Researcher profile

Bo Liu

Bo Liu contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author

89works

0followers

36topics

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

Cutscene Agent: An LLM Agent Framework for Automated 3D Cutscene Generation

Cutscenes are carefully choreographed cinematic sequences embedded in video games and interactive media, serving as the primary vehicle for narrative delivery, character development, and emotional engagement. Producing cutscenes is inherently complex: it demands seamless coordination across screenwriting, cinematography, character animation, voice acting, and technical direction, often requiring days to weeks of collaborative effort from multidisciplinary teams to produce minutes of polished content. In this work, we present Cutscene Agent, an LLM agent framework for automated end-to-end cutscene generation. The framework makes three contributions: (1)~a Cutscene Toolkit built on the Model Context Protocol (MCP) that establishes \emph{bidirectional} integration between LLM agents and the game engine -- agents not only invoke engine operations but continuously observe real-time scene state, enabling closed-loop generation of editable engine-native cinematic assets; (2)~a multi-agent system where a director agent orchestrates specialist subagents for animation, cinematography, and sound design, augmented by a visual reasoning feedback loop for perception-driven refinement; and (3)~CutsceneBench, a hierarchical evaluation benchmark for cutscene generation. Unlike typical tool-use benchmarks that evaluate short, isolated function calls, cutscene generation requires long-horizon, multi-step orchestration of dozens of interdependent tool invocations with strict ordering constraints -- a capability dimension that existing benchmarks do not cover. We evaluate a range of LLMs on CutsceneBench and analyze their performance across this challenging task.

preprint2025arXiv

MGML: A Plug-and-Play Meta-Guided Multi-Modal Learning Framework for Incomplete Multimodal Brain Tumor Segmentation

Leveraging multimodal information from Magnetic Resonance Imaging (MRI) plays a vital role in lesion segmentation, especially for brain tumors. However, in clinical practice, multimodal MRI data are often incomplete, making it challenging to fully utilize the available information. Therefore, maximizing the utilization of this incomplete multimodal information presents a crucial research challenge. We present a novel meta-guided multi-modal learning (MGML) framework that comprises two components: meta-parameterized adaptive modality fusion and consistency regularization module. The meta-parameterized adaptive modality fusion (Meta-AMF) enables the model to effectively integrate information from multiple modalities under varying input conditions. By generating adaptive soft-label supervision signals based on the available modalities, Meta-AMF explicitly promotes more coherent multimodal fusion. In addition, the consistency regularization module enhances segmentation performance and implicitly reinforces the robustness and generalization of the overall framework. Notably, our approach does not alter the original model architecture and can be conveniently integrated into the training pipeline for end-to-end model optimization. We conducted extensive experiments on the public BraTS2020 and BraTS2023 datasets. Compared to multiple state-of-the-art methods from previous years, our method achieved superior performance. On BraTS2020, for the average Dice scores across fifteen missing modality combinations, building upon the baseline, our method obtained scores of 87.55, 79.36, and 62.67 for the whole tumor (WT), the tumor core (TC), and the enhancing tumor (ET), respectively. We have made our source code publicly available at https://github.com/worldlikerr/MGML.

preprint2024arXiv

DeepSeek LLM: Scaling Open-Source Language Models with Longtermism

The rapid development of open-source large language models (LLMs) has been truly remarkable. However, the scaling law described in previous literature presents varying conclusions, which casts a dark cloud over scaling LLMs. We delve into the study of scaling laws and present our distinctive findings that facilitate scaling of large scale models in two commonly used open-source configurations, 7B and 67B. Guided by the scaling laws, we introduce DeepSeek LLM, a project dedicated to advancing open-source language models with a long-term perspective. To support the pre-training phase, we have developed a dataset that currently consists of 2 trillion tokens and is continuously expanding. We further conduct supervised fine-tuning (SFT) and Direct Preference Optimization (DPO) on DeepSeek LLM Base models, resulting in the creation of DeepSeek Chat models. Our evaluation results demonstrate that DeepSeek LLM 67B surpasses LLaMA-2 70B on various benchmarks, particularly in the domains of code, mathematics, and reasoning. Furthermore, open-ended evaluations reveal that DeepSeek LLM 67B Chat exhibits superior performance compared to GPT-3.5.

