemes, AGConv implements the adaptiveness inside the convolution operation instead of simply assigning different weights to the neighboring points. Extensive evaluations clearly show that our method outperforms state-of-the-arts of point cloud classification and segmentation on various benchmark datasets.Meanwhile, AGConv can flexibly serve more point cloud analysis approaches to boost their performance. To validate its flexibility and effectiveness, we explore AGConv-based paradigms of completion, denoising, upsampling, registration and circle extraction, which are comparable or even superior to their competitors. Our code is available at https://github.com/hrzhou2/AdaptConv-master.

preprint2023arXiv

Communication under Mixed Gaussian-Impulsive Channel: An End-to-End Framework

In many communication scenarios, the communication signals simultaneously suffer from white Gaussian noise (WGN) and non-Gaussian impulsive noise (IN), i.e., mixed Gaussian-impulsive noise (MGIN). Under MGIN channel, classical communication signal schemes and corresponding detection methods usually can not achieve desirable performance as they are optimized with respect to WGN. Moreover, as the widely adopted IN model has no analytical and general closed-form expression of probability density function (PDF), it is extremely hard to obtain optimal communication signal and corresponding detection schemes based on classical stochastic signal processing theory. To circumvent these difficulties, we propose a data-driven end-to-end framework to address the communication signal design and detection under MGIN channel in this paper. In this proposed framework, a channel noise simulator (CNS) is elaborately designed based on an improved generative adversarial net (GAN) to simulate the MGIN without requirement of any analytical PDF. Meanwhile, a multi-level wavelet convolutional neural network (MWCNN) based preprocessing network is used to mitigate the negative effect of outliers due to the IN. Compared with conventional approaches and existing end-to-end systems, extensive simulation results verify that our proposed novel end-to-end communication system can achieve better performance in terms of bit-error rate (BER) under MGIN environments.

preprint2023arXiv

Cross Tensor Approximation for Image and Video Completion

This paper proposes a general framework to use the cross tensor approximation or tensor ColUmn-Row (CUR) approximation for reconstructing incomplete images and videos. The key importance of the new algorithms is their simplicity and ease of implementation with low computational complexity. For the case of data tensors with 1) structural missing components or 2) a high missing rate, we propose an efficient smooth tensor CUR algorithms which first make the sampled fibers smooth and then apply the proposed CUR algorithms. The numerical experiments show the significant benefit of this smoothing procedure. The main contribution of this paper is to develop/investigate improved multistage CUR algorithms with filtering (smoothing ) preprocessing for tensor completion. The second contribution is a detailed comparison of the performance of image recovery for four different CUR strategies via extensive computer simulations. Our simulations clearly indicated that the proposed algorithms are much faster than most of the existing state-of-the-art algorithms developed for tensor completion, while performance is comparable and often even better. Furthermore, we will provide in GitHub the MATLAB codes which can be used for various applications. Moreover, to our best knowledge, the CUR (cross approximation) algorithms have not been investigated nor compared till now for image and video completion.

preprint2023arXiv

MANAS: Multi-Agent Neural Architecture Search

The Neural Architecture Search (NAS) problem is typically formulated as a graph search problem where the goal is to learn the optimal operations over edges in order to maximise a graph-level global objective. Due to the large architecture parameter space, efficiency is a key bottleneck preventing NAS from its practical use. In this paper, we address the issue by framing NAS as a multi-agent problem where agents control a subset of the network and coordinate to reach optimal architectures. We provide two distinct lightweight implementations, with reduced memory requirements (1/8th of state-of-the-art), and performances above those of much more computationally expensive methods. Theoretically, we demonstrate vanishing regrets of the form O(sqrt(T)), with T being the total number of rounds. Finally, aware that random search is an, often ignored, effective baseline we perform additional experiments on 3 alternative datasets and 2 network configurations, and achieve favourable results in comparison.

preprint2023arXiv

On the Complexity of Computing Markov Perfect Equilibrium in General-Sum Stochastic Games

Similar to the role of Markov decision processes in reinforcement learning, Stochastic Games (SGs) lay the foundation for the study of multi-agent reinforcement learning (MARL) and sequential agent interactions. In this paper, we derive that computing an approximate Markov Perfect Equilibrium (MPE) in a finite-state discounted Stochastic Game within the exponential precision is \textbf{PPAD}-complete. We adopt a function with a polynomially bounded description in the strategy space to convert the MPE computation to a fixed-point problem, even though the stochastic game may demand an exponential number of pure strategies, in the number of states, for each agent. The completeness result follows the reduction of the fixed-point problem to {\sc End of the Line}. Our results indicate that finding an MPE in SGs is highly unlikely to be \textbf{NP}-hard unless \textbf{NP}=\textbf{co-NP}. Our work offers confidence for MARL research to study MPE computation on general-sum SGs and to develop fruitful algorithms as currently on zero-sum SGs.

preprint2022arXiv

A Comprehensive Survey on Aerial Mobile Edge Computing: Challenges, State-of-the-Art, and Future Directions

Driven by the visions of Internet of Things (IoT), there is an ever-increasing demand for computation resources of IoT users to support diverse applications. Mobile edge computing (MEC) has been deemed a promising solution to settle the conflict between the resource-hungry mobile applications and the resource-constrained IoT users. On the other hand, in order to provide ubiquitous and reliable connectivity in wireless networks, unmanned aerial vehicles (UAVs) can be leveraged as efficient aerial platforms by exploiting their inherent attributes, such as the on-demand deployment, high cruising altitude, and controllable maneuverability in three-dimensional (3D) space. Thus, the UAV-enabled aerial MEC is believed as a win-win solution to facilitate cost-effective and energy-saving communication and computation services in various environments. In this paper, we provide a comprehensive survey on the UAV-enabled aerial MEC. Firstly, the related advantages and research challenges for aerial MEC are discussed. Then, we provide a comprehensive review of the recent research advances, which is categorized by different domains, including the joint optimization of UAV trajectory, computation offloading and resource allocation, UAV deployment, task scheduling and load balancing, interplay between aerial MEC and other technologies, as well as the machine-learning (ML)-driven optimization. Finally, some important research directions deserved more efforts in future work are summarized.

preprint2022arXiv

A Game-Theoretic Approach for Improving Generalization Ability of TSP Solvers

In this paper, we introduce a two-player zero-sum framework between a trainable \emph{Solver} and a \emph{Data Generator} to improve the generalization ability of deep learning-based solvers for Traveling Salesman Problem (TSP). Grounded in \textsl{Policy Space Response Oracle} (PSRO) methods, our two-player framework outputs a population of best-responding Solvers, over which we can mix and output a combined model that achieves the least exploitability against the Generator, and thereby the most generalizable performance on different TSP tasks. We conduct experiments on a variety of TSP instances with different types and sizes. Results suggest that our Solvers achieve the state-of-the-art performance even on tasks the Solver never meets, whilst the performance of other deep learning-based Solvers drops sharply due to over-fitting. To demonstrate the principle of our framework, we study the learning outcome of the proposed two-player game and demonstrate that the exploitability of the Solver population decreases during training, and it eventually approximates the Nash equilibrium along with the Generator.

preprint2022arXiv

A simple normalization technique using window statistics to improve the out-of-distribution generalization on medical images

Since data scarcity and data heterogeneity are prevailing for medical images, well-trained Convolutional Neural Networks (CNNs) using previous normalization methods may perform poorly when deployed to a new site. However, a reliable model for real-world clinical applications should be able to generalize well both on in-distribution (IND) and out-of-distribution (OOD) data (e.g., the new site data). In this study, we present a novel normalization technique called window normalization (WIN) to improve the model generalization on heterogeneous medical images, which is a simple yet effective alternative to existing normalization methods. Specifically, WIN perturbs the normalizing statistics with the local statistics computed on the window of features. This feature-level augmentation technique regularizes the models well and improves their OOD generalization significantly. Taking its advantage, we propose a novel self-distillation method called WIN-WIN for classification tasks. WIN-WIN is easily implemented with twice forward passes and a consistency constraint, which can be a simple extension for existing methods. Extensive experimental results on various tasks (6 tasks) and datasets (24 datasets) demonstrate the generality and effectiveness of our methods.

preprint2022arXiv

AA-Forecast: Anomaly-Aware Forecast for Extreme Events

Time series models often deal with extreme events and anomalies, both prevalent in real-world datasets. Such models often need to provide careful probabilistic forecasting, which is vital in risk management for extreme events such as hurricanes and pandemics. However, it is challenging to automatically detect and learn to use extreme events and anomalies for large-scale datasets, which often require manual effort. Hence, we propose an anomaly-aware forecast framework that leverages the previously seen effects of anomalies to improve its prediction accuracy during and after the presence of extreme events. Specifically, the framework automatically extracts anomalies and incorporates them through an attention mechanism to increase its accuracy for future extreme events. Moreover, the framework employs a dynamic uncertainty optimization algorithm that reduces the uncertainty of forecasts in an online manner. The proposed framework demonstrated consistent superior accuracy with less uncertainty on three datasets with different varieties of anomalies over the current prediction models.

preprint2022arXiv

Afterpulse measurement of JUNO 20-inch PMTs

In this article we present the large photo-multiplier tube (PMT) afterpulse measurement results of Jiangmen Underground Neutrino Observatory (JUNO) experiment. Totally 11 dynode-PMTs (R12860) from Hamamatsu company and 150 micro-channel plate PMTs (MCP-PMTs, GDB-6201) from NNVT company were tested, an afterpulse model is built according to the afterpulse time distribution and probability of occurrence for these two types of PMTs. The average ratio between the total afterpulse charge with the delay between 0.5 $μ$ s and 20 $μ$ s to the primary pulse charge is 5.6%(13.2%) for the tested MCP-PMTs (dynode-PMTs). JUNO experiment will deploy 20,012 20-inch PMTs, and this study will benefit the detector simulation, event reconstruction and data analysis of JUNO experiment.

preprint2022arXiv

An Architecture for the detection of GAN-generated Flood Images with Localization Capabilities

In this paper, we address a new image forensics task, namely the detection of fake flood images generated by ClimateGAN architecture. We do so by proposing a hybrid deep learning architecture including both a detection and a localization branch, the latter being devoted to the identification of the image regions manipulated by ClimateGAN. Even if our goal is the detection of fake flood images, in fact, we found that adding a localization branch helps the network to focus on the most relevant image regions with significant improvements in terms of generalization capabilities and robustness against image processing operations. The good performance of the proposed architecture is validated on two datasets of pristine flood images downloaded from the internet and three datasets of fake flood images generated by ClimateGAN starting from a large set of diverse street images.

preprint2022arXiv

BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis

Diffusion probabilistic models (DPMs) and their extensions have emerged as competitive generative models yet confront challenges of efficient sampling. We propose a new bilateral denoising diffusion model (BDDM) that parameterizes both the forward and reverse processes with a schedule network and a score network, which can train with a novel bilateral modeling objective. We show that the new surrogate objective can achieve a lower bound of the log marginal likelihood tighter than a conventional surrogate. We also find that BDDM allows inheriting pre-trained score network parameters from any DPMs and consequently enables speedy and stable learning of the schedule network and optimization of a noise schedule for sampling. Our experiments demonstrate that BDDMs can generate high-fidelity audio samples with as few as three sampling steps. Moreover, compared to other state-of-the-art diffusion-based neural vocoders, BDDMs produce comparable or higher quality samples indistinguishable from human speech, notably with only seven sampling steps (143x faster than WaveGrad and 28.6x faster than DiffWave). We release our code at https://github.com/tencent-ailab/bddm.

preprint2022arXiv

BI-GreenNet: Learning Green's functions by boundary integral network

Green's function plays a significant role in both theoretical analysis and numerical computing of partial differential equations (PDEs). However, in most cases, Green's function is difficult to compute. The troubles arise in the following three folds. Firstly, compared with the original PDE, the dimension of Green's function is doubled, making it impossible to be handled by traditional mesh-based methods. Secondly, Green's function usually contains singularities which increase the difficulty to get a good approximation. Lastly, the computational domain may be very complex or even unbounded. To override these problems, we leverage the fundamental solution, boundary integral method and neural networks to develop a new method for computing Green's function with high accuracy in this paper. We focus on Green's function of Poisson and Helmholtz equations in bounded domains, unbounded domains. We also consider Poisson equation and Helmholtz domains with interfaces. Extensive numerical experiments illustrate the efficiency and the accuracy of our method for solving Green's function. In addition, we also use the Green's function calculated by our method to solve a class of PDE, and also obtain high-precision solutions, which shows the good generalization ability of our method on solving PDEs.

preprint2022arXiv

Borsuk's partition problem in four-dimensional $\ell_{p}$ space

In 1933, Borsuk made a conjecture that every $n$-dimensional bounded set can be divided into $n+1$ subsets of smaller diameter. Up to now, the problem is still open for $4\leq n\leq 63$. In this paper, we firstly discuss the Banach-Mazur distance between the $n$-dimensional cube and the $\ell_{p}$ ball $(1\leq p< 2)$, then we study the generalized Borsuk's partition problem in metric spaces and prove that all bounded sets $X$ in every four-dimensional $\ell_{p}$ space can be divided into $2^4$ subsets of smaller diameter.

preprint2022arXiv

Branch Ranking for Efficient Mixed-Integer Programming via Offline Ranking-based Policy Learning

Deriving a good variable selection strategy in branch-and-bound is essential for the efficiency of modern mixed-integer programming (MIP) solvers. With MIP branching data collected during the previous solution process, learning to branch methods have recently become superior over heuristics. As branch-and-bound is naturally a sequential decision making task, one should learn to optimize the utility of the whole MIP solving process instead of being myopic on each step. In this work, we formulate learning to branch as an offline reinforcement learning (RL) problem, and propose a long-sighted hybrid search scheme to construct the offline MIP dataset, which values the long-term utilities of branching decisions. During the policy training phase, we deploy a ranking-based reward assignment scheme to distinguish the promising samples from the long-term or short-term view, and train the branching model named Branch Ranking via offline policy learning. Experiments on synthetic MIP benchmarks and real-world tasks demonstrate that Branch Rankink is more efficient and robust, and can better generalize to large scales of MIP instances compared to the widely used heuristics and state-of-the-art learning-based branching models.

preprint2022arXiv

CandidateDrug4Cancer: An Open Molecular Graph Learning Benchmark on Drug Discovery for Cancer

Anti-cancer drug discoveries have been serendipitous, we sought to present the Open Molecular Graph Learning Benchmark, named CandidateDrug4Cancer, a challenging and realistic benchmark dataset to facilitate scalable, robust, and reproducible graph machine learning research for anti-cancer drug discovery. CandidateDrug4Cancer dataset encompasses multiple most-mentioned 29 targets for cancer, covering 54869 cancer-related drug molecules which are ranged from pre-clinical, clinical and FDA-approved. Besides building the datasets, we also perform benchmark experiments with effective Drug Target Interaction (DTI) prediction baselines using descriptors and expressive graph neural networks. Experimental results suggest that CandidateDrug4Cancer presents significant challenges for learning molecular graphs and targets in practical application, indicating opportunities for future researches on developing candidate drugs for treating cancers.

preprint2022arXiv

Chinese Word Segmentation with Heterogeneous Graph Neural Network

In recent years, deep learning has achieved significant success in the Chinese word segmentation (CWS) task. Most of these methods improve the performance of CWS by leveraging external information, e.g., words, sub-words, syntax. However, existing approaches fail to effectively integrate the multi-level linguistic information and also ignore the structural feature of the external information. Therefore, in this paper, we proposed a framework to improve CWS, named HGNSeg. It exploits multi-level external information sufficiently with the pre-trained language model and heterogeneous graph neural network. The experimental results on six benchmark datasets (e.g., Bakeoff 2005, Bakeoff 2008) validate that our approach can effectively improve the performance of Chinese word segmentation. Importantly, in cross-domain scenarios, our method also shows a strong ability to alleviate the out-of-vocabulary (OOV) problem.

preprint2022arXiv

Cross Attention-guided Dense Network for Images Fusion

In recent years, various applications in computer vision have achieved substantial progress based on deep learning, which has been widely used for image fusion and shown to achieve adequate performance. However, suffering from limited ability in modeling the spatial correspondence of different source images, it still remains a great challenge for existing unsupervised image fusion models to extract appropriate feature and achieves adaptive and balanced fusion. In this paper, we propose a novel cross-attention-guided image fusion network, which is a unified and unsupervised framework for multi-modal image fusion, multi-exposure image fusion, and multi-focus image fusion. Different from the existing self-attention module, our cross-attention module focus on modeling the cross-correlation between different source images. Using the proposed cross attention module as a core block, a densely connected cross attention-guided network is built to dynamically learn the spatial correspondence to derive better alignment of important details from different input images. Meanwhile, an auxiliary branch is also designed to model the long-range information, and a merging network is attached to finally reconstruct the fusion image. Extensive experiments have been carried out on publicly available datasets, and the results demonstrate that the proposed model outperforms the state-of-the-art quantitatively and qualitatively.

preprint2022arXiv

Cross-modal Prototype Driven Network for Radiology Report Generation

Radiology report generation (RRG) aims to describe automatically a radiology image with human-like language and could potentially support the work of radiologists, reducing the burden of manual reporting. Previous approaches often adopt an encoder-decoder architecture and focus on single-modal feature learning, while few studies explore cross-modal feature interaction. Here we propose a Cross-modal PROtotype driven NETwork (XPRONET) to promote cross-modal pattern learning and exploit it to improve the task of radiology report generation. This is achieved by three well-designed, fully differentiable and complementary modules: a shared cross-modal prototype matrix to record the cross-modal prototypes; a cross-modal prototype network to learn the cross-modal prototypes and embed the cross-modal information into the visual and textual features; and an improved multi-label contrastive loss to enable and enhance multi-label prototype learning. XPRONET obtains substantial improvements on the IU-Xray and MIMIC-CXR benchmarks, where its performance exceeds recent state-of-the-art approaches by a large margin on IU-Xray and comparable performance on MIMIC-CXR.

preprint2022arXiv

Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-Speech

Modelling prosody variation is critical for synthesizing natural and expressive speech in end-to-end text-to-speech (TTS) systems. In this paper, a cross-utterance conditional VAE (CUC-VAE) is proposed to estimate a posterior probability distribution of the latent prosody features for each phoneme by conditioning on acoustic features, speaker information, and text features obtained from both past and future sentences. At inference time, instead of the standard Gaussian distribution used by VAE, CUC-VAE allows sampling from an utterance-specific prior distribution conditioned on cross-utterance information, which allows the prosody features generated by the TTS system to be related to the context and is more similar to how humans naturally produce prosody. The performance of CUC-VAE is evaluated via a qualitative listening test for naturalness, intelligibility and quantitative measurements, including word error rates and the standard deviation of prosody attributes. Experimental results on LJ-Speech and LibriTTS data show that the proposed CUC-VAE TTS system improves naturalness and prosody diversity with clear margins.

preprint2022arXiv

CSDN: Cross-modal Shape-transfer Dual-refinement Network for Point Cloud Completion

How will you repair a physical object with some missings? You may imagine its original shape from previously captured images, recover its overall (global) but coarse shape first, and then refine its local details. We are motivated to imitate the physical repair procedure to address point cloud completion. To this end, we propose a cross-modal shape-transfer dual-refinement network (termed CSDN), a coarse-to-fine paradigm with images of full-cycle participation, for quality point cloud completion. CSDN mainly consists of "shape fusion" and "dual-refinement" modules to tackle the cross-modal challenge. The first module transfers the intrinsic shape characteristics from single images to guide the geometry generation of the missing regions of point clouds, in which we propose IPAdaIN to embed the global features of both the image and the partial point cloud into completion. The second module refines the coarse output by adjusting the positions of the generated points, where the local refinement unit exploits the geometric relation between the novel and the input points by graph convolution, and the global constraint unit utilizes the input image to fine-tune the generated offset. Different from most existing approaches, CSDN not only explores the complementary information from images but also effectively exploits cross-modal data in the whole coarse-to-fine completion procedure. Experimental results indicate that CSDN performs favorably against ten competitors on the cross-modal benchmark.

preprint2022arXiv

Debiased Recommendation with User Feature Balancing

Debiased recommendation has recently attracted increasing attention from both industry and academic communities. Traditional models mostly rely on the inverse propensity score (IPS), which can be hard to estimate and may suffer from the high variance issue. To alleviate these problems, in this paper, we propose a novel debiased recommendation framework based on user feature balancing. The general idea is to introduce a projection function to adjust user feature distributions, such that the ideal unbiased learning objective can be upper bounded by a solvable objective purely based on the offline dataset. In the upper bound, the projected user distributions are expected to be equal given different items. From the causal inference perspective, this requirement aims to remove the causal relation from the user to the item, which enables us to achieve unbiased recommendation, bypassing the computation of IPS. In order to efficiently balance the user distributions upon each item pair, we propose three strategies, including clipping, sampling and adversarial learning to improve the training process. For more robust optimization, we deploy an explicit model to capture the potential latent confounders in recommendation systems. To the best of our knowledge, this paper is the first work on debiased recommendation based on confounder balancing. In the experiments, we compare our framework with many state-of-the-art methods based on synthetic, semi-synthetic and real-world datasets. Extensive experiments demonstrate that our model is effective in promoting the recommendation performance.

preprint2022arXiv

Deep Algebraic Fitting for Multiple Circle Primitives Extraction from Raw Point Clouds

The shape of circle is one of fundamental geometric primitives of man-made engineering objects. Thus, extraction of circles from scanned point clouds is a quite important task in 3D geometry data processing. However, existing circle extraction methods either are sensitive to the quality of raw point clouds when classifying circle-boundary points, or require well-designed fitting functions when regressing circle parameters. To relieve the challenges, we propose an end-to-end Point Cloud Circle Algebraic Fitting Network (Circle-Net) based on a synergy of deep circle-boundary point feature learning and weighted algebraic fitting. First, we design a circle-boundary learning module, which considers local and global neighboring contexts of each point, to detect all potential circle-boundary points. Second, we develop a deep feature based circle parameter learning module for weighted algebraic fitting, without designing any weight metric, to avoid the influence of outliers during fitting. Unlike most of the cutting-edge circle extraction wisdoms, the proposed classification-and-fitting modules are originally co-trained with a comprehensive loss to enhance the quality of extracted circles.Comparisons on the established dataset and real-scanned point clouds exhibit clear improvements of Circle-Net over SOTAs in terms of both noise-robustness and extraction accuracy. We will release our code, model, and data for both training and evaluation on GitHub upon publication.

preprint2022arXiv

Demonstration of room-temperature continuous-wave operation of InGaAs/AlGaAs quantum well lasers directly grown on on-axis silicon (001)

Room-temperature continuous-wave operation of InGaAs/AlGaAs quantum well lasers directly grown on on-axis silicon (001) has been demonstrated. A 420 nm thick GaAs epilayer completely free of antiphase domains was initially grown on the silicon substrate in a metal-organic chemical vapor deposition system and the other epilayers including four sets of five-period strained-layer superlattices and the laser-structural layers were successively grown in a molecular beam epitaxy system. The lasers were prepared as broad-stripe Fabry-Perot ones with a stripe width of 21.5 um and a cavity length of 1 mm. Typically, the threshold current and the corresponding threshold current density are 186.4 mA and 867 A/cm2, respectively. The lasing wavelength is around 980 nm and the slope efficiency is 0.097 W/A with a single-facet output power of 22.5 mW at an injection current of 400 mA. This advancement makes the silicon-based monolithic optoelectronic integration relevant to quantum well lasers more promising with an enhanced feasibility.

preprint2022arXiv

Deterministic Identification over Channels without CSI

Identification capacities of randomized and deterministic identification were proved to exceed channel capacity for Gaussian channels \emph{with} channel side information (CSI). In this work, we extend deterministic identification to the block fading channels without CSI by applying identification codes for both channel estimation and user identification. We prove that identification capacity is asymptotically higher than transmission capacity even in the absence of CSI. And we also analyze the finite-length performance theoretically and numerically. The simulation results verify the feasibility of the proposed blind deterministic identification in finite blocklength regime.

preprint2022arXiv

Differentiable and Scalable Generative Adversarial Models for Data Imputation

Data imputation has been extensively explored to solve the missing data problem. The dramatically increasing volume of incomplete data makes the imputation models computationally infeasible in many real-life applications. In this paper, we propose an effective scalable imputation system named SCIS to significantly speed up the training of the differentiable generative adversarial imputation models under accuracy-guarantees for large-scale incomplete data. SCIS consists of two modules, differentiable imputation modeling (DIM) and sample size estimation (SSE). DIM leverages a new masking Sinkhorn divergence function to make an arbitrary generative adversarial imputation model differentiable, while for such a differentiable imputation model, SSE can estimate an appropriate sample size to ensure the user-specified imputation accuracy of the final model. Extensive experiments upon several real-life large-scale datasets demonstrate that, our proposed system can accelerate the generative adversarial model training by 7.1x. Using around 7.6% samples, SCIS yields competitive accuracy with the state-of-the-art imputation methods in a much shorter computation time.

preprint2022arXiv

Efficient Policy Space Response Oracles

Policy Space Response Oracle methods (PSRO) provide a general solution to learn Nash equilibrium in two-player zero-sum games but suffer from two drawbacks: (1) the computation inefficiency due to the need for consistent meta-game evaluation via simulations, and (2) the exploration inefficiency due to finding the best response against a fixed meta-strategy at every epoch. In this work, we propose Efficient PSRO (EPSRO) that largely improves the efficiency of the above two steps. Central to our development is the newly-introduced subroutine of no-regret optimization on the unrestricted-restricted (URR) game. By solving URR at each epoch, one can evaluate the current game and compute the best response in one forward pass without the need for meta-game simulations. Theoretically, we prove that the solution procedures of EPSRO offer a monotonic improvement on the exploitability, which none of existing PSRO methods possess. Furthermore, we prove that the no-regret optimization has a regret bound of $\mathcal{O}(\sqrt{T\log{[(k^2+k)/2]}})$, where $k$ is the size of restricted policy set. Most importantly, a desirable property of EPSRO is that it is parallelizable, this allows for highly efficient exploration in the policy space that induces behavioral diversity. We test EPSRO on three classes of games, and report a 50x speedup in wall-time and 10x data efficiency while maintaining similar exploitability as existing PSRO methods on Kuhn and Leduc Poker games.

preprint2022arXiv

Empirical or Invariant Risk Minimization? A Sample Complexity Perspective

Recently, invariant risk minimization (IRM) was proposed as a promising solution to address out-of-distribution (OOD) generalization. However, it is unclear when IRM should be preferred over the widely-employed empirical risk minimization (ERM) framework. In this work, we analyze both these frameworks from the perspective of sample complexity, thus taking a firm step towards answering this important question. We find that depending on the type of data generation mechanism, the two approaches might have very different finite sample and asymptotic behavior. For example, in the covariate shift setting we see that the two approaches not only arrive at the same asymptotic solution, but also have similar finite sample behavior with no clear winner. For other distribution shifts such as those involving confounders or anti-causal variables, however, the two approaches arrive at different asymptotic solutions where IRM is guaranteed to be close to the desired OOD solutions in the finite sample regime, while ERM is biased even asymptotically. We further investigate how different factors -- the number of environments, complexity of the model, and IRM penalty weight -- impact the sample complexity of IRM in relation to its distance from the OOD solutions

preprint2022arXiv

ESSumm: Extractive Speech Summarization from Untranscribed Meeting

In this paper, we propose a novel architecture for direct extractive speech-to-speech summarization, ESSumm, which is an unsupervised model without dependence on intermediate transcribed text. Different from previous methods with text presentation, we are aimed at generating a summary directly from speech without transcription. First, a set of smaller speech segments are extracted based on speech signal's acoustic features. For each candidate speech segment, a distance-based summarization confidence score is designed for latent speech representation measure. Specifically, we leverage the off-the-shelf self-supervised convolutional neural network to extract the deep speech features from raw audio. Our approach automatically predicts the optimal sequence of speech segments that capture the key information with a target summary length. Extensive results on two well-known meeting datasets (AMI and ICSI corpora) show the effectiveness of our direct speech-based method to improve the summarization quality with untranscribed data. We also observe that our unsupervised speech-based method even performs on par with recent transcript-based summarization approaches, where extra speech recognition is required.

preprint2022arXiv

FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis

Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hindered their applications to speech synthesis. This paper proposes FastDiff, a fast conditional diffusion model for high-quality speech synthesis. FastDiff employs a stack of time-aware location-variable convolutions of diverse receptive field patterns to efficiently model long-term time dependencies with adaptive conditions. A noise schedule predictor is also adopted to reduce the sampling steps without sacrificing the generation quality. Based on FastDiff, we design an end-to-end text-to-speech synthesizer, FastDiff-TTS, which generates high-fidelity speech waveforms without any intermediate feature (e.g., Mel-spectrogram). Our evaluation of FastDiff demonstrates the state-of-the-art results with higher-quality (MOS 4.28) speech samples. Also, FastDiff enables a sampling speed of 58x faster than real-time on a V100 GPU, making diffusion models practically applicable to speech synthesis deployment for the first time. We further show that FastDiff generalized well to the mel-spectrogram inversion of unseen speakers, and FastDiff-TTS outperformed other competing methods in end-to-end text-to-speech synthesis. Audio samples are available at \url{https://FastDiff.github.io/}.

preprint2022arXiv

Feature Fusion Vision Transformer for Fine-Grained Visual Categorization

The core for tackling the fine-grained visual categorization (FGVC) is to learn subtle yet discriminative features. Most previous works achieve this by explicitly selecting the discriminative parts or integrating the attention mechanism via CNN-based approaches.However, these methods enhance the computational complexity and make the modeldominated by the regions containing the most of the objects. Recently, vision trans-former (ViT) has achieved SOTA performance on general image recognition tasks. Theself-attention mechanism aggregates and weights the information from all patches to the classification token, making it perfectly suitable for FGVC. Nonetheless, the classifi-cation token in the deep layer pays more attention to the global information, lacking the local and low-level features that are essential for FGVC. In this work, we proposea novel pure transformer-based framework Feature Fusion Vision Transformer (FFVT)where we aggregate the important tokens from each transformer layer to compensate thelocal, low-level and middle-level information. We design a novel token selection mod-ule called mutual attention weight selection (MAWS) to guide the network effectively and efficiently towards selecting discriminative tokens without introducing extra param-eters. We verify the effectiveness of FFVT on three benchmarks where FFVT achieves the state-of-the-art performance.

preprint2022arXiv

GCS: Graph-based Coordination Strategy for Multi-Agent Reinforcement Learning

Many real-world scenarios involve a team of agents that have to coordinate their policies to achieve a shared goal. Previous studies mainly focus on decentralized control to maximize a common reward and barely consider the coordination among control policies, which is critical in dynamic and complicated environments. In this work, we propose factorizing the joint team policy into a graph generator and graph-based coordinated policy to enable coordinated behaviours among agents. The graph generator adopts an encoder-decoder framework that outputs directed acyclic graphs (DAGs) to capture the underlying dynamic decision structure. We also apply the DAGness-constrained and DAG depth-constrained optimization in the graph generator to balance efficiency and performance. The graph-based coordinated policy exploits the generated decision structure. The graph generator and coordinated policy are trained simultaneously to maximize the discounted return. Empirical evaluations on Collaborative Gaussian Squeeze, Cooperative Navigation, and Google Research Football demonstrate the superiority of the proposed method.

preprint2022arXiv

Generalizable Information Theoretic Causal Representation

It is evidence that representation learning can improve model's performance over multiple downstream tasks in many real-world scenarios, such as image classification and recommender systems. Existing learning approaches rely on establishing the correlation (or its proxy) between features and the downstream task (labels), which typically results in a representation containing cause, effect and spurious correlated variables of the label. Its generalizability may deteriorate because of the unstability of the non-causal parts. In this paper, we propose to learn causal representation from observational data by regularizing the learning procedure with mutual information measures according to our hypothetical causal graph. The optimization involves a counterfactual loss, based on which we deduce a theoretical guarantee that the causality-inspired learning is with reduced sample complexity and better generalization ability. Extensive experiments show that the models trained on causal representations learned by our approach is robust under adversarial attacks and distribution shift.

preprint2022arXiv

Geometric and Learning-based Mesh Denoising: A Comprehensive Survey

Mesh denoising is a fundamental problem in digital geometry processing. It seeks to remove surface noise, while preserving surface intrinsic signals as accurately as possible. While the traditional wisdom has been built upon specialized priors to smooth surfaces, learning-based approaches are making their debut with great success in generalization and automation. In this work, we provide a comprehensive review of the advances in mesh denoising, containing both traditional geometric approaches and recent learning-based methods. First, to familiarize readers with the denoising tasks, we summarize four common issues in mesh denoising. We then provide two categorizations of the existing denoising methods. Furthermore, three important categories, including optimization-, filter-, and data-driven-based techniques, are introduced and analyzed in detail, respectively. Both qualitative and quantitative comparisons are illustrated, to demonstrate the effectiveness of the state-of-the-art denoising methods. Finally, potential directions of future work are pointed out to solve the common problems of these approaches. A mesh denoising benchmark is also built in this work, and future researchers will easily and conveniently evaluate their methods with the state-of-the-art approaches.

preprint2022arXiv

HEBO Pushing The Limits of Sample-Efficient Hyperparameter Optimisation

In this work we rigorously analyse assumptions inherent to black-box optimisation hyper-parameter tuning tasks. Our results on the Bayesmark benchmark indicate that heteroscedasticity and non-stationarity pose significant challenges for black-box optimisers. Based on these findings, we propose a Heteroscedastic and Evolutionary Bayesian Optimisation solver (HEBO). HEBO performs non-linear input and output warping, admits exact marginal log-likelihood optimisation and is robust to the values of learned parameters. We demonstrate HEBO's empirical efficacy on the NeurIPS 2020 Black-Box Optimisation challenge, where HEBO placed first. Upon further analysis, we observe that HEBO significantly outperforms existing black-box optimisers on 108 machine learning hyperparameter tuning tasks comprising the Bayesmark benchmark. Our findings indicate that the majority of hyper-parameter tuning tasks exhibit heteroscedasticity and non-stationarity, multi-objective acquisition ensembles with Pareto front solutions improve queried configurations, and robust acquisition maximisers afford empirical advantages relative to their non-robust counterparts. We hope these findings may serve as guiding principles for practitioners of Bayesian optimisation. All code is made available at https://github.com/huawei-noah/HEBO.

preprint2022arXiv

Heterogeneous-Agent Mirror Learning: A Continuum of Solutions to Cooperative MARL

The necessity for cooperation among intelligent machines has popularised cooperative multi-agent reinforcement learning (MARL) in the artificial intelligence (AI) research community. However, many research endeavors have been focused on developing practical MARL algorithms whose effectiveness has been studied only empirically, thereby lacking theoretical guarantees. As recent studies have revealed, MARL methods often achieve performance that is unstable in terms of reward monotonicity or suboptimal at convergence. To resolve these issues, in this paper, we introduce a novel framework named Heterogeneous-Agent Mirror Learning (HAML) that provides a general template for MARL algorithmic designs. We prove that algorithms derived from the HAML template satisfy the desired properties of the monotonic improvement of the joint reward and the convergence to Nash equilibrium. We verify the practicality of HAML by proving that the current state-of-the-art cooperative MARL algorithms, HATRPO and HAPPO, are in fact HAML instances. Next, as a natural outcome of our theory, we propose HAML extensions of two well-known RL algorithms, HAA2C (for A2C) and HADDPG (for DDPG), and demonstrate their effectiveness against strong baselines on StarCraftII and Multi-Agent MuJoCo tasks.

preprint2022arXiv

HRBF-Fusion: Accurate 3D reconstruction from RGB-D data using on-the-fly implicits

Reconstruction of high-fidelity 3D objects or scenes is a fundamental research problem. Recent advances in RGB-D fusion have demonstrated the potential of producing 3D models from consumer-level RGB-D cameras. However, due to the discrete nature and limited resolution of their surface representations (e.g., point- or voxel-based), existing approaches suffer from the accumulation of errors in camera tracking and distortion in the reconstruction, which leads to an unsatisfactory 3D reconstruction. In this paper, we present a method using on-the-fly implicits of Hermite Radial Basis Functions (HRBFs) as a continuous surface representation for camera tracking in an existing RGB-D fusion framework. Furthermore, curvature estimation and confidence evaluation are coherently derived from the inherent surface properties of the on-the-fly HRBF implicits, which devote to a data fusion with better quality. We argue that our continuous but on-the-fly surface representation can effectively mitigate the impact of noise with its robustness and constrain the reconstruction with inherent surface smoothness when being compared with discrete representations. Experimental results on various real-world and synthetic datasets demonstrate that our HRBF-fusion outperforms the state-of-the-art approaches in terms of tracking robustness and reconstruction accuracy.

preprint2022arXiv

IH-GAN: A Conditional Generative Model for Implicit Surface-Based Inverse Design of Cellular Structures

Variable-density cellular structures can overcome connectivity and manufacturability issues of topologically optimized structures, particularly those represented as discrete density maps. However, the optimization of such cellular structures is challenging due to the multiscale design problem. Past work addressing this problem generally either only optimizes the volume fraction of single-type unit cells but ignores the effects of unit cell geometry on properties, or considers the geometry-property relation but builds this relation via heuristics. In contrast, we propose a simple yet more principled way to accurately model the property to geometry mapping using a conditional deep generative model, named Inverse Homogenization Generative Adversarial Network (IH-GAN). It learns the conditional distribution of unit cell geometries given properties and can realize the one-to-many mapping from properties to geometries. We further reduce the complexity of IH-GAN by using the implicit function parameterization to represent unit cell geometries. Results show that our method can 1) generate various unit cells that satisfy given material properties with high accuracy ($R^2$-scores between target properties and properties of generated unit cells $>98\%$) and 2) improve the optimized structural performance over the conventional variable-density single-type structure. In the minimum compliance example, our IH-GAN generated structure achieves a $79.7\%$ reduction in concentrated stress and an extra $3.03\%$ reduction in displacement. In the target deformation examples, our IH-GAN generated structure reduces the target matching error by $86.4\%$ and $79.6\%$ for two test cases, respectively. We also demonstrated that the connectivity issue for multi-type unit cells can be solved by transition layer blending.

preprint2022arXiv

Image-Goal Navigation in Complex Environments via Modular Learning

We present a novel approach for image-goal navigation, where an agent navigates with a goal image rather than accurate target information, which is more challenging. Our goal is to decouple the learning of navigation goal planning, collision avoidance, and navigation ending prediction, which enables more concentrated learning of each part. This is realized by four different modules. The first module maintains an obstacle map during robot navigation. The second predicts a long-term goal on the real-time map periodically, which can thus convert an image-goal navigation task to several point-goal navigation tasks. To achieve these point-goal navigation tasks, the third module plans collision-free command sets for navigating to these long-term goals. The final module stops the robot properly near the goal image. The four modules are designed or maintained separately, which helps cut down the search time during navigation and improves the generalization to previously unseen real scenes. We evaluate the method in both a simulator and in the real world with a mobile robot. The results in real complex environments show that our method attains at least a $17\%$ increase in navigation success rate and a $23\%$ decrease in navigation collision rate over some state-of-the-art models.

preprint2022arXiv

ImLoveNet: Misaligned Image-supported Registration Network for Low-overlap Point Cloud Pairs

Low-overlap regions between paired point clouds make the captured features very low-confidence, leading cutting edge models to point cloud registration with poor quality. Beyond the traditional wisdom, we raise an intriguing question: Is it possible to exploit an intermediate yet misaligned image between two low-overlap point clouds to enhance the performance of cutting-edge registration models? To answer it, we propose a misaligned image supported registration network for low-overlap point cloud pairs, dubbed ImLoveNet. ImLoveNet first learns triple deep features across different modalities and then exports these features to a two-stage classifier, for progressively obtaining the high-confidence overlap region between the two point clouds. Therefore, soft correspondences are well established on the predicted overlap region, resulting in accurate rigid transformations for registration. ImLoveNet is simple to implement yet effective, since 1) the misaligned image provides clearer overlap information for the two low-overlap point clouds to better locate overlap parts; 2) it contains certain geometry knowledge to extract better deep features; and 3) it does not require the extrinsic parameters of the imaging device with respect to the reference frame of the 3D point cloud. Extensive qualitative and quantitative evaluations on different kinds of benchmarks demonstrate the effectiveness and superiority of our ImLoveNet over state-of-the-art approaches.

preprint2022arXiv

Joint Caching and Transmission in the Mobile Edge Network: A Multi-Agent Learning Approach