preprint2024arXiv

Query-Based Knowledge Sharing for Open-Vocabulary Multi-Label Classification

Identifying labels that did not appear during training, known as multi-label zero-shot learning, is a non-trivial task in computer vision. To this end, recent studies have attempted to explore the multi-modal knowledge of vision-language pre-training (VLP) models by knowledge distillation, allowing to recognize unseen labels in an open-vocabulary manner. However, experimental evidence shows that knowledge distillation is suboptimal and provides limited performance gain in unseen label prediction. In this paper, a novel query-based knowledge sharing paradigm is proposed to explore the multi-modal knowledge from the pretrained VLP model for open-vocabulary multi-label classification. Specifically, a set of learnable label-agnostic query tokens is trained to extract critical vision knowledge from the input image, and further shared across all labels, allowing them to select tokens of interest as visual clues for recognition. Besides, we propose an effective prompt pool for robust label embedding, and reformulate the standard ranking learning into a form of classification to allow the magnitude of feature vectors for matching, which both significantly benefit label recognition. Experimental results show that our framework significantly outperforms state-of-the-art methods on zero-shot task by 5.9% and 4.5% in mAP on the NUS-WIDE and Open Images, respectively.

preprint2023arXiv

Async-fork: Mitigating Query Latency Spikes Incurred by the Fork-based Snapshot Mechanism from the OS Level

In-memory key-value stores (IMKVSes) serve many online applications because of their efficiency. To support data backup, popular industrial IMKVSes periodically take a point-in-time snapshot of the in-memory data with the system call fork. However, this mechanism can result in latency spikes for queries arriving during the snapshot period because fork leads the engine into the kernel mode in which the engine is out-of-service for queries. In contrast to existing research focusing on optimizing snapshot algorithms, we optimize the fork operation to address the latency spikes problem from the operating system (OS) level, while keeping the data persistent mechanism in IMKVSes unchanged. Specifically, we first conduct an in-depth study to reveal the impact of the fork operation as well as the optimization techniques on query latency. Based on findings in the study, we propose Async-fork to offload the work of copying the page table from the engine (the parent process) to the child process as copying the page table dominates the execution time of fork. To keep data consistent between the parent and the child, we design the proactive synchronization strategy. Async-fork is implemented in the Linux kernel and deployed into the online Redis database in public clouds. Our experiment results show that compared with the default fork method in OS, Async-fork reduces the tail latency of queries arriving during the snapshot period by 81.76% on an 8GB instance and 99.84% on a 64GB instance.

preprint2023arXiv

Metric Residual Networks for Sample Efficient Goal-Conditioned Reinforcement Learning

Goal-conditioned reinforcement learning (GCRL) has a wide range of potential real-world applications, including manipulation and navigation problems in robotics. Especially in such robotics tasks, sample efficiency is of the utmost importance for GCRL since, by default, the agent is only rewarded when it reaches its goal. While several methods have been proposed to improve the sample efficiency of GCRL, one relatively under-studied approach is the design of neural architectures to support sample efficiency. In this work, we introduce a novel neural architecture for GCRL that achieves significantly better sample efficiency than the commonly-used monolithic network architecture. The key insight is that the optimal action-value function Q^*(s, a, g) must satisfy the triangle inequality in a specific sense. Furthermore, we introduce the metric residual network (MRN) that deliberately decomposes the action-value function Q(s,a,g) into the negated summation of a metric plus a residual asymmetric component. MRN provably approximates any optimal action-value function Q^*(s,a,g), thus making it a fitting neural architecture for GCRL. We conduct comprehensive experiments across 12 standard benchmark environments in GCRL. The empirical results demonstrate that MRN uniformly outperforms other state-of-the-art GCRL neural architectures in terms of sample efficiency.

preprint2023arXiv

Principal Stratification with Time-to-Event Outcomes

Post-randomization events, also known as intercurrent events, such as treatment noncompliance and censoring due to a terminal event, are common in clinical trials. Principal stratification is a framework for causal inference in the presence of intercurrent events. Despite the extensive existing literature, there lacks generally applicable and accessible methods for principal stratification analysis with time-to-event outcomes. In this paper, we specify two causal estimands for time-to-event outcomes in principal stratification. For estimation, we adopt the general strategy of latent mixture modeling and derive the corresponding likelihood function. For computational convenience, we illustrate the general strategy with a mixture of Bayesian parametric Weibull-Cox proportional model for the outcome. We utilize the Stan programming language to obtain automatic posterior sampling of the model parameters via the Hamiltonian Monte Carlo. We provide the analytical forms of the causal estimands as functions of the model parameters and an alternative numerical method when analytical forms are not available. We apply the proposed method to the ADAPTABLE trial to evaluate the causal effect of taking 81 mg versus 325 mg aspirin on the risk of major adverse cardiovascular events.

preprint2023arXiv

Self-supervised Hypergraph Representation Learning for Sociological Analysis

Modern sociology has profoundly uncovered many convincing social criteria for behavioural analysis. Unfortunately, many of them are too subjective to be measured and presented in online social networks. On the other hand, data mining techniques can better find data patterns but many of them leave behind unnatural understanding. In this paper, we propose a fundamental methodology to support the further fusion of data mining techniques and sociological behavioral criteria. Our highlights are three-fold: First, we propose an effective hypergraph awareness and a fast line graph construction framework. The hypergraph can more profoundly indicate the interactions between individuals and their environments because each edge in the hypergraph (a.k.a hyperedge) contains more than two nodes, which is perfect to describe social environments. A line graph treats each social environment as a super node with the underlying influence between different environments. In this way, we go beyond traditional pair-wise relations and explore richer patterns under various sociological criteria; Second, we propose a novel hypergraph-based neural network to learn social influence flowing from users to users, users to environments, environment to users, and environments to environments. The neural network can be learned via a task-free method, making our model very flexible to support various data mining tasks and sociological analysis; Third, we propose both qualitative and quantitive solutions to effectively evaluate the most common sociological criteria like social conformity, social equivalence, environmental evolving and social polarization. Our extensive experiments show that our framework can better support both data mining tasks for online user behaviours and sociological analysis.

preprint2022arXiv

A multi-task learning for cavitation detection and cavitation intensity recognition of valve acoustic signals

With the rapid development of smart manufacturing, data-driven machinery health management has received a growing attention. As one of the most popular methods in machinery health management, deep learning (DL) has achieved remarkable successes. However, due to the issues of limited samples and poor separability of different cavitation states of acoustic signals, which greatly hinder the eventual performance of DL modes for cavitation intensity recognition and cavitation detection. In this work, a novel multi-task learning framework for simultaneous cavitation detection and cavitation intensity recognition framework using 1-D double hierarchical residual networks (1-D DHRN) is proposed for analyzing valves acoustic signals. Firstly, a data augmentation method based on sliding window with fast Fourier transform (Swin-FFT) is developed to alleviate the small-sample issue confronted in this study. Secondly, a 1-D double hierarchical residual block (1-D DHRB) is constructed to capture sensitive features from the frequency domain acoustic signals of valve. Then, a new structure of 1-D DHRN is proposed. Finally, the devised 1-D DHRN is evaluated on two datasets of valve acoustic signals without noise (Dataset 1 and Dataset 2) and one dataset of valve acoustic signals with realistic surrounding noise (Dataset 3) provided by SAMSON AG (Frankfurt). Our method has achieved state-of-the-art results. The prediction accurcies of 1-D DHRN for cavitation intensitys recognition are as high as 93.75%, 94.31% and 100%, which indicates that 1-D DHRN outperforms other DL models and conventional methods. At the same time, the testing accuracies of 1-D DHRN for cavitation detection are as high as 97.02%, 97.64% and 100%. In addition, 1-D DHRN has also been tested for different frequencies of samples and shows excellent results for frequency of samples that mobile phones can accommodate.

preprint2022arXiv

An acoustic signal cavitation detection framework based on XGBoost with adaptive selection feature engineering