Joint caching and transmission optimization problem is challenging due to the deep coupling between decisions. This paper proposes an iterative distributed multi-agent learning approach to jointly optimize caching and transmission. The goal of this approach is to minimize the total transmission delay of all users. In this iterative approach, each iteration includes caching optimization and transmission optimization. A multi-agent reinforcement learning (MARL)-based caching network is developed to cache popular tasks, such as answering which files to evict from the cache and which files to storage. Based on the cached files of the caching network, the transmission network transmits cached files for users by single transmission (ST) or joint transmission (JT) with multi-agent Bayesian learning automaton (MABLA) method. And then users access the edge servers with the minimum transmission delay. The experimental results demonstrate the performance of the proposed multi-agent learning approach.

preprint2022arXiv

Joint Optimization of Resource Allocation, Phase Shift and UAV Trajectory for Energy-Efficient RIS-Assisted UAV-Enabled MEC Systems

The unmanned aerial vehicle (UAV) enabled mobile edge computing (MEC) has been deemed a promising paradigm to provide ubiquitous communication and computing services for the Internet of Things (IoT). Besides, by intelligently reflecting the received signals, the reconfigurable intelligent surface (RIS) can significantly improve the propagation environment and further enhance the service quality of the UAV-enabled MEC. Motivated by this vision, in this paper, we consider both the amount of completed task bits and the energy consumption to maximize the energy efficiency of the RIS-assisted UAV-enabled MEC systems, where the bit allocation, transmit power, phase shift, and UAV trajectory are jointly optimized by an iterative algorithm with a double-loop structure based on the Dinkelbach's method and block coordinate decent (BCD) technique. Simulation results demonstrate that: 1) with the deployment of RIS, our proposed algorithm can achieve higher energy efficiency than baseline schemes while satisfying the task tolerance latency; 2) the energy efficiency first increases and then decreases with the increase of the mission period and the total amount of task-input bits of IoT devices; 3) when the CPU cycles required for computing 1-bit of task-input data becomes larger, more task bits will be offloaded to the UAV while the energy efficiency will be decreased.

preprint2022arXiv

Joint Resource Allocation and Configuration Design for STAR-RIS-Enhanced Wireless-Powered MEC

In this paper, a novel concept called simultaneously transmitting and reflecting RIS (STAR-RIS) is introduced into the wireless-powered mobile edge computing (MEC) systems to improve the efficiency of energy transfer and task offloading. Compared with traditional reflecting-only RIS, STAR-RIS extends the half-space coverage to full-space coverage by simultaneously transmitting and reflecting incident signals, and also provides new degrees-of-freedom (DoFs) for manipulating signal propagation. We aim to maximize the total computation rate of all users, where the energy transfer time, transmit power and CPU frequencies of users, and the configuration design of STAR-RIS are jointly optimized. Considering the characteristics of STAR-RIS, three operating protocols, namely energy splitting (ES), mode switching (MS), and time splitting (TS) are studied, respectively. For the ES protocol, based on the penalty method, successive convex approximation (SCA), and the linear search method, an iterative algorithm is proposed to solve the formulated non-convex problem. Then, the proposed algorithm for ES protocol is extended to solve the MS and TS problems. Simulation results illustrate that the STAR-RIS outperforms traditional reflecting/transmitting-only RIS. More importantly, the TS protocol can achieve the largest computation rate among the three operating protocols of STAR-RIS.

preprint2022arXiv

Knowledge Graph Based Waveform Recommendation: A New Communication Waveform Design Paradigm

Traditionally, a communication waveform is designed by experts based on communication theory and their experiences on a case-by-case basis, which is usually laborious and time-consuming. In this paper, we investigate the waveform design from a novel perspective and propose a new waveform design paradigm with the knowledge graph (KG)-based intelligent recommendation system. The proposed paradigm aims to improve the design efficiency by structural characterization and representations of existing waveforms and intelligently utilizing the knowledge learned from them. To achieve this goal, we first build a communication waveform knowledge graph (CWKG) with a first-order neighbor node, for which both structured semantic knowledge and numerical parameters of a waveform are integrated by representation learning. Based on the developed CWKG, we further propose an intelligent communication waveform recommendation system (CWRS) to generate waveform candidates. In the CWRS, an improved involution1D operator, which is channel-agnostic and space-specific, is introduced according to the characteristics of KG-based waveform representation for feature extraction, and the multi-head self-attention is adopted to weigh the influence of various components for feature fusion. Meanwhile, multilayer perceptron-based collaborative filtering is used to evaluate the matching degree between the requirement and the waveform candidate. Simulation results show that the proposed CWKG-based CWRS can automatically recommend waveform candidates with high reliability.

preprint2022arXiv

Learning to Identify Top Elo Ratings: A Dueling Bandits Approach

The Elo rating system is widely adopted to evaluate the skills of (chess) game and sports players. Recently it has been also integrated into machine learning algorithms in evaluating the performance of computerised AI agents. However, an accurate estimation of the Elo rating (for the top players) often requires many rounds of competitions, which can be expensive to carry out. In this paper, to improve the sample efficiency of the Elo evaluation (for top players), we propose an efficient online match scheduling algorithm. Specifically, we identify and match the top players through a dueling bandits framework and tailor the bandit algorithm to the gradient-based update of Elo. We show that it reduces the per-step memory and time complexity to constant, compared to the traditional likelihood maximization approaches requiring $O(t)$ time. Our algorithm has a regret guarantee of $\tilde{O}(\sqrt{T})$, sublinear in the number of competition rounds and has been extended to the multidimensional Elo ratings for handling intransitive games. We empirically demonstrate that our method achieves superior convergence speed and time efficiency on a variety of gaming tasks.

preprint2022arXiv

Level compatibility in Sharifi's conjecture

Sharifi has constructed a map from the first homology of the modular curve $X_1(M)$ to the $K$-group $K_2(\mathbf{Z}[ζ_M, \frac{1}{M}])$, where $ζ_M$ is a primitive $M$th root of unity. We study how these maps relate when $M$ varies. Our method relies on the techniques developed by Sharifi and Venkatesh.

preprint2022arXiv

LIGS: Learnable Intrinsic-Reward Generation Selection for Multi-Agent Learning

Efficient exploration is important for reinforcement learners to achieve high rewards. In multi-agent systems, coordinated exploration and behaviour is critical for agents to jointly achieve optimal outcomes. In this paper, we introduce a new general framework for improving coordination and performance of multi-agent reinforcement learners (MARL). Our framework, named Learnable Intrinsic-Reward Generation Selection algorithm (LIGS) introduces an adaptive learner, Generator that observes the agents and learns to construct intrinsic rewards online that coordinate the agents' joint exploration and joint behaviour. Using a novel combination of MARL and switching controls, LIGS determines the best states to learn to add intrinsic rewards which leads to a highly efficient learning process. LIGS can subdivide complex tasks making them easier to solve and enables systems of MARL agents to quickly solve environments with sparse rewards. LIGS can seamlessly adopt existing MARL algorithms and, our theory shows that it ensures convergence to policies that deliver higher system performance. We demonstrate its superior performance in challenging tasks in Foraging and StarCraft II.

preprint2022arXiv

LPCSE: Neural Speech Enhancement through Linear Predictive Coding

The increasingly stringent requirement on quality-of-experience in 5G/B5G communication systems has led to the emerging neural speech enhancement techniques, which however have been developed in isolation from the existing expert-rule based models of speech pronunciation and distortion, such as the classic Linear Predictive Coding (LPC) speech model because it is difficult to integrate the models with auto-differentiable machine learning frameworks. In this paper, to improve the efficiency of neural speech enhancement, we introduce an LPC-based speech enhancement (LPCSE) architecture, which leverages the strong inductive biases in the LPC speech model in conjunction with the expressive power of neural networks. Differentiable end-to-end learning is achieved in LPCSE via two novel blocks: a block that utilizes the expert rules to reduce the computational overhead when integrating the LPC speech model into neural networks, and a block that ensures the stability of the model and avoids exploding gradients in end-to-end training by mapping the Linear prediction coefficients to the filter poles. The experimental results show that LPCSE successfully restores the formants of the speeches distorted by transmission loss, and outperforms two existing neural speech enhancement methods of comparable neural network sizes in terms of the Perceptual evaluation of speech quality (PESQ) and Short-Time Objective Intelligibility (STOI) on the LJ Speech corpus.

preprint2022arXiv

M2N: Mesh Movement Networks for PDE Solvers

Mainstream numerical Partial Differential Equation (PDE) solvers require discretizing the physical domain using a mesh. Mesh movement methods aim to improve the accuracy of the numerical solution by increasing mesh resolution where the solution is not well-resolved, whilst reducing unnecessary resolution elsewhere. However, mesh movement methods, such as the Monge-Ampere method, require the solution of auxiliary equations, which can be extremely expensive especially when the mesh is adapted frequently. In this paper, we propose to our best knowledge the first learning-based end-to-end mesh movement framework for PDE solvers. Key requirements of learning-based mesh movement methods are alleviating mesh tangling, boundary consistency, and generalization to mesh with different resolutions. To achieve these goals, we introduce the neural spline model and the graph attention network (GAT) into our models respectively. While the Neural-Spline based model provides more flexibility for large deformation, the GAT based model can handle domains with more complicated shapes and is better at performing delicate local deformation. We validate our methods on stationary and time-dependent, linear and non-linear equations, as well as regularly and irregularly shaped domains. Compared to the traditional Monge-Ampere method, our approach can greatly accelerate the mesh adaptation process, whilst achieving comparable numerical error reduction.

preprint2022arXiv

Masked Gradient-Based Causal Structure Learning

This paper studies the problem of learning causal structures from observational data. We reformulate the Structural Equation Model (SEM) with additive noises in a form parameterized by binary graph adjacency matrix and show that, if the original SEM is identifiable, then the binary adjacency matrix can be identified up to super-graphs of the true causal graph under mild conditions. We then utilize the reformulated SEM to develop a causal structure learning method that can be efficiently trained using gradient-based optimization, by leveraging a smooth characterization on acyclicity and the Gumbel-Softmax approach to approximate the binary adjacency matrix. It is found that the obtained entries are typically near zero or one and can be easily thresholded to identify the edges. We conduct experiments on synthetic and real datasets to validate the effectiveness of the proposed method, and show that it readily includes different smooth model functions and achieves a much improved performance on most datasets considered.

preprint2022arXiv

Mass Testing and Characterization of 20-inch PMTs for JUNO

Main goal of the JUNO experiment is to determine the neutrino mass ordering using a 20kt liquid-scintillator detector. Its key feature is an excellent energy resolution of at least 3 % at 1 MeV, for which its instruments need to meet a certain quality and thus have to be fully characterized. More than 20,000 20-inch PMTs have been received and assessed by JUNO after a detailed testing program which began in 2017 and elapsed for about four years. Based on this mass characterization and a set of specific requirements, a good quality of all accepted PMTs could be ascertained. This paper presents the performed testing procedure with the designed testing systems as well as the statistical characteristics of all 20-inch PMTs intended to be used in the JUNO experiment, covering more than fifteen performance parameters including the photocathode uniformity. This constitutes the largest sample of 20-inch PMTs ever produced and studied in detail to date, i.e. 15,000 of the newly developed 20-inch MCP-PMTs from Northern Night Vision Technology Co. (NNVT) and 5,000 of dynode PMTs from Hamamatsu Photonics K. K.(HPK).

preprint2022arXiv

Modeling Temporal-Modal Entity Graph for Procedural Multimodal Machine Comprehension

Procedural Multimodal Documents (PMDs) organize textual instructions and corresponding images step by step. Comprehending PMDs and inducing their representations for the downstream reasoning tasks is designated as Procedural MultiModal Machine Comprehension (M3C). In this study, we approach Procedural M3C at a fine-grained level (compared with existing explorations at a document or sentence level), that is, entity. With delicate consideration, we model entity both in its temporal and cross-modal relation and propose a novel Temporal-Modal Entity Graph (TMEG). Specifically, graph structure is formulated to capture textual and visual entities and trace their temporal-modal evolution. In addition, a graph aggregation module is introduced to conduct graph encoding and reasoning. Comprehensive experiments across three Procedural M3C tasks are conducted on a traditional dataset RecipeQA and our new dataset CraftQA, which can better evaluate the generalization of TMEG.

preprint2022arXiv

Multi-Agent Constrained Policy Optimisation

Developing reinforcement learning algorithms that satisfy safety constraints is becoming increasingly important in real-world applications. In multi-agent reinforcement learning (MARL) settings, policy optimisation with safety awareness is particularly challenging because each individual agent has to not only meet its own safety constraints, but also consider those of others so that their joint behaviour can be guaranteed safe. Despite its importance, the problem of safe multi-agent learning has not been rigorously studied; very few solutions have been proposed, nor a sharable testing environment or benchmarks. To fill these gaps, in this work, we formulate the safe MARL problem as a constrained Markov game and solve it with policy optimisation methods. Our solutions -- Multi-Agent Constrained Policy Optimisation (MACPO) and MAPPO-Lagrangian -- leverage the theories from both constrained policy optimisation and multi-agent trust region learning. Crucially, our methods enjoy theoretical guarantees of both monotonic improvement in reward and satisfaction of safety constraints at every iteration. To examine the effectiveness of our methods, we develop the benchmark suite of Safe Multi-Agent MuJoCo that involves a variety of MARL baselines. Experimental results justify that MACPO/MAPPO-Lagrangian can consistently satisfy safety constraints, meanwhile achieving comparable performance to strong baselines.

preprint2022arXiv

Multi-Agent Feedback Enabled Neural Networks for Intelligent Communications

In the intelligent communication field, deep learning (DL) has attracted much attention due to its strong fitting ability and data-driven learning capability. Compared with the typical DL feedforward network structures, an enhancement structure with direct data feedback have been studied and proved to have better performance than the feedfoward networks. However, due to the above simple feedback methods lack sufficient analysis and learning ability on the feedback data, it is inadequate to deal with more complicated nonlinear systems and therefore the performance is limited for further improvement. In this paper, a novel multi-agent feedback enabled neural network (MAFENN) framework is proposed, which make the framework have stronger feedback learning capabilities and more intelligence on feature abstraction, denoising or generation, etc. Furthermore, the MAFENN framework is theoretically formulated into a three-player Feedback Stackelberg game, and the game is proved to converge to the Feedback Stackelberg equilibrium. The design of MAFENN framework and algorithm are dedicated to enhance the learning capability of the feedfoward DL networks or their variations with the simple data feedback. To verify the MAFENN framework's feasibility in wireless communications, a multi-agent MAFENN based equalizer (MAFENN-E) is developed for wireless fading channels with inter-symbol interference (ISI). Experimental results show that when the quadrature phase-shift keying (QPSK) modulation scheme is adopted, the SER performance of our proposed method outperforms that of the traditional equalizers by about 2 dB in linear channels. When in nonlinear channels, the SER performance of our proposed method outperforms that of either traditional or DL based equalizers more significantly, which shows the effectiveness and robustness of our proposal in the complex channel environment.

preprint2022arXiv

Multi-View Pre-Trained Model for Code Vulnerability Identification

Vulnerability identification is crucial for cyber security in the software-related industry. Early identification methods require significant manual efforts in crafting features or annotating vulnerable code. Although the recent pre-trained models alleviate this issue, they overlook the multiple rich structural information contained in the code itself. In this paper, we propose a novel Multi-View Pre-Trained Model (MV-PTM) that encodes both sequential and multi-type structural information of the source code and uses contrastive learning to enhance code representations. The experiments conducted on two public datasets demonstrate the superiority of MV-PTM. In particular, MV-PTM improves GraphCodeBERT by 3.36\% on average in terms of F1 score.

preprint2022arXiv

NeoNav: Improving the Generalization of Visual Navigation via Generating Next Expected Observations

We propose improving the cross-target and cross-scene generalization of visual navigation through learning an agent that is guided by conceiving the next observations it expects to see. This is achieved by learning a variational Bayesian model, called NeoNav, which generates the next expected observations (NEO) conditioned on the current observations of the agent and the target view. Our generative model is learned through optimizing a variational objective encompassing two key designs. First, the latent distribution is conditioned on current observations and the target view, leading to a model-based, target-driven navigation. Second, the latent space is modeled with a Mixture of Gaussians conditioned on the current observation and the next best action. Our use of mixture-of-posteriors prior effectively alleviates the issue of over-regularized latent space, thus significantly boosting the model generalization for new targets and in novel scenes. Moreover, the NEO generation models the forward dynamics of agent-environment interaction, which improves the quality of approximate inference and hence benefits data efficiency. We have conducted extensive evaluations on both real-world and synthetic benchmarks, and show that our model consistently outperforms the state-of-the-art models in terms of success rate, data efficiency, and generalization.

preprint2022arXiv

Noise-like Pulses from an All-Normal-Dispersion Fiber Laser with Weakened Spectrum Filtering

Noise-like pulses (NLP) are extremely sought after in many fields. Here, we experimentally and numerically investigated the generation of noise-like pulses in an all-normal-dispersion fiber laser with weak spectrum filtering. With the insertion of the grating as a tunable spectrum filter, the laser operates at a stable dissipative soliton state with a 3.84 ps duration. Replacing the grating with a mirror, NLPs with double-scale intensity autocorrelation trace is ultimately attained. Numerical simulations are performed in detail and demonstrated that with the absence of a spectrum filter, the stable state cannot be established but form the random pulse cluster. The random pulse cluster achieves dynamic stability with suitable feedback, and the NLP is ultimately generated. The NLP here is directly evolved by the initial noise, and no other states occur during its evolution. These explorations could deepen the understanding of NLP and enrich the complex dynamics of the ANDi ultrafast fiber laser.

preprint2022arXiv

Offline Pre-trained Multi-Agent Decision Transformer: One Big Sequence Model Tackles All SMAC Tasks

Offline reinforcement learning leverages previously-collected offline datasets to learn optimal policies with no necessity to access the real environment. Such a paradigm is also desirable for multi-agent reinforcement learning (MARL) tasks, given the increased interactions among agents and with the enviroment. Yet, in MARL, the paradigm of offline pre-training with online fine-tuning has not been studied, nor datasets or benchmarks for offline MARL research are available. In this paper, we facilitate the research by providing large-scale datasets, and use them to examine the usage of the Decision Transformer in the context of MARL. We investigate the generalisation of MARL offline pre-training in the following three aspects: 1) between single agents and multiple agents, 2) from offline pretraining to the online fine-tuning, and 3) to that of multiple downstream tasks with few-shot and zero-shot capabilities. We start by introducing the first offline MARL dataset with diverse quality levels based on the StarCraftII environment, and then propose the novel architecture of multi-agent decision transformer (MADT) for effective offline learning. MADT leverages transformer's modelling ability of sequence modelling and integrates it seamlessly with both offline and online MARL tasks. A crucial benefit of MADT is that it learns generalisable policies that can transfer between different types of agents under different task scenarios. On StarCraft II offline dataset, MADT outperforms the state-of-the-art offline RL baselines. When applied to online tasks, the pre-trained MADT significantly improves sample efficiency, and enjoys strong performance both few-short and zero-shot cases. To our best knowledge, this is the first work that studies and demonstrates the effectiveness of offline pre-trained models in terms of sample efficiency and generalisability enhancements in MARL.

preprint2022arXiv

On Iwasawa invariants of modular forms with reducible and non-$p$-distinguished residual Galois representations

In the present paper, we study the $p$-adic $L$-functions and the (strict) Selmer groups over $\mathbb{Q}_{\infty}$, the cyclotomic $\mathbb{Z}_p$-extension of $\mathbb{Q}$, of the $p$-adic weight one cusp forms $f$, obtained via the $p$-stabilization of weight one Eisenstein series, under the assumption that a certain Eisenstein component of the $p$-ordinary universal cuspidal Hecke algebra is Gorenstein. As an application, we compute the Iwasawa invariants of ordinary modular forms of weight $k\geq 2$ with the same residual Galois representations as the one of $f$, which in our setting, is reducible and non-$p$-distinguished. Combining this with a result of Kato \cite[Theorem~17.4.2]{kato04}, we prove the Iwasawa main conjecture for these forms. Also, we give numerical examples that satisfy the Gorenstein hypothesis. The crucial point on the analytic counter part is that under the Gorenstein hypothesis, we are able to define, following Greenberg--Vatsal, the $p$-adic $L$-functions of $p$-adic weight one forms $f$ as an element in the one-dimensional Iwasawa algebra by using Mazur--Kitagawa two-variable $p$-adic $L$-function and then, to compute them explicitly via local explicit reciprocity law. On the algebraic counter part, we compute the (strict) Selmer groups of $f$ over $\mathbb{Q}_{\infty}$ via the knowledge of the Galois representations of $f$ studied in \cite{BDP}.