Valves are widely used in industrial and domestic pipeline systems. However, during their operation, they may suffer from the occurrence of the cavitation, which can cause loud noise, vibration and damage to the internal components of the valve. Therefore, monitoring the flow status inside valves is significantly beneficial to prevent the additional cost induced by cavitation. In this paper, a novel acoustic signal cavitation detection framework--based on XGBoost with adaptive selection feature engineering--is proposed. Firstly, a data augmentation method with non-overlapping sliding window (NOSW) is developed to solve small-sample problem involved in this study. Then, the each segmented piece of time-domain acoustic signal is transformed by fast Fourier transform (FFT) and its statistical features are extracted to be the input to the adaptive selection feature engineering (ASFE) procedure, where the adaptive feature aggregation and feature crosses are performed. Finally, with the selected features the XGBoost algorithm is trained for cavitation detection and tested on valve acoustic signal data provided by Samson AG (Frankfurt). Our method has achieved state-of-the-art results. The prediction performance on the binary classification (cavitation and no-cavitation) and the four-class classification (cavitation choked flow, constant cavitation, incipient cavitation and no-cavitation) are satisfactory and outperform the traditional XGBoost by 4.67% and 11.11% increase of the accuracy.

preprint2022arXiv

An Iterative Co-Training Transductive Framework for Zero Shot Learning

In zero-shot learning (ZSL) community, it is generally recognized that transductive learning performs better than inductive one as the unseen-class samples are also used in its training stage. How to generate pseudo labels for unseen-class samples and how to use such usually noisy pseudo labels are two critical issues in transductive learning. In this work, we introduce an iterative co-training framework which contains two different base ZSL models and an exchanging module. At each iteration, the two different ZSL models are co-trained to separately predict pseudo labels for the unseen-class samples, and the exchanging module exchanges the predicted pseudo labels, then the exchanged pseudo-labeled samples are added into the training sets for the next iteration. By such, our framework can gradually boost the ZSL performance by fully exploiting the potential complementarity of the two models' classification capabilities. In addition, our co-training framework is also applied to the generalized ZSL (GZSL), in which a semantic-guided OOD detector is proposed to pick out the most likely unseen-class samples before class-level classification to alleviate the bias problem in GZSL. Extensive experiments on three benchmarks show that our proposed methods could significantly outperform about $31$ state-of-the-art ones.

preprint2022arXiv

Appending Information Reconciliation for Quantum Key Distribution

Information reconciliation (IR), which corrects the errors in the sifted keys, directly determines the secure key rate and the link distance of quantum key distribution (QKD) systems. In this article, we propose an appending information reconciliation (AIR) scheme based on polar codes, which achieves high efficiency and ultra-low failure probability simultaneously, by gradually disclosing the bit values of the polarized channels with high error probability. The experimental results show that the efficiency of the proposed AIR scheme is closer to the Shannon limit, compared with the state-of-the-art implemented polar codes-based IR schemes, with the overall failure probability around 1E-8, especially when performed with smaller block sizes. Moreover, the efficiency of the proposed AIR scheme is 1.046, when the block size is 1 Gb and the quantum bit error rate of 0.02. Therefore, the proposed AIR scheme can further eradicate the performance gap between theory and implementation for QKD systems.

preprint2022arXiv

APPL: Adaptive Planner Parameter Learning

While current autonomous navigation systems allow robots to successfully drive themselves from one point to another in specific environments, they typically require extensive manual parameter re-tuning by human robotics experts in order to function in new environments. Furthermore, even for just one complex environment, a single set of fine-tuned parameters may not work well in different regions of that environment. These problems prohibit reliable mobile robot deployment by non-expert users. As a remedy, we propose Adaptive Planner Parameter Learning (APPL), a machine learning framework that can leverage non-expert human interaction via several modalities -- including teleoperated demonstrations, corrective interventions, and evaluative feedback -- and also unsupervised reinforcement learning to learn a parameter policy that can dynamically adjust the parameters of classical navigation systems in response to changes in the environment. APPL inherits safety and explainability from classical navigation systems while also enjoying the benefits of machine learning, i.e., the ability to adapt and improve from experience. We present a suite of individual APPL methods and also a unifying cycle-of-learning scheme that combines all the proposed methods in a framework that can improve navigation performance through continual, iterative human interaction and simulation training.

preprint2022arXiv

Bismut-Cheeger eta form and higher spectral flow

In this paper, using the equivariant version of the Dai-Zhang higher spectral flow, we generalize the variation formula, embedding formula and the adiabatic limit formula for the Atiyah-Patodi-Singer eta invariants to the equivariant Bismut-Cheeger eta forms for a fiberwise compact Lie group action when the kernels of corresponding fiberwise Dirac operators form equivariant vector bundles.

preprint2022arXiv

Boosting Multi-Label Image Classification with Complementary Parallel Self-Distillation

Multi-Label Image Classification (MLIC) approaches usually exploit label correlations to achieve good performance. However, emphasizing correlation like co-occurrence may overlook discriminative features of the target itself and lead to model overfitting, thus undermining the performance. In this study, we propose a generic framework named Parallel Self-Distillation (PSD) for boosting MLIC models. PSD decomposes the original MLIC task into several simpler MLIC sub-tasks via two elaborated complementary task decomposition strategies named Co-occurrence Graph Partition (CGP) and Dis-occurrence Graph Partition (DGP). Then, the MLIC models of fewer categories are trained with these sub-tasks in parallel for respectively learning the joint patterns and the category-specific patterns of labels. Finally, knowledge distillation is leveraged to learn a compact global ensemble of full categories with these learned patterns for reconciling the label correlation exploitation and model overfitting. Extensive results on MS-COCO and NUS-WIDE datasets demonstrate that our framework can be easily plugged into many MLIC approaches and improve performances of recent state-of-the-art approaches. The explainable visual study also further validates that our method is able to learn both the category-specific and co-occurring features. The source code is released at https://github.com/Robbie-Xu/CPSD.

preprint2022arXiv

Broad Emission and Absorption Line Outflows in the Quasar SDSS J163345.22+512748.4

We present a detailed study of the optical and NIR emission and absorption line spectrum of the quasar SDSS J163345.22+512748.4. We discovered on the newly acquired NIR spectrum a highly meta-stable neutral helium broad absorption line (BAL) \heiozetz\ with a width of $\sim$ 2000 \kmps\ and a blueshift of $\sim$ 7000 \kmps\ in the velocity space. The BAL system is also significantly detected in \mgii\ and \heiteen. We estimate a column density of $(5.0 \pm 1.7) \times 10^{14}$ cm$^{-2}$ for the HeI*(2~$^3$S) level, and infer an ionization parameter of $U_{A} = 10^{-1.9\pm 0.2}$ for the BAL outflow assuming that the BAL region is thick enough for a full development of an ionization front. The total column density of the BAL outflow is constrained in the range N$\rm _{H}$ $\sim$ 10$^{21}$-10$^{21.4}$ cm$^{-2}$. We also found that the bulk of both MgII and UV FeII, as well as H$α$ broad emission lines (BELs) are blueshifted with a velocity of $\sim$ 2200 \kmps\ with respect to the quasar systemic redshift. We constrain that the blueshifted BEL region has a covering factor $C_{f}\approx 16\%$, a density n$\rm _{H}$ $\sim $ 10$^{10.6}$-10$^{11.3}$ cm$^{-3}$, a column density N$\rm _{H}\gtrsim 10^{23}$ cm$^{-2}$, and an ionization parameter $U_{E}\sim 10^{-2.1}-10^{-1.5}$. The outflow gas is located at $\sim$0.1 pc away from the central ionization source, at a scale comparable to the BLR. A toy kinetic model has been proposed to reproduce the profile of MgII BEL well if assuming a partial obscured axisymmetric geometry of the outflow with a radial velocity as observed by the BALs.

preprint2022arXiv

Continual Learning and Private Unlearning

As intelligent agents become autonomous over longer periods of time, they may eventually become lifelong counterparts to specific people. If so, it may be common for a user to want the agent to master a task temporarily but later on to forget the task due to privacy concerns. However enabling an agent to \emph{forget privately} what the user specified without degrading the rest of the learned knowledge is a challenging problem. With the aim of addressing this challenge, this paper formalizes this continual learning and private unlearning (CLPU) problem. The paper further introduces a straightforward but exactly private solution, CLPU-DER++, as the first step towards solving the CLPU problem, along with a set of carefully designed benchmark problems to evaluate the effectiveness of the proposed solution. The code is available at https://github.com/Cranial-XIX/Continual-Learning-Private-Unlearning.

preprint2022arXiv

D-Unet: A Dual-encoder U-Net for Image Splicing Forgery Detection and Localization