preprint2022arXiv

On the Convergence of Fictitious Play: A Decomposition Approach

Fictitious play (FP) is one of the most fundamental game-theoretical learning frameworks for computing Nash equilibrium in $n$-player games, which builds the foundation for modern multi-agent learning algorithms. Although FP has provable convergence guarantees on zero-sum games and potential games, many real-world problems are often a mixture of both and the convergence property of FP has not been fully studied yet. In this paper, we extend the convergence results of FP to the combinations of such games and beyond. Specifically, we derive new conditions for FP to converge by leveraging game decomposition techniques. We further develop a linear relationship unifying cooperation and competition in the sense that these two classes of games are mutually transferable. Finally, we analyze a non-convergent example of FP, the Shapley game, and develop sufficient conditions for FP to converge.

preprint2022arXiv

Perceptual Learned Source-Channel Coding for High-Fidelity Image Semantic Transmission

As one novel approach to realize end-to-end wireless image semantic transmission, deep learning-based joint source-channel coding (deep JSCC) method is emerging in both deep learning and communication communities. However, current deep JSCC image transmission systems are typically optimized for traditional distortion metrics such as peak signal-to-noise ratio (PSNR) or multi-scale structural similarity (MS-SSIM). But for low transmission rates, due to the imperfect wireless channel, these distortion metrics lose significance as they favor pixel-wise preservation. To account for human visual perception in semantic communications, it is of great importance to develop new deep JSCC systems optimized beyond traditional PSNR and MS-SSIM metrics. In this paper, we introduce adversarial losses to optimize deep JSCC, which tends to preserve global semantic information and local texture. Our new deep JSCC architecture combines encoder, wireless channel, decoder/generator, and discriminator, which are jointly learned under both perceptual and adversarial losses. Our method yields human visually much more pleasing results than state-of-the-art engineered image coded transmission systems and traditional deep JSCC systems. A user study confirms that achieving the perceptually similar end-to-end image transmission quality, the proposed method can save about 50\% wireless channel bandwidth cost.

preprint2022arXiv

PGTRNet: Two-phase Weakly Supervised Object Detection with Pseudo Ground Truth Refinement

Current state-of-the-art weakly supervised object detection (WSOD) studies mainly follow a two-stage training strategy which integrates a fully supervised detector (FSD) with a pure WSOD model. There are two main problems hindering the performance of the two-phase WSOD approaches, i.e., insufficient learning problem and strict reliance between the FSD and the pseudo ground truth (PGT) generated by the WSOD model. This paper proposes pseudo ground truth refinement network (PGTRNet), a simple yet effective method without introducing any extra learnable parameters, to cope with these problems. PGTRNet utilizes multiple bounding boxes to establish the PGT, mitigating the insufficient learning problem. Besides, we propose a novel online PGT refinement approach to steadily improve the quality of PGT by fully taking advantage of the power of FSD during the second-phase training, decoupling the first and second-phase models. Elaborate experiments are conducted on the PASCAL VOC 2007 benchmark to verify the effectiveness of our methods. Experimental results demonstrate that PGTRNet boosts the backbone model by 2.1% mAP and achieves the state-of-the-art performance.

preprint2022arXiv

PointAttN: You Only Need Attention for Point Cloud Completion

Point cloud completion referring to completing 3D shapes from partial 3D point clouds is a fundamental problem for 3D point cloud analysis tasks. Benefiting from the development of deep neural networks, researches on point cloud completion have made great progress in recent years. However, the explicit local region partition like kNNs involved in existing methods makes them sensitive to the density distribution of point clouds. Moreover, it serves limited receptive fields that prevent capturing features from long-range context information. To solve the problems, we leverage the cross-attention and self-attention mechanisms to design novel neural network for processing point cloud in a per-point manner to eliminate kNNs. Two essential blocks Geometric Details Perception (GDP) and Self-Feature Augment (SFA) are proposed to establish the short-range and long-range structural relationships directly among points in a simple yet effective way via attention mechanism. Then based on GDP and SFA, we construct a new framework with popular encoder-decoder architecture for point cloud completion. The proposed framework, namely PointAttN, is simple, neat and effective, which can precisely capture the structural information of 3D shapes and predict complete point clouds with highly detailed geometries. Experimental results demonstrate that our PointAttN outperforms state-of-the-art methods by a large margin on popular benchmarks like Completion3D and PCN. Code is available at: https://github.com/ohhhyeahhh/PointAttN

preprint2022arXiv

Real-time automatic polyp detection in colonoscopy using feature enhancement module and spatiotemporal similarity correlation unit

Automatic detection of polyps is challenging because different polyps vary greatly, while the changes between polyps and their analogues are small. The state-of-the-art methods are based on convolutional neural networks (CNNs). However, they may fail due to lack of training data, resulting in high rates of missed detection and false positives (FPs). In order to solve these problems, our method combines the two-dimensional (2-D) CNN-based real-time object detector network with spatiotemporal information. Firstly, we use a 2-D detector network to detect static images and frames, and based on the detector network, we propose two feature enhancement modules-the FP Relearning Module (FPRM) to make the detector network learning more about the features of FPs for higher precision, and the Image Style Transfer Module (ISTM) to enhance the features of polyps for sensitivity improvement. In video detection, we integrate spatiotemporal information, which uses Structural Similarity (SSIM) to measure the similarity between video frames. Finally, we propose the Inter-frame Similarity Correlation Unit (ISCU) to combine the results obtained by the detector network and frame similarity to make the final decision. We verify our method on both private databases and publicly available databases. Experimental results show that these modules and units provide a performance improvement compared with the baseline method. Comparison with the state-of-the-art methods shows that the proposed method outperforms the existing ones which can meet real-time constraints. It's demonstrated that our method provides a performance improvement in sensitivity, precision and specificity, and has great potential to be applied in clinical colonoscopy.

preprint2022arXiv

Refine-Net: Normal Refinement Neural Network for Noisy Point Clouds

Point normal, as an intrinsic geometric property of 3D objects, not only serves conventional geometric tasks such as surface consolidation and reconstruction, but also facilitates cutting-edge learning-based techniques for shape analysis and generation. In this paper, we propose a normal refinement network, called Refine-Net, to predict accurate normals for noisy point clouds. Traditional normal estimation wisdom heavily depends on priors such as surface shapes or noise distributions, while learning-based solutions settle for single types of hand-crafted features. Differently, our network is designed to refine the initial normal of each point by extracting additional information from multiple feature representations. To this end, several feature modules are developed and incorporated into Refine-Net by a novel connection module. Besides the overall network architecture of Refine-Net, we propose a new multi-scale fitting patch selection scheme for the initial normal estimation, by absorbing geometry domain knowledge. Also, Refine-Net is a generic normal estimation framework: 1) point normals obtained from other methods can be further refined, and 2) any feature module related to the surface geometric structures can be potentially integrated into the framework. Qualitative and quantitative evaluations demonstrate the clear superiority of Refine-Net over the state-of-the-arts on both synthetic and real-scanned datasets. Our code is available at https://github.com/hrzhou2/refinenet.

preprint2022arXiv

Reinforcement Learning in Presence of Discrete Markovian Context Evolution

We consider a context-dependent Reinforcement Learning (RL) setting, which is characterized by: a) an unknown finite number of not directly observable contexts; b) abrupt (discontinuous) context changes occurring during an episode; and c) Markovian context evolution. We argue that this challenging case is often met in applications and we tackle it using a Bayesian approach and variational inference. We adapt a sticky Hierarchical Dirichlet Process (HDP) prior for model learning, which is arguably best-suited for Markov process modeling. We then derive a context distillation procedure, which identifies and removes spurious contexts in an unsupervised fashion. We argue that the combination of these two components allows to infer the number of contexts from data thus dealing with the context cardinality assumption. We then find the representation of the optimal policy enabling efficient policy learning using off-the-shelf RL algorithms. Finally, we demonstrate empirically (using gym environments cart-pole swing-up, drone, intersection) that our approach succeeds where state-of-the-art methods of other frameworks fail and elaborate on the reasons for such failures.

preprint2022arXiv

Reinforcement Learning-based Visual Navigation with Information-Theoretic Regularization

To enhance the cross-target and cross-scene generalization of target-driven visual navigation based on deep reinforcement learning (RL), we introduce an information-theoretic regularization term into the RL objective. The regularization maximizes the mutual information between navigation actions and visual observation transforms of an agent, thus promoting more informed navigation decisions. This way, the agent models the action-observation dynamics by learning a variational generative model. Based on the model, the agent generates (imagines) the next observation from its current observation and navigation target. This way, the agent learns to understand the causality between navigation actions and the changes in its observations, which allows the agent to predict the next action for navigation by comparing the current and the imagined next observations. Cross-target and cross-scene evaluations on the AI2-THOR framework show that our method attains at least a $10\%$ improvement of average success rate over some state-of-the-art models. We further evaluate our model in two real-world settings: navigation in unseen indoor scenes from a discrete Active Vision Dataset (AVD) and continuous real-world environments with a TurtleBot.We demonstrate that our navigation model is able to successfully achieve navigation tasks in these scenarios. Videos and models can be found in the supplementary material.

preprint2022arXiv

Sample-Efficient Optimisation with Probabilistic Transformer Surrogates

Faced with problems of increasing complexity, recent research in Bayesian Optimisation (BO) has focused on adapting deep probabilistic models as flexible alternatives to Gaussian Processes (GPs). In a similar vein, this paper investigates the feasibility of employing state-of-the-art probabilistic transformers in BO. Upon further investigation, we observe two drawbacks stemming from their training procedure and loss definition, hindering their direct deployment as proxies in black-box optimisation. First, we notice that these models are trained on uniformly distributed inputs, which impairs predictive accuracy on non-uniform data - a setting arising from any typical BO loop due to exploration-exploitation trade-offs. Second, we realise that training losses (e.g., cross-entropy) only asymptotically guarantee accurate posterior approximations, i.e., after arriving at the global optimum, which generally cannot be ensured. At the stationary points of the loss function, however, we observe a degradation in predictive performance especially in exploratory regions of the input space. To tackle these shortcomings we introduce two components: 1) a BO-tailored training prior supporting non-uniformly distributed points, and 2) a novel approximate posterior regulariser trading-off accuracy and input sensitivity to filter favourable stationary points for improved predictive performance. In a large panel of experiments, we demonstrate, for the first time, that one transformer pre-trained on data sampled from random GP priors produces competitive results on 16 benchmark black-boxes compared to GP-based BO. Since our model is only pre-trained once and used in all tasks without any retraining and/or fine-tuning, we report an order of magnitude time-reduction, while matching and sometimes outperforming GPs.

preprint2022arXiv

Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation

Satisfying safety constraints almost surely (or with probability one) can be critical for the deployment of Reinforcement Learning (RL) in real-life applications. For example, plane landing and take-off should ideally occur with probability one. We address the problem by introducing Safety Augmented (Saute) Markov Decision Processes (MDPs), where the safety constraints are eliminated by augmenting them into the state-space and reshaping the objective. We show that Saute MDP satisfies the Bellman equation and moves us closer to solving Safe RL with constraints satisfied almost surely. We argue that Saute MDP allows viewing the Safe RL problem from a different perspective enabling new features. For instance, our approach has a plug-and-play nature, i.e., any RL algorithm can be "Sauteed". Additionally, state augmentation allows for policy generalization across safety constraints. We finally show that Saute RL algorithms can outperform their state-of-the-art counterparts when constraint satisfaction is of high importance.

preprint2022arXiv

Scalable Model-based Policy Optimization for Decentralized Networked Systems

Reinforcement learning algorithms require a large amount of samples; this often limits their real-world applications on even simple tasks. Such a challenge is more outstanding in multi-agent tasks, as each step of operation is more costly requiring communications or shifting or resources. This work aims to improve data efficiency of multi-agent control by model-based learning. We consider networked systems where agents are cooperative and communicate only locally with their neighbors, and propose the decentralized model-based policy optimization framework (DMPO). In our method, each agent learns a dynamic model to predict future states and broadcast their predictions by communication, and then the policies are trained under the model rollouts. To alleviate the bias of model-generated data, we restrain the model usage for generating myopic rollouts, thus reducing the compounding error of model generation. To pertain the independence of policy update, we introduce extended value function and theoretically prove that the resulting policy gradient is a close approximation to true policy gradients. We evaluate our algorithm on several benchmarks for intelligent transportation systems, which are connected autonomous vehicle control tasks (Flow and CACC) and adaptive traffic signal control (ATSC). Empirically results show that our method achieves superior data efficiency and matches the performance of model-free methods using true models.

preprint2022arXiv

Self-consistent Gradient-like Eigen Decomposition in Solving Schrödinger Equations

The Schrödinger equation is at the heart of modern quantum mechanics. Since exact solutions of the ground state are typically intractable, standard approaches approximate Schrödinger equation as forms of nonlinear generalized eigenvalue problems $F(V)V = SVΛ$ in which $F(V)$, the matrix to be decomposed, is a function of its own top-$k$ smallest eigenvectors $V$, leading to a "self-consistency problem". Traditional iterative methods heavily rely on high-quality initial guesses of $V$ generated via domain-specific heuristics methods based on quantum mechanics. In this work, we eliminate such a need for domain-specific heuristics by presenting a novel framework, Self-consistent Gradient-like Eigen Decomposition (SCGLED) that regards $F(V)$ as a special "online data generator", thus allows gradient-like eigendecomposition methods in streaming $k$-PCA to approach the self-consistency of the equation from scratch in an iterative way similar to online learning. With several critical numerical improvements, SCGLED is robust to initial guesses, free of quantum-mechanism-based heuristics designs, and neat in implementation. Our experiments show that it not only can simply replace traditional heuristics-based initial guess methods with large performance advantage (achieved averagely 25x more precise than the best baseline in similar wall time), but also is capable of finding highly precise solutions independently without any traditional iterative methods.

preprint2022arXiv

SEREN: Knowing When to Explore and When to Exploit

Efficient reinforcement learning (RL) involves a trade-off between "exploitative" actions that maximise expected reward and "explorative'" ones that sample unvisited states. To encourage exploration, recent approaches proposed adding stochasticity to actions, separating exploration and exploitation phases, or equating reduction in uncertainty with reward. However, these techniques do not necessarily offer entirely systematic approaches making this trade-off. Here we introduce SElective Reinforcement Exploration Network (SEREN) that poses the exploration-exploitation trade-off as a game between an RL agent -- \exploiter, which purely exploits known rewards, and another RL agent -- \switcher, which chooses at which states to activate a pure exploration policy that is trained to minimise system uncertainty and override Exploiter. Using a form of policies known as impulse control, \switcher is able to determine the best set of states to switch to the exploration policy while Exploiter is free to execute its actions everywhere else. We prove that SEREN converges quickly and induces a natural schedule towards pure exploitation. Through extensive empirical studies in both discrete (MiniGrid) and continuous (MuJoCo) control benchmarks, we show that SEREN can be readily combined with existing RL algorithms to yield significant improvement in performance relative to state-of-the-art algorithms.

preprint2022arXiv

Settling the Communication Complexity for Distributed Offline Reinforcement Learning

We study a novel setting in offline reinforcement learning (RL) where a number of distributed machines jointly cooperate to solve the problem but only one single round of communication is allowed and there is a budget constraint on the total number of information (in terms of bits) that each machine can send out. For value function prediction in contextual bandits, and both episodic and non-episodic MDPs, we establish information-theoretic lower bounds on the minimax risk for distributed statistical estimators; this reveals the minimum amount of communication required by any offline RL algorithms. Specifically, for contextual bandits, we show that the number of bits must scale at least as $Ω(AC)$ to match the centralised minimax optimal rate, where $A$ is the number of actions and $C$ is the context dimension; meanwhile, we reach similar results in the MDP settings. Furthermore, we develop learning algorithms based on least-squares estimates and Monte-Carlo return estimates and provide a sharp analysis showing that they can achieve optimal risk up to logarithmic factors. Additionally, we also show that temporal difference is unable to efficiently utilise information from all available devices under the single-round communication setting due to the initial bias of this method. To our best knowledge, this paper presents the first minimax lower bounds for distributed offline RL problems.

preprint2022arXiv

Settling the Variance of Multi-Agent Policy Gradients

Policy gradient (PG) methods are popular reinforcement learning (RL) methods where a baseline is often applied to reduce the variance of gradient estimates. In multi-agent RL (MARL), although the PG theorem can be naturally extended, the effectiveness of multi-agent PG (MAPG) methods degrades as the variance of gradient estimates increases rapidly with the number of agents. In this paper, we offer a rigorous analysis of MAPG methods by, firstly, quantifying the contributions of the number of agents and agents' explorations to the variance of MAPG estimators. Based on this analysis, we derive the optimal baseline (OB) that achieves the minimal variance. In comparison to the OB, we measure the excess variance of existing MARL algorithms such as vanilla MAPG and COMA. Considering using deep neural networks, we also propose a surrogate version of OB, which can be seamlessly plugged into any existing PG methods in MARL. On benchmarks of Multi-Agent MuJoCo and StarCraft challenges, our OB technique effectively stabilises training and improves the performance of multi-agent PPO and COMA algorithms by a significant margin.

preprint2022arXiv

SFE-AI at SemEval-2022 Task 11: Low-Resource Named Entity Recognition using Large Pre-trained Language Models

Large scale pre-training models have been widely used in named entity recognition (NER) tasks. However, model ensemble through parameter averaging or voting can not give full play to the differentiation advantages of different models, especially in the open domain. This paper describes our NER system in the SemEval 2022 task11: MultiCoNER. We proposed an effective system to adaptively ensemble pre-trained language models by a Transformer layer. By assigning different weights to each model for different inputs, we adopted the Transformer layer to integrate the advantages of diverse models effectively. Experimental results show that our method achieves superior performances in Farsi and Dutch.

preprint2022arXiv

Some criteria for integer sequences pair being realizable by a graph

Let $A=(a_1,\ldots,a_n)$ and $B=(b_1,\ldots,b_n)$ be two sequences of nonnegative integers with $a_i \le b_i$ for $1\le i\le n$. The pair $(A;B)$ is said to be realizable by a graph if there exists a simple graph $G$ with vertices $v_1,\ldots, v_n$ such that $a_i\le d_G(v_i)\le b_i$ for $1\le i\le n$. Let $\preceq$ denote the lexicographic ordering on $Z\times Z:$ $(a_{i+1},b_{i+1})\preceq (a_i,b_i)\Longleftrightarrow [(a_{i+1}<a_i)\vee ((a_{i+1}=a_i)\&(b_{i+1}\le b_i))]$. We say that the sequences $A$ and $B$ are in good order if $(a_{i+1},b_{i+1})\preceq (a_i,b_i)$. In this paper, we consider the generalizations of six classical characterizations on sequences pair due to Berge, Ryser et al. and present related results.

preprint2022arXiv

Structured Q-learning For Antibody Design

Optimizing combinatorial structures is core to many real-world problems, such as those encountered in life sciences. For example, one of the crucial steps involved in antibody design is to find an arrangement of amino acids in a protein sequence that improves its binding with a pathogen. Combinatorial optimization of antibodies is difficult due to extremely large search spaces and non-linear objectives. Even for modest antibody design problems, where proteins have a sequence length of eleven, we are faced with searching over 2.05 x 10^14 structures. Applying traditional Reinforcement Learning algorithms such as Q-learning to combinatorial optimization results in poor performance. We propose Structured Q-learning (SQL), an extension of Q-learning that incorporates structural priors for combinatorial optimization. Using a molecular docking simulator, we demonstrate that SQL finds high binding energy sequences and performs favourably against baselines on eight challenging antibody design tasks, including designing antibodies for SARS-COV.

preprint2022arXiv

That Slepen Al the Nyght with Open Ye! Cross-era Sequence Segmentation with Switch-memory

The evolution of language follows the rule of gradual change. Grammar, vocabulary, and lexical semantic shifts take place over time, resulting in a diachronic linguistic gap. As such, a considerable amount of texts are written in languages of different eras, which creates obstacles for natural language processing tasks, such as word segmentation and machine translation. Although the Chinese language has a long history, previous Chinese natural language processing research has primarily focused on tasks within a specific era. Therefore, we propose a cross-era learning framework for Chinese word segmentation (CWS), CROSSWISE, which uses the Switch-memory (SM) module to incorporate era-specific linguistic knowledge. Experiments on four corpora from different eras show that the performance of each corpus significantly improves. Further analyses also demonstrate that the SM can effectively integrate the knowledge of the eras into the neural network.