Recently, many detection methods based on convolutional neural networks (CNNs) have been proposed for image splicing forgery detection. Most of these detection methods focus on the local patches or local objects. In fact, image splicing forgery detection is a global binary classification task that distinguishes the tampered and non-tampered regions by image fingerprints. However, some specific image contents are hardly retained by CNN-based detection networks, but if included, would improve the detection accuracy of the networks. To resolve these issues, we propose a novel network called dual-encoder U-Net (D-Unet) for image splicing forgery detection, which employs an unfixed encoder and a fixed encoder. The unfixed encoder autonomously learns the image fingerprints that differentiate between the tampered and non-tampered regions, whereas the fixed encoder intentionally provides the direction information that assists the learning and detection of the network. This dual-encoder is followed by a spatial pyramid global-feature extraction module that expands the global insight of D-Unet for classifying the tampered and non-tampered regions more accurately. In an experimental comparison study of D-Unet and state-of-the-art methods, D-Unet outperformed the other methods in image-level and pixel-level detection, without requiring pre-training or training on a large number of forgery images. Moreover, it was stably robust to different attacks.

preprint2022arXiv

Design and Commissioning of A Beam Distribution System for Multiple Undulator Line Operation of the SXFEL-UF

As an important measure of improving the efficiency and usability of X-ray free electron laser facilities, simultaneous operation of multiple undulator lines realized by a beam distribution system has become a standard configuration in the recent built XFEL facilities. In Shanghai, SXFEL-UF, the first soft X-ray free electron laser user facility in China, has finished construction and started commissioning recently. Electron beam from linac is alternately distributed between the two parallel undulator beam lines by a beam distribution system with a 6° deflection line. The beam distribution system is designed to keep the beam properties like low emittance, high peak charge and small bunch length from being spoiled. Beam collective effects such as the dispersion, coherent synchrotron radiation and micro-bunching instability should be well suppressed to guarantee the beam quality. In this work, the detailed physics design of the beam distribution system is described and the recent commissioning result is reported.

preprint2022arXiv

Effective Mutation Rate Adaptation through Group Elite Selection

Evolutionary algorithms are sensitive to the mutation rate (MR); no single value of this parameter works well across domains. Self-adaptive MR approaches have been proposed but they tend to be brittle: Sometimes they decay the MR to zero, thus halting evolution. To make self-adaptive MR robust, this paper introduces the Group Elite Selection of Mutation Rates (GESMR) algorithm. GESMR co-evolves a population of solutions and a population of MRs, such that each MR is assigned to a group of solutions. The resulting best mutational change in the group, instead of average mutational change, is used for MR selection during evolution, thus avoiding the vanishing MR problem. With the same number of function evaluations and with almost no overhead, GESMR converges faster and to better solutions than previous approaches on a wide range of continuous test optimization problems. GESMR also scales well to high-dimensional neuroevolution for supervised image-classification tasks and for reinforcement learning control tasks. Remarkably, GESMR produces MRs that are optimal in the long-term, as demonstrated through a comprehensive look-ahead grid search. Thus, GESMR and its theoretical and empirical analysis demonstrate how self-adaptation can be harnessed to improve performance in several applications of evolutionary computation.

preprint2022arXiv

Enantiodiscrimination of chiral molecules via quantum correlation function

We propose a method to realize enantiodiscrimination of chiral molecules based on quantum correlation function in a driven cavity-molecule system, where the chiral molecule is coupled with a quantized cavity field and two classical light fields to form a cyclic three-level model. According to the inherent properties of electric-dipole transition moments of chiral molecules, there is a $π$-phase difference in the overall phase of the cyclic three-level model for the left- and right-handed chiral molecules. Thus, the correlation function depends on this overall phase and is chirality-dependent. The analytical and numerical results indicate that the left- and right-handed chiral molecules can be discriminated by detecting quantum correlation function. Our work opens up a promising route to discriminate molecular chirality, which is an extremely important task in pharmacology and biochemistry.

preprint2022arXiv

HardBoost: Boosting Zero-Shot Learning with Hard Classes

This work is a systematical analysis on the so-called hard class problem in zero-shot learning (ZSL), that is, some unseen classes disproportionally affect the ZSL performances than others, as well as how to remedy the problem by detecting and exploiting hard classes. At first, we report our empirical finding that the hard class problem is a ubiquitous phenomenon and persists regardless of used specific methods in ZSL. Then, we find that high semantic affinity among unseen classes is a plausible underlying cause of hardness and design two metrics to detect hard classes. Finally, two frameworks are proposed to remedy the problem by detecting and exploiting hard classes, one under inductive setting, the other under transductive setting. The proposed frameworks could accommodate most existing ZSL methods to further significantly boost their performances with little efforts. Extensive experiments on three popular benchmarks demonstrate the benefits by identifying and exploiting the hard classes in ZSL.