preprint2022arXiv

The Complete SC-invariant Affine Automorphisms of Polar Codes

Automorphism ensemble (AE) decoding for polar codes was proposed by decoding permuted codewords with successive cancellation (SC) decoders in parallel and hence has lower latency compared to that of successive cancellation list (SCL) decoding. However, some automorphisms are SC-invariant, thus are redundant in AE decoding. In this paper, we find a necessary and sufficient condition related to the block lower-triangular structure of transformation matrices to identify SC-invariant automorphisms. Furthermore, we provide an algorithm to determine the complete SC-invariant affine automorphisms under a specific polar code construction.

preprint2022arXiv

Towards Target-Driven Visual Navigation in Indoor Scenes via Generative Imitation Learning

We present a target-driven navigation system to improve mapless visual navigation in indoor scenes. Our method takes a multi-view observation of a robot and a target as inputs at each time step to provide a sequence of actions that move the robot to the target without relying on odometry or GPS at runtime. The system is learned by optimizing a combinational objective encompassing three key designs. First, we propose that an agent conceives the next observation before making an action decision. This is achieved by learning a variational generative module from expert demonstrations. We then propose predicting static collision in advance, as an auxiliary task to improve safety during navigation. Moreover, to alleviate the training data imbalance problem of termination action prediction, we also introduce a target checking module to differentiate from augmenting navigation policy with a termination action. The three proposed designs all contribute to the improved training data efficiency, static collision avoidance, and navigation generalization performance, resulting in a novel target-driven mapless navigation system. Through experiments on a TurtleBot, we provide evidence that our model can be integrated into a robotic system and navigate in the real world. Videos and models can be found in the supplementary material.

preprint2022arXiv

Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning

Trust region methods rigorously enabled reinforcement learning (RL) agents to learn monotonically improving policies, leading to superior performance on a variety of tasks. Unfortunately, when it comes to multi-agent reinforcement learning (MARL), the property of monotonic improvement may not simply apply; this is because agents, even in cooperative games, could have conflicting directions of policy updates. As a result, achieving a guaranteed improvement on the joint policy where each agent acts individually remains an open challenge. In this paper, we extend the theory of trust region learning to MARL. Central to our findings are the multi-agent advantage decomposition lemma and the sequential policy update scheme. Based on these, we develop Heterogeneous-Agent Trust Region Policy Optimisation (HATPRO) and Heterogeneous-Agent Proximal Policy Optimisation (HAPPO) algorithms. Unlike many existing MARL algorithms, HATRPO/HAPPO do not need agents to share parameters, nor do they need any restrictive assumptions on decomposibility of the joint value function. Most importantly, we justify in theory the monotonic improvement property of HATRPO/HAPPO. We evaluate the proposed methods on a series of Multi-Agent MuJoCo and StarCraftII tasks. Results show that HATRPO and HAPPO significantly outperform strong baselines such as IPPO, MAPPO and MADDPG on all tested tasks, therefore establishing a new state of the art.

preprint2022arXiv

Uncertainty Quantification for Hyperspectral Image Denoising Frameworks based on Low-rank Matrix Approximation

Sliding-window based low-rank matrix approximation (LRMA) is a technique widely used in hyperspectral images (HSIs) denoising or completion. However, the uncertainty quantification of the restored HSI has not been addressed to date. Accurate uncertainty quantification of the denoised HSI facilitates to applications such as multi-source or multi-scale data fusion, data assimilation, and product uncertainty quantification, since these applications require an accurate approach to describe the statistical distributions of the input data. Therefore, we propose a prior-free closed-form element-wise uncertainty quantification method for LRMA-based HSI restoration. Our closed-form algorithm overcomes the difficulty of the HSI patch mixing problem caused by the sliding-window strategy used in the conventional LRMA process. The proposed approach only requires the uncertainty of the observed HSI and provides the uncertainty result relatively rapidly and with similar computational complexity as the LRMA technique. We conduct extensive experiments to validate the estimation accuracy of the proposed closed-form uncertainty approach. The method is robust to at least 10% random impulse noise at the cost of 10-20% of additional processing time compared to the LRMA. The experiments indicate that the proposed closed-form uncertainty quantification method is more applicable to real-world applications than the baseline Monte Carlo test, which is computationally expensive. The code is available in the attachment and will be released after the acceptance of this paper.

preprint2022arXiv

UTOPIC: Uncertainty-aware Overlap Prediction Network for Partial Point Cloud Registration

High-confidence overlap prediction and accurate correspondences are critical for cutting-edge models to align paired point clouds in a partial-to-partial manner. However, there inherently exists uncertainty between the overlapping and non-overlapping regions, which has always been neglected and significantly affects the registration performance. Beyond the current wisdom, we propose a novel uncertainty-aware overlap prediction network, dubbed UTOPIC, to tackle the ambiguous overlap prediction problem; to our knowledge, this is the first to explicitly introduce overlap uncertainty to point cloud registration. Moreover, we induce the feature extractor to implicitly perceive the shape knowledge through a completion decoder, and present a geometric relation embedding for Transformer to obtain transformation-invariant geometry-aware feature representations. With the merits of more reliable overlap scores and more precise dense correspondences, UTOPIC can achieve stable and accurate registration results, even for the inputs with limited overlapping areas. Extensive quantitative and qualitative experiments on synthetic and real benchmarks demonstrate the superiority of our approach over state-of-the-art methods.

preprint2022arXiv

Verified Compositions of Neural Network Controllers for Temporal Logic Control Objectives

This paper presents a new approach to design verified compositions of Neural Network (NN) controllers for autonomous systems with tasks captured by Linear Temporal Logic (LTL) formulas. Particularly, the LTL formula requires the system to reach and avoid certain regions in a temporal/logical order. We assume that the system is equipped with a finite set of trained NN controllers. Each controller has been trained so that it can drive the system towards a specific region of interest while avoiding others. Our goal is to check if there exists a temporal composition of the trained NN controllers - and if so, to compute it - that will yield composite system behaviors that satisfy a user-specified LTL task for any initial system state belonging to a given set. To address this problem, we propose a new approach that relies on a novel integration of automata theory and recently proposed reachability analysis tools for NN-controlled systems. We note that the proposed method can be applied to other controllers, not necessarily modeled by NNs, by appropriate selection of the reachability analysis tool. We focus on NN controllers due to their lack of robustness. The proposed method is demonstrated on navigation tasks for aerial vehicles.

preprint2021arXiv

A relic sketch extraction framework based on detail-aware hierarchical deep network

As the first step of the restoration process of painted relics, sketch extraction plays an important role in cultural research. However, sketch extraction suffers from serious disease corrosion, which results in broken lines and noise. To overcome these problems, we propose a deep learning-based hierarchical sketch extraction framework for painted cultural relics. We design the sketch extraction process into two stages: coarse extraction and fine extraction. In the coarse extraction stage, we develop a novel detail-aware bi-directional cascade network that integrates flow-based difference-of-Gaussians (FDoG) edge detection and a bi-directional cascade network (BDCN) under a transfer learning framework. It not only uses the pre-trained strategy to extenuate the requirements of large datasets for deep network training but also guides the network to learn the detail characteristics by the prior knowledge from FDoG. For the fine extraction stage, we design a new multiscale U-Net (MSU-Net) to effectively remove disease noise and refine the sketch. Specifically, all the features extracted from multiple intermediate layers in the decoder of MSU-Net are fused for sketch predication. Experimental results showed that the proposed method outperforms the other seven state-of-the-art methods in terms of visual and quantitative metrics and can also deal with complex backgrounds.

preprint2021arXiv

A Targeted Attack on Black-Box Neural Machine Translation with Parallel Data Poisoning

As modern neural machine translation (NMT) systems have been widely deployed, their security vulnerabilities require close scrutiny. Most recently, NMT systems have been found vulnerable to targeted attacks which cause them to produce specific, unsolicited, and even harmful translations. These attacks are usually exploited in a white-box setting, where adversarial inputs causing targeted translations are discovered for a known target system. However, this approach is less viable when the target system is black-box and unknown to the adversary (e.g., secured commercial systems). In this paper, we show that targeted attacks on black-box NMT systems are feasible, based on poisoning a small fraction of their parallel training data. We show that this attack can be realised practically via targeted corruption of web documents crawled to form the system's training data. We then analyse the effectiveness of the targeted poisoning in two common NMT training scenarios: the from-scratch training and the pre-train & fine-tune paradigm. Our results are alarming: even on the state-of-the-art systems trained with massive parallel data (tens of millions), the attacks are still successful (over 50% success rate) under surprisingly low poisoning budgets (e.g., 0.006%). Lastly, we discuss potential defences to counter such attacks.

preprint2021arXiv

Adaptive Multi-Teacher Multi-level Knowledge Distillation

Knowledge distillation~(KD) is an effective learning paradigm for improving the performance of lightweight student networks by utilizing additional supervision knowledge distilled from teacher networks. Most pioneering studies either learn from only a single teacher in their distillation learning methods, neglecting the potential that a student can learn from multiple teachers simultaneously, or simply treat each teacher to be equally important, unable to reveal the different importance of teachers for specific examples. To bridge this gap, we propose a novel adaptive multi-teacher multi-level knowledge distillation learning framework~(AMTML-KD), which consists two novel insights: (i) associating each teacher with a latent representation to adaptively learn instance-level teacher importance weights which are leveraged for acquiring integrated soft-targets~(high-level knowledge) and (ii) enabling the intermediate-level hints~(intermediate-level knowledge) to be gathered from multiple teachers by the proposed multi-group hint strategy. As such, a student model can learn multi-level knowledge from multiple teachers through AMTML-KD. Extensive results on publicly available datasets demonstrate the proposed learning framework ensures student to achieve improved performance than strong competitors.

preprint2021arXiv

Contrastive Separative Coding for Self-supervised Representation Learning

To extract robust deep representations from long sequential modeling of speech data, we propose a self-supervised learning approach, namely Contrastive Separative Coding (CSC). Our key finding is to learn such representations by separating the target signal from contrastive interfering signals. First, a multi-task separative encoder is built to extract shared separable and discriminative embedding; secondly, we propose a powerful cross-attention mechanism performed over speaker representations across various interfering conditions, allowing the model to focus on and globally aggregate the most critical information to answer the "query" (current bottom-up embedding) while paying less attention to interfering, noisy, or irrelevant parts; lastly, we form a new probabilistic contrastive loss which estimates and maximizes the mutual information between the representations and the global speaker vector. While most prior unsupervised methods have focused on predicting the future, neighboring, or missing samples, we take a different perspective of predicting the interfered samples. Moreover, our contrastive separative loss is free from negative sampling. The experiment demonstrates that our approach can learn useful representations achieving a strong speaker verification performance in adverse conditions.

preprint2021arXiv

Controllable and Diverse Text Generation in E-commerce

In E-commerce, a key challenge in text generation is to find a good trade-off between word diversity and accuracy (relevance) in order to make generated text appear more natural and human-like. In order to improve the relevance of generated results, conditional text generators were developed that use input keywords or attributes to produce the corresponding text. Prior work, however, do not finely control the diversity of automatically generated sentences. For example, it does not control the order of keywords to put more relevant ones first. Moreover, it does not explicitly control the balance between diversity and accuracy. To remedy these problems, we propose a fine-grained controllable generative model, called~\textit{Apex}, that uses an algorithm borrowed from automatic control (namely, a variant of the \textit{proportional, integral, and derivative (PID) controller}) to precisely manipulate the diversity/accuracy trade-off of generated text. The algorithm is injected into a Conditional Variational Autoencoder (CVAE), allowing \textit{Apex} to control both (i) the order of keywords in the generated sentences (conditioned on the input keywords and their order), and (ii) the trade-off between diversity and accuracy. Evaluation results on real-world datasets show that the proposed method outperforms existing generative models in terms of diversity and relevance. Apex is currently deployed to generate production descriptions and item recommendation reasons in Taobao owned by Alibaba, the largest E-commerce platform in China. The A/B production test results show that our method improves click-through rate (CTR) by 13.17\% compared to the existing method for production descriptions. For item recommendation reason, it is able to increase CTR by 6.89\% and 1.42\% compared to user reviews and top-K item recommendation without reviews, respectively.

preprint2021arXiv

Data-Free Knowledge Transfer: A Survey

In the last decade, many deep learning models have been well trained and made a great success in various fields of machine intelligence, especially for computer vision and natural language processing. To better leverage the potential of these well-trained models in intra-domain or cross-domain transfer learning situations, knowledge distillation (KD) and domain adaptation (DA) are proposed and become research highlights. They both aim to transfer useful information from a well-trained model with original training data. However, the original data is not always available in many cases due to privacy, copyright or confidentiality. Recently, the data-free knowledge transfer paradigm has attracted appealing attention as it deals with distilling valuable knowledge from well-trained models without requiring to access to the training data. In particular, it mainly consists of the data-free knowledge distillation (DFKD) and source data-free domain adaptation (SFDA). On the one hand, DFKD aims to transfer the intra-domain knowledge of original data from a cumbersome teacher network to a compact student network for model compression and efficient inference. On the other hand, the goal of SFDA is to reuse the cross-domain knowledge stored in a well-trained source model and adapt it to a target domain. In this paper, we provide a comprehensive survey on data-free knowledge transfer from the perspectives of knowledge distillation and unsupervised domain adaptation, to help readers have a better understanding of the current research status and ideas. Applications and challenges of the two areas are briefly reviewed, respectively. Furthermore, we provide some insights to the subject of future research.

preprint2021arXiv

Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems

Multiagent reinforcement learning (MARL) has achieved a remarkable amount of success in solving various types of video games. A cornerstone of this success is the auto-curriculum framework, which shapes the learning process by continually creating new challenging tasks for agents to adapt to, thereby facilitating the acquisition of new skills. In order to extend MARL methods to real-world domains outside of video games, we envision in this blue sky paper that maintaining a diversity-aware auto-curriculum is critical for successful MARL applications. Specifically, we argue that \emph{behavioural diversity} is a pivotal, yet under-explored, component for real-world multiagent learning systems, and that significant work remains in understanding how to design a diversity-aware auto-curriculum. We list four open challenges for auto-curriculum techniques, which we believe deserve more attention from this community. Towards validating our vision, we recommend modelling realistic interactive behaviours in autonomous driving as an important test bed, and recommend the SMARTS/ULTRA benchmark.

preprint2021arXiv

Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networks

Recent research on the time-domain audio separation networks (TasNets) has brought great success to speech separation. Nevertheless, conventional TasNets struggle to satisfy the memory and latency constraints in industrial applications. In this regard, we design a low-cost high-performance architecture, namely, globally attentive locally recurrent (GALR) network. Alike the dual-path RNN (DPRNN), we first split a feature sequence into 2D segments and then process the sequence along both the intra- and inter-segment dimensions. Our main innovation lies in that, on top of features recurrently processed along the inter-segment dimensions, GALR applies a self-attention mechanism to the sequence along the inter-segment dimension, which aggregates context-aware information and also enables parallelization. Our experiments suggest that GALR is a notably more effective network than the prior work. On one hand, with only 1.5M parameters, it has achieved comparable separation performance at a much lower cost with 36.1% less runtime memory and 49.4% fewer computational operations, relative to the DPRNN. On the other hand, in a comparable model size with DPRNN, GALR has consistently outperformed DPRNN in three datasets, in particular, with a substantial margin of 2.4dB absolute improvement of SI-SNRi in the benchmark WSJ0-2mix task.

preprint2021arXiv

Efficient Semi-Implicit Variational Inference

In this paper, we propose CI-VI an efficient and scalable solver for semi-implicit variational inference (SIVI). Our method, first, maps SIVI's evidence lower bound (ELBO) to a form involving a nonlinear functional nesting of expected values and then develops a rigorous optimiser capable of correctly handling bias inherent to nonlinear nested expectations using an extrapolation-smoothing mechanism coupled with gradient sketching. Our theoretical results demonstrate convergence to a stationary point of the ELBO in general non-convex settings typically arising when using deep network models and an order of $O(t^{-\frac{4}{5}})$ gradient-bias-vanishing rate. We believe these results generalise beyond the specific nesting arising from SIVI to other forms. Finally, in a set of experiments, we demonstrate the effectiveness of our algorithm in approximating complex posteriors on various data-sets including those from natural language processing.

preprint2021arXiv

Facile preparation of CuCo$_2$S$_4$/Cu$_7$S$_4$ nanocomposites as high-performance cathode materials for rechargeable magnesium batteries

Searching for efficient and high-performance cathode materials for rechargeable magnesium ion batteries (RMBs) is urgent for exploring sustainable energy technologies. However, the majority of cathode materials for RMBs usually suffer from low rate capacity and inferior cycle performance caused by structure collapse. Herein, ternary CuCo$_2$S$_4$/Cu$_7$S$_4$ composites with nano-sized are first synthesized by a facile solvothermal method in this work and the magnesium ion storage behavior is discussed when applied in the cathode for RMBs. Electrochemical results demonstrate that the nanosphere-like CuCo$_2$S$_4$/Cu$_7$S$_4$ composites exhibit a high initial discharge capacity of 256 mAh/g at 10 mA/g and 123 mAh/g at 300 mA/g at room temperature. Furthermore, an outstanding long-term cyclic stability with a reversible capacity of 106 mA/g after 300 cycles and the coulombic efficiency of about 99% are achieved at 300 mA/g. Such remarkable electrochemical performance is owing to the nanosphere-like structure, ternary composition and pseudocapacitive storage behavior of CuCo$_2$S$_4$/Cu$_7$S$_4$. The results of this work indicate that the CuCo$_2$S$_4$/Cu$_7$S$_4$ nanocomposites synthesized by a facile and efficient method are promising cathodes for RMBs in energy storage/conversion application.

preprint2021arXiv

High power 1640-nm Er:Y2O3 ceramic laser at room temperature

We report on high power operation of Er:Y2O3 ceramic laser at ~1.6 μm using low scattering loss, 0.25 at.% Er3+ doped ceramic sample fabricated in-house via co-precipitation process. The laser is in-band pumped by an Er, Yb fiber laser at 1535.6 nm and generates 10.2 W of continuous-wave (CW) output power at 1640.4 nm with a slope efficiency of 25% with respect to the absorbed pump power. To the best of our knowledge, this is the first demonstration of ~1.6 μm Er:Y2O3 laser at room temperature. The prospects for further scaling in output power and lasing efficiency via low Er3+ doping and reduced energy-transfer upconversion are discussed.

preprint2021arXiv

JUNO Physics and Detector

The Jiangmen Underground Neutrino Observatory (JUNO) is a 20 kton LS detector at 700-m underground. An excellent energy resolution and a large fiducial volume offer exciting opportunities for addressing many important topics in neutrino and astro-particle physics. With 6 years of data, the neutrino mass ordering can be determined at 3-4 sigma and three oscillation parameters can be measured to a precision of 0.6% or better by detecting reactor antineutrinos. With 10 years of data, DSNB could be observed at 3-sigma; a lower limit of the proton lifetime of 8.34e33 years (90% C.L.) can be set by searching for p->nu_bar K^+; detection of solar neutrinos would shed new light on the solar metallicity problem and examine the vacuum-matter transition region. A core-collapse supernova at 10 kpc would lead to ~5000 IBD and ~2000 (300) all-flavor neutrino-proton (electron) scattering events. Geo-neutrinos can be detected with a rate of ~400 events/year. We also summarize the final design of the JUNO detector and the key R&D achievements. All 20-inch PMTs have been tested. The average photon detection efficiency is 28.9% for the 15,000 MCP PMTs and 28.1% for the 5,000 dynode PMTs, higher than the JUNO requirement of 27%. Together with the >20 m attenuation length of LS, we expect a yield of 1345 p.e. per MeV and an effective energy resolution of 3.02%/\sqrt{E (MeV)}$ in simulations. The underwater electronics is designed to have a loss rate <0.5% in 6 years. With degassing membranes and a micro-bubble system, the radon concentration in the 35-kton water pool could be lowered to <10 mBq/m^3. Acrylic panels of radiopurity <0.5 ppt U/Th are produced. The 20-kton LS will be purified onsite. Singles in the fiducial volume can be controlled to ~10 Hz. The JUNO experiment also features a double calorimeter system with 25,600 3-inch PMTs, a LS testing facility OSIRIS, and a near detector TAO.

preprint2021arXiv

Learning the Implicit Semantic Representation on Graph-Structured Data

Existing representation learning methods in graph convolutional networks are mainly designed by describing the neighborhood of each node as a perceptual whole, while the implicit semantic associations behind highly complex interactions of graphs are largely unexploited. In this paper, we propose a Semantic Graph Convolutional Networks (SGCN) that explores the implicit semantics by learning latent semantic-paths in graphs. In previous work, there are explorations of graph semantics via meta-paths. However, these methods mainly rely on explicit heterogeneous information that is hard to be obtained in a large amount of graph-structured data. SGCN first breaks through this restriction via leveraging the semantic-paths dynamically and automatically during the node aggregating process. To evaluate our idea, we conduct sufficient experiments on several standard datasets, and the empirical results show the superior performance of our model.

preprint2021arXiv

Meromorphic functions of finite $φ$-order and linear Askey-Wilson divided difference equations

The growth of meromorphic solutions of linear difference equations containing Askey-Wilson divided difference operators is estimated. The $φ$-order is used as a general growth indicator, which covers the growth spectrum between the logarithmic order $ρ_{\log}(f)$ and the classical order $ρ(f)$ of a meromorphic function $f$.

preprint2021arXiv

Multiscale Attention Guided Network for COVID-19 Diagnosis Using Chest X-ray Images

Coronavirus disease 2019 (COVID-19) is one of the most destructive pandemic after millennium, forcing the world to tackle a health crisis. Automated lung infections classification using chest X-ray (CXR) images could strengthen diagnostic capability when handling COVID-19. However, classifying COVID-19 from pneumonia cases using CXR image is a difficult task because of shared spatial characteristics, high feature variation and contrast diversity between cases. Moreover, massive data collection is impractical for a newly emerged disease, which limited the performance of data thirsty deep learning models. To address these challenges, Multiscale Attention Guided deep network with Soft Distance regularization (MAG-SD) is proposed to automatically classify COVID-19 from pneumonia CXR images. In MAG-SD, MA-Net is used to produce prediction vector and attention from multiscale feature maps. To improve the robustness of trained model and relieve the shortage of training data, attention guided augmentations along with a soft distance regularization are posed, which aims at generating meaningful augmentations and reduce noise. Our multiscale attention model achieves better classification performance on our pneumonia CXR image dataset. Plentiful experiments are proposed for MAG-SD which demonstrates its unique advantage in pneumonia classification over cutting-edge models. The code is available at https://github.com/JasonLeeGHub/MAG-SD.

preprint2021arXiv

Replica-exchange Nosé-Hoover dynamics for Bayesian learning on large datasets

In this paper, we present a new practical method for Bayesian learning that can rapidly draw representative samples from complex posterior distributions with multiple isolated modes in the presence of mini-batch noise. This is achieved by simulating a collection of replicas in parallel with different temperatures and periodically swapping them. When evolving the replicas' states, the Nosé-Hoover dynamics is applied, which adaptively neutralizes the mini-batch noise. To perform proper exchanges, a new protocol is developed with a noise-aware test of acceptance, by which the detailed balance is reserved in an asymptotic way. While its efficacy on complex multimodal posteriors has been illustrated by testing over synthetic distributions, experiments with deep Bayesian neural networks on large-scale datasets have shown its significant improvements over strong baselines.

preprint2021arXiv

Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separation

One of the leading single-channel speech separation (SS) models is based on a TasNet with a dual-path segmentation technique, where the size of each segment remains unchanged throughout all layers. In contrast, our key finding is that multi-granularity features are essential for enhancing contextual modeling and computational efficiency. We introduce a self-attentive network with a novel sandglass-shape, namely Sandglasset, which advances the state-of-the-art (SOTA) SS performance at significantly smaller model size and computational cost. Forward along each block inside Sandglasset, the temporal granularity of the features gradually becomes coarser until reaching half of the network blocks, and then successively turns finer towards the raw signal level. We also unfold that residual connections between features with the same granularity are critical for preserving information after passing through the bottleneck layer. Experiments show our Sandglasset with only 2.3M parameters has achieved the best results on two benchmark SS datasets -- WSJ0-2mix and WSJ0-3mix, where the SI-SNRi scores have been improved by absolute 0.8 dB and 2.4 dB, respectively, comparing to the prior SOTA results.

preprint2021arXiv

Tune-In: Training Under Negative Environments with Interference for Attention Networks Simulating Cocktail Party Effect

We study the cocktail party problem and propose a novel attention network called Tune-In, abbreviated for training under negative environments with interference. It firstly learns two separate spaces of speaker-knowledge and speech-stimuli based on a shared feature space, where a new block structure is designed as the building block for all spaces, and then cooperatively solves different tasks. Between the two spaces, information is cast towards each other via a novel cross- and dual-attention mechanism, mimicking the bottom-up and top-down processes of a human's cocktail party effect. It turns out that substantially discriminative and generalizable speaker representations can be learnt in severely interfered conditions via our self-supervised training. The experimental results verify this seeming paradox. The learnt speaker embedding has superior discriminative power than a standard speaker verification method; meanwhile, Tune-In achieves remarkably better speech separation performances in terms of SI-SNRi and SDRi consistently in all test modes, and especially at lower memory and computational consumption, than state-of-the-art benchmark systems.

preprint2020arXiv

$H_\infty$ Model-free Reinforcement Learning with Robust Stability Guarantee

Reinforcement learning is showing great potentials in robotics applications, including autonomous driving, robot manipulation and locomotion. However, with complex uncertainties in the real-world environment, it is difficult to guarantee the successful generalization and sim-to-real transfer of learned policies theoretically. In this paper, we introduce and extend the idea of robust stability and $H_\infty$ control to design policies with both stability and robustness guarantee. Specifically, a sample-based approach for analyzing the Lyapunov stability and performance robustness of a learning-based control system is proposed. Based on the theoretical results, a maximum entropy algorithm is developed for searching Lyapunov function and designing a policy with provable robust stability guarantee. Without any specific domain knowledge, our method can find a policy that is robust to various uncertainties and generalizes well to different test environments. In our experiments, we show that our method achieves better robustness to both large impulsive disturbances and parametric variations in the environment than the state-of-art results in both robust and generic RL, as well as classic control. Anonymous code is available to reproduce the experimental results at https://github.com/RobustStabilityGuaranteeRL/RobustStabilityGuaranteeRL.

preprint2020arXiv

3DPVNet: Patch-level 3D Hough Voting Network for 6D Pose Estimation

In this paper, we focus on estimating the 6D pose of objects in point clouds. Although the topic has been widely studied, pose estimation in point clouds remains a challenging problem due to the noise and occlusion. To address the problem, a novel 3DPVNet is presented in this work, which utilizes 3D local patches to vote for the object 6D poses. 3DPVNet is comprised of three modules. In particular, a Patch Unification (\textbf{PU}) module is first introduced to normalize the input patch, and also create a standard local coordinate frame on it to generate a reliable vote. We then devise a Weight-guided Neighboring Feature Fusion (\textbf{WNFF}) module in the network, which fuses the neighboring features to yield a semi-global feature for the center patch. WNFF module mines the neighboring information of a local patch, such that the representation capability to local geometric characteristics is significantly enhanced, making the method robust to a certain level of noise. Moreover, we present a Patch-level Voting (\textbf{PV}) module to regress transformations and generates pose votes. After the aggregation of all votes from patches and a refinement step, the final pose of the object can be obtained. Compared to recent voting-based methods, 3DPVNet is patch-level, and directly carried out on point clouds. Therefore, 3DPVNet achieves less computation than point/pixel-level voting scheme, and has robustness to partial data. Experiments on several datasets demonstrate that 3DPVNet achieves the state-of-the-art performance, and is also robust against noise and occlusions.

preprint2020arXiv

A Deep Recurrent Survival Model for Unbiased Ranking

Position bias is a critical problem in information retrieval when dealing with implicit yet biased user feedback data. Unbiased ranking methods typically rely on causality models and debias the user feedback through inverse propensity weighting. While practical, these methods still suffer from two major problems. First, when inferring a user click, the impact of the contextual information, such as documents that have been examined, is often ignored. Second, only the position bias is considered but other issues resulted from user browsing behaviors are overlooked. In this paper, we propose an end-to-end Deep Recurrent Survival Ranking (DRSR), a unified framework to jointly model user's various behaviors, to (i) consider the rich contextual information in the ranking list; and (ii) address the hidden issues underlying user behaviors, i.e., to mine observe pattern in queries without any click (non-click queries), and to model tracking logs which cannot truly reflect the user browsing intents (untrusted observation). Specifically, we adopt a recurrent neural network to model the contextual information and estimates the conditional likelihood of user feedback at each position. We then incorporate survival analysis techniques with the probability chain rule to mathematically recover the unbiased joint probability of one user's various behaviors. DRSR can be easily incorporated with both point-wise and pair-wise learning objectives. The extensive experiments over two large-scale industrial datasets demonstrate the significant performance gains of our model comparing with the state-of-the-arts.

preprint2020arXiv

A Framework for Behavioral Biometric Authentication using Deep Metric Learning on Mobile Devices

Mobile authentication using behavioral biometrics has been an active area of research. Existing research relies on building machine learning classifiers to recognize an individual's unique patterns. However, these classifiers are not powerful enough to learn the discriminative features. When implemented on the mobile devices, they face new challenges from the behavioral dynamics, data privacy and side-channel leaks. To address these challenges, we present a new framework to incorporate training on battery-powered mobile devices, so private data never leaves the device and training can be flexibly scheduled to adapt the behavioral patterns at runtime. We re-formulate the classification problem into deep metric learning to improve the discriminative power and design an effective countermeasure to thwart side-channel leaks by embedding a noise signature in the sensing signals without sacrificing too much usability. The experiments demonstrate authentication accuracy over 95% on three public datasets, a sheer 15% gain from multi-class classification with less data and robustness against brute-force and side-channel attacks with 99% and 90% success, respectively. We show the feasibility of training with mobile CPUs, where training 100 epochs takes less than 10 mins and can be boosted 3-5 times with feature transfer. Finally, we profile memory, energy and computational overhead. Our results indicate that training consumes lower energy than watching videos and slightly higher energy than playing games.

preprint2020arXiv

A Novel 3D Space-Time-Frequency Non-Stationary Channel Model for 6G THz Indoor Communication Systems

Terahertz (THz) communication is now being considered as one of possible technologies for the sixth generation (6G) communication systems. In this paper, a novel three-dimensional (3D) space-time-frequency non-stationary massive multiple-input multiple-output (MIMO) channel model for 6G THz indoor communication systems is proposed. In this geometry-based stochastic model (GBSM), the initialization and evolution of parameters in time, space, and frequency domains are developed to generate the complete channel transfer function (CTF). Based on the proposed model, the correlation functions including time auto-correlation function (ACF), spatial crosscorrelation function (CCF), and frequency correlation function (FCF) are investigated. The results show that the statistical properties of the simulation model match well with those of the theoretical model. The stationary intervals at different frequencies are simulated. The non-stationarity in time, space, and frequency domains is verified by theoretical derivations and simulations.

preprint2020arXiv

A Soft Cancellation Decoder for Parity-Check Polar Codes

Polar codes has been selected as the channel coding scheme for 5G new radio (NR) control channel. Specifically, a special type of parity-check polar (PC-Polar) codes was adopted in uplink control information (UCI). In this paper, we propose a parity-check soft-cancellation (PC-SCAN) algorithm and its simplified version to decode PC-Polar codes. The potential benefits are two-fold. First, PC-SCAN can provide soft output for PC-Polar codes, which is essential for advanced turbo receivers. Second, the decoding performance is better than that of successive cancellation (SC). This is due to the fact that parity-check constraints can be exploited by PC-SCAN to enhance the reliability of other information bits over the iterations. Moreover, we describe a cyclic-shift-register (CSR) based implementation "CSR-SCAN" to reduce both hardware cost and latency with minimum performance loss.

preprint2020arXiv

Actor-Critic Reinforcement Learning for Control with Stability Guarantee

Reinforcement Learning (RL) and its integration with deep learning have achieved impressive performance in various robotic control tasks, ranging from motion planning and navigation to end-to-end visual manipulation. However, stability is not guaranteed in model-free RL by solely using data. From a control-theoretic perspective, stability is the most important property for any control system, since it is closely related to safety, robustness, and reliability of robotic systems. In this paper, we propose an actor-critic RL framework for control which can guarantee closed-loop stability by employing the classic Lyapunov's method in control theory. First of all, a data-based stability theorem is proposed for stochastic nonlinear systems modeled by Markov decision process. Then we show that the stability condition could be exploited as the critic in the actor-critic RL to learn a controller/policy. At last, the effectiveness of our approach is evaluated on several well-known 3-dimensional robot control tasks and a synthetic biology gene network tracking task in three different popular physics simulation platforms. As an empirical evaluation on the advantage of stability, we show that the learned policies can enable the systems to recover to the equilibrium or way-points when interfered by uncertainties such as system parametric variations and external disturbances to a certain extent.

preprint2020arXiv

An Improved Method for the Fitting and Prediction of the Number of COVID-19 Confirmed Cases Based on LSTM

New coronavirus disease (COVID-19) has constituted a global pandemic and has spread to most countries and regions in the world. By understanding the development trend of a regional epidemic, the epidemic can be controlled using the development policy. The common traditional mathematical differential equations and population prediction models have limitations for time series population prediction, and even have large estimation errors. To address this issue, we propose an improved method for predicting confirmed cases based on LSTM (Long-Short Term Memory) neural network. This work compared the deviation between the experimental results of the improved LSTM prediction model and the digital prediction models (such as Logistic and Hill equations) with the real data as reference. And this work uses the goodness of fitting to evaluate the fitting effect of the improvement. Experiments show that the proposed approach has a smaller prediction deviation and a better fitting effect. Compared with the previous forecasting methods, the contributions of our proposed improvement methods are mainly in the following aspects: 1) we have fully considered the spatiotemporal characteristics of the data, rather than single standardized data; 2) the improved parameter settings and evaluation indicators are more accurate for fitting and forecasting. 3) we consider the impact of the epidemic stage and conduct reasonable data processing for different stage.

preprint2020arXiv

Attention-Aware Answers of the Crowd

Crowdsourcing is a relatively economic and efficient solution to collect annotations from the crowd through online platforms. Answers collected from workers with different expertise may be noisy and unreliable, and the quality of annotated data needs to be further maintained. Various solutions have been attempted to obtain high-quality annotations. However, they all assume that workers' label quality is stable over time (always at the same level whenever they conduct the tasks). In practice, workers' attention level changes over time, and the ignorance of which can affect the reliability of the annotations. In this paper, we focus on a novel and realistic crowdsourcing scenario involving attention-aware annotations. We propose a new probabilistic model that takes into account workers' attention to estimate the label quality. Expectation propagation is adopted for efficient Bayesian inference of our model, and a generalized Expectation Maximization algorithm is derived to estimate both the ground truth of all tasks and the label-quality of each individual crowd worker with attention. In addition, the number of tasks best suited for a worker is estimated according to changes in attention. Experiments against related methods on three real-world and one semi-simulated datasets demonstrate that our method quantifies the relationship between workers' attention and label-quality on the given tasks, and improves the aggregated labels.

preprint2020arXiv

Automated Radiological Report Generation For Chest X-Rays With Weakly-Supervised End-to-End Deep Learning

The chest X-Ray (CXR) is the one of the most common clinical exam used to diagnose thoracic diseases and abnormalities. The volume of CXR scans generated daily in hospitals is huge. Therefore, an automated diagnosis system able to save the effort of doctors is of great value. At present, the applications of artificial intelligence in CXR diagnosis usually use pattern recognition to classify the scans. However, such methods rely on labeled databases, which are costly and usually have large error rates. In this work, we built a database containing more than 12,000 CXR scans and radiological reports, and developed a model based on deep convolutional neural network and recurrent network with attention mechanism. The model learns features from the CXR scans and the associated raw radiological reports directly; no additional labeling of the scans are needed. The model provides automated recognition of given scans and generation of reports. The quality of the generated reports was evaluated with both the CIDEr scores and by radiologists as well. The CIDEr scores are found to be around 5.8 on average for the testing dataset. Further blind evaluation suggested a comparable performance against human radiologist.

preprint2020arXiv

Bi-level Actor-Critic for Multi-agent Coordination

Coordination is one of the essential problems in multi-agent systems. Typically multi-agent reinforcement learning (MARL) methods treat agents equally and the goal is to solve the Markov game to an arbitrary Nash equilibrium (NE) when multiple equilibra exist, thus lacking a solution for NE selection. In this paper, we treat agents \emph{unequally} and consider Stackelberg equilibrium as a potentially better convergence point than Nash equilibrium in terms of Pareto superiority, especially in cooperative environments. Under Markov games, we formally define the bi-level reinforcement learning problem in finding Stackelberg equilibrium. We propose a novel bi-level actor-critic learning method that allows agents to have different knowledge base (thus intelligent), while their actions still can be executed simultaneously and distributedly. The convergence proof is given, while the resulting learning algorithm is tested against the state of the arts. We found that the proposed bi-level actor-critic algorithm successfully converged to the Stackelberg equilibria in matrix games and find an asymmetric solution in a highway merge environment.

preprint2020arXiv

Bidirectional Loss Function for Label Enhancement and Distribution Learning

Label distribution learning (LDL) is an interpretable and general learning paradigm that has been applied in many real-world applications. In contrast to the simple logical vector in single-label learning (SLL) and multi-label learning (MLL), LDL assigns labels with a description degree to each instance. In practice, two challenges exist in LDL, namely, how to address the dimensional gap problem during the learning process of LDL and how to exactly recover label distributions from existing logical labels, i.e., Label Enhancement (LE). For most existing LDL and LE algorithms, the fact that the dimension of the input matrix is much higher than that of the output one is alway ignored and it typically leads to the dimensional reduction owing to the unidirectional projection. The valuable information hidden in the feature space is lost during the mapping process. To this end, this study considers bidirectional projections function which can be applied in LE and LDL problems simultaneously. More specifically, this novel loss function not only considers the mapping errors generated from the projection of the input space into the output one but also accounts for the reconstruction errors generated from the projection of the output space back to the input one. This loss function aims to potentially reconstruct the input data from the output data. Therefore, it is expected to obtain more accurate results. Finally, experiments on several real-world datasets are carried out to demonstrate the superiority of the proposed method for both LE and LDL.

preprint2020arXiv

Bilevel Learning Model Towards Industrial Scheduling

Automatic industrial scheduling, aiming at optimizing the sequence of jobs over limited resources, is widely needed in manufacturing industries. However, existing scheduling systems heavily rely on heuristic algorithms, which either generate ineffective solutions or compute inefficiently when job scale increases. Thus, it is of great importance to develop new large-scale algorithms that are not only efficient and effective, but also capable of satisfying complex constraints in practice. In this paper, we propose a Bilevel Deep reinforcement learning Scheduler, \textit{BDS}, in which the higher level is responsible for exploring an initial global sequence, whereas the lower level is aiming at exploitation for partial sequence refinements, and the two levels are connected by a sliding-window sampling mechanism. In the implementation, a Double Deep Q Network (DDQN) is used in the upper level and Graph Pointer Network (GPN) lies within the lower level. After the theoretical guarantee for the convergence of BDS, we evaluate it in an industrial automatic warehouse scenario, with job number up to $5000$ in each production line. It is shown that our proposed BDS significantly outperforms two most used heuristics, three strong deep networks, and another bilevel baseline approach. In particular, compared with the most used greedy-based heuristic algorithm in real world which takes nearly an hour, our BDS can decrease the makespan by 27.5\%, 28.6\% and 22.1\% for 3 largest datasets respectively, with computational time less than 200 seconds.

preprint2020arXiv

Bohr's phenomenon for the classes of Quasi-subordination and $K$-quasiregular harmonic mappings

In this paper, we investigate the Bohr radius for $K$-quasiregular sense-preserving harmonic mappings $f=h+\overline{g}$ in the unit disk $\mathbb{D}$ such that the translated analytic part $h(z)-h(0)$ is quasi-subordinate to some analytic function. The main aim of this article is to extend and to establish sharp versions of four recent theorems by Liu and Ponnusamy \cite{LP2019} and, in particular, we settle affirmatively the two conjectures proposed by them. Furthermore, we establish two refined versions of Bohr's inequalities and determine the Bohr radius for the derivatives of analytic functions associated with quasi-subordination.

preprint2020arXiv

Boosted EfficientNet: Detection of Lymph Node Metastases in Breast Cancer Using Convolutional Neural Network

In recent years, advances in the development of whole-slide images have laid a foundation for the utilization of digital images in pathology. With the assistance of computer images analysis that automatically identifies tissue or cell types, they have greatly improved the histopathologic interpretation and diagnosis accuracy. In this paper, the Convolutional Neutral Network (CNN) has been adapted to predict and classify lymph node metastasis in breast cancer. Unlike traditional image cropping methods that are only suitable for large resolution images, we propose a novel data augmentation method named Random Center Cropping (RCC) to facilitate small resolution images. RCC enriches the datasets while retaining the image resolution and the center area of images. In addition, we reduce the downsampling scale of the network to further facilitate small resolution images better. Moreover, Attention and Feature Fusion (FF) mechanisms are employed to improve the semantic information of images. Experiments demonstrate that our methods boost performances of basic CNN architectures. And the best-performed method achieves an accuracy of 97.96% and an AUC of 99.68% on RPCam datasets, respectively.

preprint2020arXiv

Compositional ADAM: An Adaptive Compositional Solver

In this paper, we present C-ADAM, the first adaptive solver for compositional problems involving a non-linear functional nesting of expected values. We proof that C-ADAM converges to a stationary point in $\mathcal{O}(δ^{-2.25})$ with $δ$ being a precision parameter. Moreover, we demonstrate the importance of our results by bridging, for the first time, model-agnostic meta-learning (MAML) and compositional optimisation showing fastest known rates for deep network adaptation to-date. Finally, we validate our findings in a set of experiments from portfolio optimisation and meta-learning. Our results manifest significant sample complexity reductions compared to both standard and compositional solvers.

preprint2020arXiv

Computational prediction of RNA tertiary structures using machine learning methods

RNAs play crucial and versatile roles in biological processes. Computational prediction approaches can help to understand RNA structures and their stabilizing factors, thus providing information on their functions, and facilitating the design of new RNAs. Machine learning (ML) techniques have made tremendous progress in many fields in the past few years. Although their usage in protein-related fields has a long history, the use of ML methods in predicting RNA tertiary structures is new and rare. Here, we review the recent advances of using ML methods on RNA structure predictions and discuss the advantages and limitation, the difficulties and potentials of these approaches when applied in the field.

preprint2020arXiv

Consistent and Complementary Graph Regularized Multi-view Subspace Clustering

This study investigates the problem of multi-view clustering, where multiple views contain consistent information and each view also includes complementary information. Exploration of all information is crucial for good multi-view clustering. However, most traditional methods blindly or crudely combine multiple views for clustering and are unable to fully exploit the valuable information. Therefore, we propose a method that involves consistent and complementary graph-regularized multi-view subspace clustering (GRMSC), which simultaneously integrates a consistent graph regularizer with a complementary graph regularizer into the objective function. In particular, the consistent graph regularizer learns the intrinsic affinity relationship of data points shared by all views. The complementary graph regularizer investigates the specific information of multiple views. It is noteworthy that the consistent and complementary regularizers are formulated by two different graphs constructed from the first-order proximity and second-order proximity of multiple views, respectively. The objective function is optimized by the augmented Lagrangian multiplier method in order to achieve multi-view clustering. Extensive experiments on six benchmark datasets serve to validate the effectiveness of the proposed method over other state-of-the-art multi-view clustering methods.

preprint2020arXiv

ControlVAE: Controllable Variational Autoencoder

Variational Autoencoders (VAE) and their variants have been widely used in a variety of applications, such as dialog generation, image generation and disentangled representation learning. However, the existing VAE models have some limitations in different applications. For example, a VAE easily suffers from KL vanishing in language modeling and low reconstruction quality for disentangling. To address these issues, we propose a novel controllable variational autoencoder framework, ControlVAE, that combines a controller, inspired by automatic control theory, with the basic VAE to improve the performance of resulting generative models. Specifically, we design a new non-linear PI controller, a variant of the proportional-integral-derivative (PID) control, to automatically tune the hyperparameter (weight) added in the VAE objective using the output KL-divergence as feedback during model training. The framework is evaluated using three applications; namely, language modeling, disentangled representation learning, and image generation. The results show that ControlVAE can achieve better disentangling and reconstruction quality than the existing methods. For language modelling, it not only averts the KL-vanishing, but also improves the diversity of generated text. Finally, we also demonstrate that ControlVAE improves the reconstruction quality of generated images compared to the original VAE.

preprint2020arXiv

Curved Buildings Reconstruction from Airborne LiDAR Data by Matching and Deforming Geometric Primitives

Airborne LiDAR (Light Detection and Ranging) data is widely applied in building reconstruction, with studies reporting success in typical buildings. However, the reconstruction of curved buildings remains an open research problem. To this end, we propose a new framework for curved building reconstruction via assembling and deforming geometric primitives. The input LiDAR point cloud are first converted into contours where individual buildings are identified. After recognizing geometric units (primitives) from building contours, we get initial models by matching basic geometric primitives to these primitives. To polish assembly models, we employ a warping field for model refinements. Specifically, an embedded deformation (ED) graph is constructed via downsampling the initial model. Then, the point-to-model displacements are minimized by adjusting node parameters in the ED graph based on our objective function. The presented framework is validated on several highly curved buildings collected by various LiDAR in different cities. The experimental results, as well as accuracy comparison, demonstrate the advantage and effectiveness of our method. {The new insight attributes to an efficient reconstruction manner.} Moreover, we prove that the primitive-based framework significantly reduces the data storage to 10-20 percent of classical mesh models.

preprint2020arXiv

Deep Feature-preserving Normal Estimation for Point Cloud Filtering

Point cloud filtering, the main bottleneck of which is removing noise (outliers) while preserving geometric features, is a fundamental problem in 3D field. The two-step schemes involving normal estimation and position update have been shown to produce promising results. Nevertheless, the current normal estimation methods including optimization ones and deep learning ones, often either have limited automation or cannot preserve sharp features. In this paper, we propose a novel feature-preserving normal estimation method for point cloud filtering with preserving geometric features. It is a learning method and thus achieves automatic prediction for normals. For training phase, we first generate patch based samples which are then fed to a classification network to classify feature and non-feature points. We finally train the samples of feature and non-feature points separately, to achieve decent results. Regarding testing, given a noisy point cloud, its normals can be automatically estimated. For further point cloud filtering, we iterate the above normal estimation and a current position update algorithm for a few times. Various experiments demonstrate that our method outperforms state-of-the-art normal estimation methods and point cloud filtering techniques, in terms of both quality and quantity.

preprint2020arXiv

Detecting Suspected Epidemic Cases Using Trajectory Big Data

Emerging infectious diseases are existential threats to human health and global stability. The recent outbreaks of the novel coronavirus COVID-19 have rapidly formed a global pandemic, causing hundreds of thousands of infections and huge economic loss. The WHO declares that more precise measures to track, detect and isolate infected people are among the most effective means to quickly contain the outbreak. Based on trajectory provided by the big data and the mean field theory, we establish an aggregated risk mean field that contains information of all risk-spreading particles by proposing a spatio-temporal model named HiRES risk map. It has dynamic fine spatial resolution and high computation efficiency enabling fast update. We then propose an objective individual epidemic risk scoring model named HiRES-p based on HiRES risk maps, and use it to develop statistical inference and machine learning methods for detecting suspected epidemic-infected individuals. We conduct numerical experiments by applying the proposed methods to study the early outbreak of COVID-19 in China. Results show that the HiRES risk map has strong ability in capturing global trend and local variability of the epidemic risk, thus can be applied to monitor epidemic risk at country, province, city and community levels, as well as at specific high-risk locations such as hospital and station. HiRES-p score seems to be an effective measurement of personal epidemic risk. The accuracy of both detecting methods are above 90\% when the population infection rate is under 20\%, which indicates great application potential in epidemic risk prevention and control practice.

preprint2020arXiv

Dynamic Reconstruction of Deformable Soft-tissue with Stereo Scope in Minimal Invasive Surgery

In minimal invasive surgery, it is important to rebuild and visualize the latest deformed shape of soft-tissue surfaces to mitigate tissue damages. This paper proposes an innovative Simultaneous Localization and Mapping (SLAM) algorithm for deformable dense reconstruction of surfaces using a sequence of images from a stereoscope. We introduce a warping field based on the Embedded Deformation (ED) nodes with 3D shapes recovered from consecutive pairs of stereo images. The warping field is estimated by deforming the last updated model to the current live model. Our SLAM system can: (1) Incrementally build a live model by progressively fusing new observations with vivid accurate texture. (2) Estimate the deformed shape of unobserved region with the principle As-Rigid-As-Possible. (3) Show the consecutive shape of models. (4) Estimate the current relative pose between the soft-tissue and the scope. In-vivo experiments with publicly available datasets demonstrate that the 3D models can be incrementally built for different soft-tissues with different deformations from sequences of stereo images obtained by laparoscopes. Results show the potential clinical application of our SLAM system for providing surgeon useful shape and texture information in minimal invasive surgery.

preprint2020arXiv

Fair Division through Information Withholding

Envy-freeness up to one good (EF1) is a well-studied fairness notion for indivisible goods that addresses pairwise envy by the removal of at most one good. In the worst case, each pair of agents might require the (hypothetical) removal of a different good, resulting in a weak aggregate guarantee. We study allocations that are nearly envy-free in aggregate, and define a novel fairness notion based on information withholding. Under this notion, an agent can withhold (or hide) some of the goods in its bundle and reveal the remaining goods to the other agents. We observe that in practice, envy-freeness can be achieved by withholding only a small number of goods overall. We show that finding allocations that withhold an optimal number of goods is computationally hard even for highly restricted classes of valuations. In contrast to the worst-case results, our experiments on synthetic and real-world preference data show that existing algorithms for finding EF1 allocations withhold close-to-optimal number of goods.

preprint2020arXiv

Feasibility and physics potential of detecting $^8$B solar neutrinos at JUNO

The Jiangmen Underground Neutrino Observatory~(JUNO) features a 20~kt multi-purpose underground liquid scintillator sphere as its main detector. Some of JUNO's features make it an excellent experiment for $^8$B solar neutrino measurements, such as its low-energy threshold, its high energy resolution compared to water Cherenkov detectors, and its much large target mass compared to previous liquid scintillator detectors. In this paper we present a comprehensive assessment of JUNO's potential for detecting $^8$B solar neutrinos via the neutrino-electron elastic scattering process. A reduced 2~MeV threshold on the recoil electron energy is found to be achievable assuming the intrinsic radioactive background $^{238}$U and $^{232}$Th in the liquid scintillator can be controlled to 10$^{-17}$~g/g. With ten years of data taking, about 60,000 signal and 30,000 background events are expected. This large sample will enable an examination of the distortion of the recoil electron spectrum that is dominated by the neutrino flavor transformation in the dense solar matter, which will shed new light on the tension between the measured electron spectra and the predictions of the standard three-flavor neutrino oscillation framework. If $Δm^{2}_{21}=4.8\times10^{-5}~(7.5\times10^{-5})$~eV$^{2}$, JUNO can provide evidence of neutrino oscillation in the Earth at the about 3$σ$~(2$σ$) level by measuring the non-zero signal rate variation with respect to the solar zenith angle. Moveover, JUNO can simultaneously measure $Δm^2_{21}$ using $^8$B solar neutrinos to a precision of 20\% or better depending on the central value and to sub-percent precision using reactor antineutrinos. A comparison of these two measurements from the same detector will help elucidate the current tension between the value of $Δm^2_{21}$ reported by solar neutrino experiments and the KamLAND experiment.

preprint2020arXiv

InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling

Real-time 3D object detection is crucial for autonomous cars. Achieving promising performance with high efficiency, voxel-based approaches have received considerable attention. However, previous methods model the input space with features extracted from equally divided sub-regions without considering that point cloud is generally non-uniformly distributed over the space. To address this issue, we propose a novel 3D object detection framework with dynamic information modeling. The proposed framework is designed in a coarse-to-fine manner. Coarse predictions are generated in the first stage via a voxel-based region proposal network. We introduce InfoFocus, which improves the coarse detections by adaptively refining features guided by the information of point cloud density. Experiments are conducted on the large-scale nuScenes 3D detection benchmark. Results show that our framework achieves the state-of-the-art performance with 31 FPS and improves our baseline significantly by 9.0% mAP on the nuScenes test set.

preprint2020arXiv

Learning from a Lightweight Teacher for Efficient Knowledge Distillation

Knowledge Distillation (KD) is an effective framework for compressing deep learning models, realized by a student-teacher paradigm requiring small student networks to mimic the soft target generated by well-trained teachers. However, the teachers are commonly assumed to be complex and need to be trained on the same datasets as students. This leads to a time-consuming training process. The recent study shows vanilla KD plays a similar role as label smoothing and develops teacher-free KD, being efficient and mitigating the issue of learning from heavy teachers. But because teacher-free KD relies on manually-crafted output distributions kept the same for all data instances belonging to the same class, its flexibility and performance are relatively limited. To address the above issues, this paper proposes en efficient knowledge distillation learning framework LW-KD, short for lightweight knowledge distillation. It firstly trains a lightweight teacher network on a synthesized simple dataset, with an adjustable class number equal to that of a target dataset. The teacher then generates soft target whereby an enhanced KD loss could guide student learning, which is a combination of KD loss and adversarial loss for making student output indistinguishable from the output of the teacher. Experiments on several public datasets with different modalities demonstrate LWKD is effective and efficient, showing the rationality of its main design principles.

preprint2020arXiv

Learning Structured Communication for Multi-agent Reinforcement Learning

This work explores the large-scale multi-agent communication mechanism under a multi-agent reinforcement learning (MARL) setting. We summarize the general categories of topology for communication structures in MARL literature, which are often manually specified. Then we propose a novel framework termed as Learning Structured Communication (LSC) by using a more flexible and efficient communication topology. Our framework allows for adaptive agent grouping to form different hierarchical formations over episodes, which is generated by an auxiliary task combined with a hierarchical routing protocol. Given each formed topology, a hierarchical graph neural network is learned to enable effective message information generation and propagation among inter- and intra-group communications. In contrast to existing communication mechanisms, our method has an explicit while learnable design for hierarchical communication. Experiments on challenging tasks show the proposed LSC enjoys high communication efficiency, scalability, and global cooperation capability.

preprint2020arXiv

Learning to Infer User Hidden States for Online Sequential Advertising

To drive purchase in online advertising, it is of the advertiser's great interest to optimize the sequential advertising strategy whose performance and interpretability are both important. The lack of interpretability in existing deep reinforcement learning methods makes it not easy to understand, diagnose and further optimize the strategy. In this paper, we propose our Deep Intents Sequential Advertising (DISA) method to address these issues. The key part of interpretability is to understand a consumer's purchase intent which is, however, unobservable (called hidden states). In this paper, we model this intention as a latent variable and formulate the problem as a Partially Observable Markov Decision Process (POMDP) where the underlying intents are inferred based on the observable behaviors. Large-scale industrial offline and online experiments demonstrate our method's superior performance over several baselines. The inferred hidden states are analyzed, and the results prove the rationality of our inference.

preprint2020arXiv

Learning to Model Opponent Learning

Multi-Agent Reinforcement Learning (MARL) considers settings in which a set of coexisting agents interact with one another and their environment. The adaptation and learning of other agents induces non-stationarity in the environment dynamics. This poses a great challenge for value function-based algorithms whose convergence usually relies on the assumption of a stationary environment. Policy search algorithms also struggle in multi-agent settings as the partial observability resulting from an opponent's actions not being known introduces high variance to policy training. Modelling an agent's opponent(s) is often pursued as a means of resolving the issues arising from the coexistence of learning opponents. An opponent model provides an agent with some ability to reason about other agents to aid its own decision making. Most prior works learn an opponent model by assuming the opponent is employing a stationary policy or switching between a set of stationary policies. Such an approach can reduce the variance of training signals for policy search algorithms. However, in the multi-agent setting, agents have an incentive to continually adapt and learn. This means that the assumptions concerning opponent stationarity are unrealistic. In this work, we develop a novel approach to modelling an opponent's learning dynamics which we term Learning to Model Opponent Learning (LeMOL). We show our structured opponent model is more accurate and stable than naive behaviour cloning baselines. We further show that opponent modelling can improve the performance of algorithmic agents in multi-agent settings.

preprint2020arXiv

Mixup-breakdown: a consistency training method for improving generalization of speech separation models

Deep-learning based speech separation models confront poor generalization problem that even the state-of-the-art models could abruptly fail when evaluating them in mismatch conditions. To address this problem, we propose an easy-to-implement yet effective consistency based semi-supervised learning (SSL) approach, namely Mixup-Breakdown training (MBT). It learns a teacher model to "breakdown" unlabeled inputs, and the estimated separations are interpolated to produce more useful pseudo "mixup" input-output pairs, on which the consistency regularization could apply for learning a student model. In our experiment, we evaluate MBT under various conditions with ascending degrees of mismatch, including unseen interfering speech, noise, and music, and compare MBT's generalization capability against state-of-the-art supervised learning and SSL approaches. The result indicates that MBT significantly outperforms several strong baselines with up to 13.77% relative SI-SNRi improvement. Moreover, MBT only adds negligible computational overhead to standard training schemes.

preprint2020arXiv

MLCVNet: Multi-Level Context VoteNet for 3D Object Detection

In this paper, we address the 3D object detection task by capturing multi-level contextual information with the self-attention mechanism and multi-scale feature fusion. Most existing 3D object detection methods recognize objects individually, without giving any consideration on contextual information between these objects. Comparatively, we propose Multi-Level Context VoteNet (MLCVNet) to recognize 3D objects correlatively, building on the state-of-the-art VoteNet. We introduce three context modules into the voting and classifying stages of VoteNet to encode contextual information at different levels. Specifically, a Patch-to-Patch Context (PPC) module is employed to capture contextual information between the point patches, before voting for their corresponding object centroid points. Subsequently, an Object-to-Object Context (OOC) module is incorporated before the proposal and classification stage, to capture the contextual information between object candidates. Finally, a Global Scene Context (GSC) module is designed to learn the global scene context. We demonstrate these by capturing contextual information at patch, object and scene levels. Our method is an effective way to promote detection accuracy, achieving new state-of-the-art detection performance on challenging 3D object detection datasets, i.e., SUN RGBD and ScanNet. We also release our code at https://github.com/NUAAXQ/MLCVNet.

preprint2020arXiv

Modelling Bounded Rationality in Multi-Agent Interactions by Generalized Recursive Reasoning

Though limited in real-world decision making, most multi-agent reinforcement learning (MARL) models assume perfectly rational agents -- a property hardly met due to individual's cognitive limitation and/or the tractability of the decision problem. In this paper, we introduce generalized recursive reasoning (GR2) as a novel framework to model agents with different \emph{hierarchical} levels of rationality; our framework enables agents to exhibit varying levels of "thinking" ability thereby allowing higher-level agents to best respond to various less sophisticated learners. We contribute both theoretically and empirically. On the theory side, we devise the hierarchical framework of GR2 through probabilistic graphical models and prove the existence of a perfect Bayesian equilibrium. Within the GR2, we propose a practical actor-critic solver, and demonstrate its convergent property to a stationary point in two-player games through Lyapunov analysis. On the empirical side, we validate our findings on a variety of MARL benchmarks. Precisely, we first illustrate the hierarchical thinking process on the Keynes Beauty Contest, and then demonstrate significant improvements compared to state-of-the-art opponent modeling baselines on the normal-form games and the cooperative navigation benchmark.

preprint2020arXiv

Multi-Agent Determinantal Q-Learning

Centralized training with decentralized execution has become an important paradigm in multi-agent learning. Though practical, current methods rely on restrictive assumptions to decompose the centralized value function across agents for execution. In this paper, we eliminate this restriction by proposing multi-agent determinantal Q-learning. Our method is established on Q-DPP, an extension of determinantal point process (DPP) with partition-matroid constraint to multi-agent setting. Q-DPP promotes agents to acquire diverse behavioral models; this allows a natural factorization of the joint Q-functions with no need for \emph{a priori} structural constraints on the value function or special network architectures. We demonstrate that Q-DPP generalizes major solutions including VDN, QMIX, and QTRAN on decentralizable cooperative tasks. To efficiently draw samples from Q-DPP, we adopt an existing sample-by-projection sampler with theoretical approximation guarantee. The sampler also benefits exploration by coordinating agents to cover orthogonal directions in the state space during multi-agent training. We evaluate our algorithm on various cooperative benchmarks; its effectiveness has been demonstrated when compared with the state-of-the-art.

preprint2020arXiv

Multi-Agent Interactions Modeling with Correlated Policies

In multi-agent systems, complex interacting behaviors arise due to the high correlations among agents. However, previous work on modeling multi-agent interactions from demonstrations is primarily constrained by assuming the independence among policies and their reward structures. In this paper, we cast the multi-agent interactions modeling problem into a multi-agent imitation learning framework with explicit modeling of correlated policies by approximating opponents' policies, which can recover agents' policies that can regenerate similar interactions. Consequently, we develop a Decentralized Adversarial Imitation Learning algorithm with Correlated policies (CoDAIL), which allows for decentralized training and execution. Various experiments demonstrate that CoDAIL can better regenerate complex interactions close to the demonstrators and outperforms state-of-the-art multi-agent imitation learning methods. Our code is available at \url{https://github.com/apexrl/CoDAIL}.

preprint2020arXiv

Multi-modal Summarization for Video-containing Documents

Summarization of multimedia data becomes increasingly significant as it is the basis for many real-world applications, such as question answering, Web search, and so forth. Most existing multi-modal summarization works however have used visual complementary features extracted from images rather than videos, thereby losing abundant information. Hence, we propose a novel multi-modal summarization task to summarize from a document and its associated video. In this work, we also build a baseline general model with effective strategies, i.e., bi-hop attention and improved late fusion mechanisms to bridge the gap between different modalities, and a bi-stream summarization strategy to employ text and video summarization simultaneously. Comprehensive experiments show that the proposed model is beneficial for multi-modal summarization and superior to existing methods. Moreover, we collect a novel dataset and it provides a new resource for future study that results from documents and videos.

preprint2020arXiv

Neighborhood Cognition Consistent Multi-Agent Reinforcement Learning

Social psychology and real experiences show that cognitive consistency plays an important role to keep human society in order: if people have a more consistent cognition about their environments, they are more likely to achieve better cooperation. Meanwhile, only cognitive consistency within a neighborhood matters because humans only interact directly with their neighbors. Inspired by these observations, we take the first step to introduce \emph{neighborhood cognitive consistency} (NCC) into multi-agent reinforcement learning (MARL). Our NCC design is quite general and can be easily combined with existing MARL methods. As examples, we propose neighborhood cognition consistent deep Q-learning and Actor-Critic to facilitate large-scale multi-agent cooperations. Extensive experiments on several challenging tasks (i.e., packet routing, wifi configuration, and Google football player control) justify the superior performance of our methods compared with state-of-the-art MARL approaches.

preprint2020arXiv

Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Search

In this paper, we introduce a new reinforcement learning (RL) based neural architecture search (NAS) methodology for effective and efficient generative adversarial network (GAN) architecture search. The key idea is to formulate the GAN architecture search problem as a Markov decision process (MDP) for smoother architecture sampling, which enables a more effective RL-based search algorithm by targeting the potential global optimal architecture. To improve efficiency, we exploit an off-policy GAN architecture search algorithm that makes efficient use of the samples generated by previous policies. Evaluation on two standard benchmark datasets (i.e., CIFAR-10 and STL-10) demonstrates that the proposed method is able to discover highly competitive architectures for generally better image generation results with a considerably reduced computational burden: 7 GPU hours. Our code is available at https://github.com/Yuantian013/E2GAN.

preprint2020arXiv

Partial Multi-label Learning with Label and Feature Collaboration

Partial multi-label learning (PML) models the scenario where each training instance is annotated with a set of candidate labels, and only some of the labels are relevant. The PML problem is practical in real-world scenarios, as it is difficult and even impossible to obtain precisely labeled samples. Several PML solutions have been proposed to combat with the prone misled by the irrelevant labels concealed in the candidate labels, but they generally focus on the smoothness assumption in feature space or low-rank assumption in label space, while ignore the negative information between features and labels. Specifically, if two instances have largely overlapped candidate labels, irrespective of their feature similarity, their ground-truth labels should be similar; while if they are dissimilar in the feature and candidate label space, their ground-truth labels should be dissimilar with each other. To achieve a credible predictor on PML data, we propose a novel approach called PML-LFC (Partial Multi-label Learning with Label and Feature Collaboration). PML-LFC estimates the confidence values of relevant labels for each instance using the similarity from both the label and feature spaces, and trains the desired predictor with the estimated confidence values. PML-LFC achieves the predictor and the latent label matrix in a reciprocal reinforce manner by a unified model, and develops an alternative optimization procedure to optimize them. Extensive empirical study on both synthetic and real-world datasets demonstrates the superiority of PML-LFC.

preprint2020arXiv

Phase transition and entropy force between two horizons in (n+2)-dimensional de Sitter space

In this paper, the effect of the space-time dimension on effective thermodynamic quantities in (n+2)-dimensional Reissoner-Nordstrom-de Sitter space has been stud ied. Based on derived effective thermodynamic quantities, conditions for the phase transition are obtained. The result shows that the accelerating cosmic expansion can be attained by the entropy force arisen from the interaction between horizons of black holes and our universe, which provides a possible way to explain the physical mechanism for the accelerating cosmic expansion.

preprint2020arXiv

Resisting Crowd Occlusion and Hard Negatives for Pedestrian Detection in the Wild

Pedestrian detection has been heavily studied in the last decade due to its wide application. Despite incremental progress, crowd occlusion and hard negatives are still challenging current state-of-the-art pedestrian detectors. In this paper, we offer two approaches based on the general region-based detection framework to tackle these challenges. Specifically, to address the occlusion, we design a novel coulomb loss as a regulator on bounding box regression, in which proposals are attracted by their target instance and repelled by the adjacent non-target instances. For hard negatives, we propose an efficient semantic-driven strategy for selecting anchor locations, which can sample informative negative examples at training phase for classification refinement. It is worth noting that these methods can also be applied to general object detection domain, and trainable in an end-to-end manner. We achieves consistently high performance on the Caltech-USA and CityPersons benchmarks.

preprint2020arXiv

Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation and Diagnosis for COVID-19

(This paper was submitted as an invited paper to IEEE Reviews in Biomedical Engineering on April 6, 2020.) The pandemic of coronavirus disease 2019 (COVID-19) is spreading all over the world. Medical imaging such as X-ray and computed tomography (CT) plays an essential role in the global fight against COVID-19, whereas the recently emerging artificial intelligence (AI) technologies further strengthen the power of the imaging tools and help medical specialists. We hereby review the rapid responses in the community of medical imaging (empowered by AI) toward COVID-19. For example, AI-empowered image acquisition can significantly help automate the scanning procedure and also reshape the workflow with minimal contact to patients, providing the best protection to the imaging technicians. Also, AI can improve work efficiency by accurate delination of infections in X-ray and CT images, facilitating subsequent quantification. Moreover, the computer-aided platforms help radiologists make clinical decisions, i.e., for disease diagnosis, tracking, and prognosis. In this review paper, we thus cover the entire pipeline of medical imaging and analysis techniques involved with COVID-19, including image acquisition, segmentation, diagnosis, and follow-up. We particularly focus on the integration of AI with X-ray and CT, both of which are widely used in the frontline hospitals, in order to depict the latest progress of medical imaging and radiology fighting against COVID-19.

preprint2020arXiv

SAMBA: Safe Model-Based & Active Reinforcement Learning

In this paper, we propose SAMBA, a novel framework for safe reinforcement learning that combines aspects from probabilistic modelling, information theory, and statistics. Our method builds upon PILCO to enable active exploration using novel(semi-)metrics for out-of-sample Gaussian process evaluation optimised through a multi-objective problem that supports conditional-value-at-risk constraints. We evaluate our algorithm on a variety of safe dynamical system benchmarks involving both low and high-dimensional state representations. Our results show orders of magnitude reductions in samples and violations compared to state-of-the-art methods. Lastly, we provide intuition as to the effectiveness of the framework by a detailed analysis of our active metrics and safety constraints.

preprint2020arXiv

Semi-Siamese Training for Shallow Face Learning

Most existing public face datasets, such as MS-Celeb-1M and VGGFace2, provide abundant information in both breadth (large number of IDs) and depth (sufficient number of samples) for training. However, in many real-world scenarios of face recognition, the training dataset is limited in depth, i.e. only two face images are available for each ID. $\textit{We define this situation as Shallow Face Learning, and find it problematic with existing training methods.}$ Unlike deep face data, the shallow face data lacks intra-class diversity. As such, it can lead to collapse of feature dimension and consequently the learned network can easily suffer from degeneration and over-fitting in the collapsed dimension. In this paper, we aim to address the problem by introducing a novel training method named Semi-Siamese Training (SST). A pair of Semi-Siamese networks constitute the forward propagation structure, and the training loss is computed with an updating gallery queue, conducting effective optimization on shallow training data. Our method is developed without extra-dependency, thus can be flexibly integrated with the existing loss functions and network architectures. Extensive experiments on various benchmarks of face recognition show the proposed method significantly improves the training, not only in shallow face learning, but also for conventional deep face data.

preprint2020arXiv

Structural Landmarking and Interaction Modelling: on Resolution Dilemmas in Graph Classification

Graph neural networks are promising architecture for learning and inference with graph-structured data. Yet difficulties in modelling the ``parts'' and their ``interactions'' still persist in terms of graph classification, where graph-level representations are usually obtained by squeezing the whole graph into a single vector through graph pooling. From complex systems point of view, mixing all the parts of a system together can affect both model interpretability and predictive performance, because properties of a complex system arise largely from the interaction among its components. We analyze the intrinsic difficulty in graph classification under the unified concept of ``resolution dilemmas'' with learning theoretic recovery guarantees, and propose ``SLIM'', an inductive neural network model for Structural Landmarking and Interaction Modelling. It turns out, that by solving the resolution dilemmas, and leveraging explicit interacting relation between component parts of a graph to explain its complexity, SLIM is more interpretable, accurate, and offers new insight in graph representation learning.

preprint2020arXiv

TAO Conceptual Design Report: A Precision Measurement of the Reactor Antineutrino Spectrum with Sub-percent Energy Resolution

The Taishan Antineutrino Observatory (TAO, also known as JUNO-TAO) is a satellite experiment of the Jiangmen Underground Neutrino Observatory (JUNO). A ton-level liquid scintillator detector will be placed at about 30 m from a core of the Taishan Nuclear Power Plant. The reactor antineutrino spectrum will be measured with sub-percent energy resolution, to provide a reference spectrum for future reactor neutrino experiments, and to provide a benchmark measurement to test nuclear databases. A spherical acrylic vessel containing 2.8 ton gadolinium-doped liquid scintillator will be viewed by 10 m^2 Silicon Photomultipliers (SiPMs) of >50% photon detection efficiency with almost full coverage. The photoelectron yield is about 4500 per MeV, an order higher than any existing large-scale liquid scintillator detectors. The detector operates at -50 degree C to lower the dark noise of SiPMs to an acceptable level. The detector will measure about 2000 reactor antineutrinos per day, and is designed to be well shielded from cosmogenic backgrounds and ambient radioactivities to have about 10% background-to-signal ratio. The experiment is expected to start operation in 2022.

preprint2020arXiv

Time irreversibility and amplitude irreversibility measures for nonequilibrium processes

Time irreversibility, which characterizes nonequilibrium processes, can be measured based on the probabilistic differences between symmetric vectors. To simplify the quantification of time irreversibility, symmetric permutations instead of symmetric vectors have been employed in some studies. However, although effective in practical applications, this approach is conceptually incorrect. Time irreversibility should be measured based on the permutations of symmetric vectors rather than symmetric permutations, whereas symmetric permutations can instead be employed to determine the quantitative amplitude irreversibility -- a novel parameter proposed in this paper for nonequilibrium calculated by means of the probabilistic difference in amplitude fluctuations. Through theoretical and experimental analyses, we highlight the strong similarities and close associations between the time irreversibility and amplitude irreversibility measures. Our paper clarifies the connections of and the differences between the two types of permutation-based parameters for quantitative nonequilibrium, and by doing so, we bridge the concepts of amplitude irreversibility and time irreversibility and broaden the selection of quantitative tools for studying nonequilibrium processes in complex systems.

preprint2020arXiv

Toward Terabits-per-second Communications: A High-Throughput Hardware Implementation of $G_N$-Coset Codes

Recently, a parallel decoding algorithm of $G_N$-coset codes was proposed.The algorithm exploits two equivalent decoding graphs.For each graph, the inner code part, which consists of independent component codes, is decoded in parallel. The extrinsic information of the code bits is obtained and iteratively exchanged between the graphs until convergence. This algorithm enjoys a higher decoding parallelism than the previous successive cancellation algorithms, due to the avoidance of serial outer code processing. In this work, we present a hardware implementation of the parallel decoding algorithm, it can support maximum $N=16384$. We complete the decoder's physical layout in TSMC $16nm$ process and the size is $999.936μm\times 999.936μm, \,\approx 1.00mm^2$. The decoder's area efficiency and power consumption are evaluated for the cases of $N=16384,K=13225$ and $N=16384, K=14161$. Scaled to $7nm$ process, the decoder's throughput is higher than $477Gbps/mm^2$ and $533Gbps/mm^2$ with five iterations.

preprint2020arXiv

Toward Terabits-per-second Communications: Low-Complexity Parallel Decoding of $G_N$-Coset Codes

Recently, a parallel decoding framework of $G_N$-coset codes was proposed. High throughput is achieved by decoding the independent component polar codes in parallel. Various algorithms can be employed to decode these component codes, enabling a flexible throughput-performance tradeoff. In this work, we adopt SC as the component decoders to achieve the highest-throughput end of the tradeoff. The benefits over soft-output component decoders are reduced complexity and simpler (binary) interconnections among component decoders. To reduce performance degradation, we integrate an error detector and a log-likelihood ratio (LLR) generator into each component decoder. The LLR generator, specifically the damping factors therein, is designed by a genetic algorithm. This low-complexity design can achieve an area efficiency of $533Gbps/mm^2$ under 7nm technology.

preprint2020arXiv

ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language

Person search by natural language aims at retrieving a specific person in a large-scale image pool that matches the given textual descriptions. While most of the current methods treat the task as a holistic visual and textual feature matching one, we approach it from an attribute-aligning perspective that allows grounding specific attribute phrases to the corresponding visual regions. We achieve success as well as the performance boosting by a robust feature learning that the referred identity can be accurately bundled by multiple attribute visual cues. To be concrete, our Visual-Textual Attribute Alignment model (dubbed as ViTAA) learns to disentangle the feature space of a person into subspaces corresponding to attributes using a light auxiliary attribute segmentation computing branch. It then aligns these visual features with the textual attributes parsed from the sentences by using a novel contrastive learning loss. Upon that, we validate our ViTAA framework through extensive experiments on tasks of person search by natural language and by attribute-phrase queries, on which our system achieves state-of-the-art performances. Code will be publicly available upon publication.

preprint2018arXiv

Scalable Quantum Tomography with Fidelity Estimation

We propose a quantum tomography scheme for pure qudit systems which adopts random base measurements and generative learning methods, along with a built-in fidelity estimation approach to assess the reliability of the tomographic states. We prove the validity of the scheme theoretically, and we perform numerically simulated experiments on several target states including three typical quantum information states and randomly initiated states, demonstrating its efficiency and robustness. The number of replicas required by a certain convergence criterion grows in the manner of low-degree polynomial when the system scales, thus the scheme achieves high scalability that is crucial for practical quantum state tomography.

Jun 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

160 published item(s)

SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory

The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design

Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction

Constrained Language Model Policy Optimization via Risk-aware Stepwise Alignment

Multi-stages attention Breast cancer classification based on nonlinear spiking neural P neurons with autapses

SLP-Net:An efficient lightweight network for segmentation of skin lesions

A Siamese-based Verification System for Open-set Architecture Attribution of Synthetic Images

AGConv: Adaptive Graph Convolution on 3D Point Clouds

Communication under Mixed Gaussian-Impulsive Channel: An End-to-End Framework

Cross Tensor Approximation for Image and Video Completion

MANAS: Multi-Agent Neural Architecture Search

On the Complexity of Computing Markov Perfect Equilibrium in General-Sum Stochastic Games

A Comprehensive Survey on Aerial Mobile Edge Computing: Challenges, State-of-the-Art, and Future Directions

A Game-Theoretic Approach for Improving Generalization Ability of TSP Solvers

A simple normalization technique using window statistics to improve the out-of-distribution generalization on medical images

AA-Forecast: Anomaly-Aware Forecast for Extreme Events

Afterpulse measurement of JUNO 20-inch PMTs

An Architecture for the detection of GAN-generated Flood Images with Localization Capabilities

BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis

BI-GreenNet: Learning Green&#39;s functions by boundary integral network

Borsuk&#39;s partition problem in four-dimensional $\ell_{p}$ space

Branch Ranking for Efficient Mixed-Integer Programming via Offline Ranking-based Policy Learning

CandidateDrug4Cancer: An Open Molecular Graph Learning Benchmark on Drug Discovery for Cancer

Chinese Word Segmentation with Heterogeneous Graph Neural Network

Cross Attention-guided Dense Network for Images Fusion

Cross-modal Prototype Driven Network for Radiology Report Generation

Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-Speech

CSDN: Cross-modal Shape-transfer Dual-refinement Network for Point Cloud Completion

Debiased Recommendation with User Feature Balancing

Deep Algebraic Fitting for Multiple Circle Primitives Extraction from Raw Point Clouds

Demonstration of room-temperature continuous-wave operation of InGaAs/AlGaAs quantum well lasers directly grown on on-axis silicon (001)

Deterministic Identification over Channels without CSI

Differentiable and Scalable Generative Adversarial Models for Data Imputation

Efficient Policy Space Response Oracles

Empirical or Invariant Risk Minimization? A Sample Complexity Perspective

ESSumm: Extractive Speech Summarization from Untranscribed Meeting

FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis

Feature Fusion Vision Transformer for Fine-Grained Visual Categorization

GCS: Graph-based Coordination Strategy for Multi-Agent Reinforcement Learning

Generalizable Information Theoretic Causal Representation

Geometric and Learning-based Mesh Denoising: A Comprehensive Survey

HEBO Pushing The Limits of Sample-Efficient Hyperparameter Optimisation

Heterogeneous-Agent Mirror Learning: A Continuum of Solutions to Cooperative MARL

HRBF-Fusion: Accurate 3D reconstruction from RGB-D data using on-the-fly implicits

IH-GAN: A Conditional Generative Model for Implicit Surface-Based Inverse Design of Cellular Structures

Image-Goal Navigation in Complex Environments via Modular Learning

ImLoveNet: Misaligned Image-supported Registration Network for Low-overlap Point Cloud Pairs

Joint Caching and Transmission in the Mobile Edge Network: A Multi-Agent Learning Approach

Joint Optimization of Resource Allocation, Phase Shift and UAV Trajectory for Energy-Efficient RIS-Assisted UAV-Enabled MEC Systems

Joint Resource Allocation and Configuration Design for STAR-RIS-Enhanced Wireless-Powered MEC

Knowledge Graph Based Waveform Recommendation: A New Communication Waveform Design Paradigm

Learning to Identify Top Elo Ratings: A Dueling Bandits Approach

Level compatibility in Sharifi&#39;s conjecture

LIGS: Learnable Intrinsic-Reward Generation Selection for Multi-Agent Learning

LPCSE: Neural Speech Enhancement through Linear Predictive Coding

M2N: Mesh Movement Networks for PDE Solvers

Masked Gradient-Based Causal Structure Learning

Mass Testing and Characterization of 20-inch PMTs for JUNO

Modeling Temporal-Modal Entity Graph for Procedural Multimodal Machine Comprehension

Multi-Agent Constrained Policy Optimisation

Multi-Agent Feedback Enabled Neural Networks for Intelligent Communications

Multi-View Pre-Trained Model for Code Vulnerability Identification

NeoNav: Improving the Generalization of Visual Navigation via Generating Next Expected Observations

Noise-like Pulses from an All-Normal-Dispersion Fiber Laser with Weakened Spectrum Filtering

Offline Pre-trained Multi-Agent Decision Transformer: One Big Sequence Model Tackles All SMAC Tasks

On Iwasawa invariants of modular forms with reducible and non-$p$-distinguished residual Galois representations

On the Convergence of Fictitious Play: A Decomposition Approach

Perceptual Learned Source-Channel Coding for High-Fidelity Image Semantic Transmission

PGTRNet: Two-phase Weakly Supervised Object Detection with Pseudo Ground Truth Refinement

PointAttN: You Only Need Attention for Point Cloud Completion

Real-time automatic polyp detection in colonoscopy using feature enhancement module and spatiotemporal similarity correlation unit

Refine-Net: Normal Refinement Neural Network for Noisy Point Clouds

BI-GreenNet: Learning Green's functions by boundary integral network

Borsuk's partition problem in four-dimensional $\ell_{p}$ space

Level compatibility in Sharifi's conjecture

Bohr's phenomenon for the classes of Quasi-subordination and $K$-quasiregular harmonic mappings