preprint2022arXiv

Implicit semantic-based personalized micro-videos recommendation

With the rapid development of mobile Internet and big data, a huge amount of data is generated in the network, but the data that users are really interested in a very small portion. To extract the information that users are interested in from the huge amount of data, the information overload problem needs to be solved. In the era of mobile internet, the user's characteristics and other information should be combined in the massive amount of data to quickly and accurately recommend content to the user, as far as possible to meet the user's personalized needs. Therefore, there is an urgent need to realize high-speed and effective retrieval in tens of thousands of micro-videos. Video data content contains complex meanings, and there are intrinsic connections between video data. For multimodal information, subspace coding learning is introduced to build a coding network from public potential representations to multimodal feature information, taking into account the consistency and complementarity of information under each modality to obtain a public representation of the complete eigenvalue. An end-to-end reordering model based on deep learning and attention mechanism, called interest-related product similarity model based on multimodal data, is proposed for providing top-N recommendations. The multimodal feature learning module, interest-related network module and product similarity recommendation module together form the new model.By conducting extensive experiments on publicly accessible datasets, the results demonstrate the state-of-the-art performance of our proposed algorithm and its effectiveness.

preprint2022arXiv

Label-only Model Inversion Attack: The Attack that Requires the Least Information

In a model inversion attack, an adversary attempts to reconstruct the data records, used to train a target model, using only the model's output. In launching a contemporary model inversion attack, the strategies discussed are generally based on either predicted confidence score vectors, i.e., black-box attacks, or the parameters of a target model, i.e., white-box attacks. However, in the real world, model owners usually only give out the predicted labels; the confidence score vectors and model parameters are hidden as a defense mechanism to prevent such attacks. Unfortunately, we have found a model inversion method that can reconstruct the input data records based only on the output labels. We believe this is the attack that requires the least information to succeed and, therefore, has the best applicability. The key idea is to exploit the error rate of the target model to compute the median distance from a set of data records to the decision boundary of the target model. The distance, then, is used to generate confidence score vectors which are adopted to train an attack model to reconstruct the data records. The experimental results show that highly recognizable data records can be reconstructed with far less information than existing methods.

preprint2022arXiv

Language-Level Semantics Conditioned 3D Point Cloud Segmentation

In this work, a language-level Semantics Conditioned framework for 3D Point cloud segmentation, called SeCondPoint, is proposed, where language-level semantics are introduced to condition the modeling of point feature distribution as well as the pseudo-feature generation, and a feature-geometry-based mixup approach is further proposed to facilitate the distribution learning. To our knowledge, this is the first attempt in literature to introduce language-level semantics to the 3D point cloud segmentation task. Since a large number of point features could be generated from the learned distribution thanks to the semantics conditioned modeling, any existing segmentation network could be embedded into the proposed framework to boost its performance. In addition, the proposed framework has the inherent advantage of dealing with novel classes, which seems an impossible feat for the current segmentation networks. Extensive experimental results on two public datasets demonstrate that three typical segmentation networks could achieve significant improvements over their original performances after enhancement by the proposed framework in the conventional 3D segmentation task. Two benchmarks are also introduced for a newly introduced zero-shot 3D segmentation task, and the results also validate the proposed framework.

preprint2022arXiv

Low-temperature specific-heat studies on two square-kagome antiferromagnets

We studied the low-temperature specific heats of two antiferromagnets with the two-dimensional square-kagome structure, i.e., KCu$_6$AlBiO$_4$(SO$_4$)$_5$Cl (KCu6) and Na$_6$Cu$_7$BiO$_4$(PO$_4$)$_4$[Cl,(OH)]$_3$ (NaCu7) with the structural differences that there are interlayer Cu$^{2+}$ ions in NaCu7. Both materials show no magnetic ordering down to 50 mK. At zero field, the $C/T$ of KCu6 has a finite value when the temperature is close to zero K. Under the magnetic field, a seemingly $T^2$ dependence appears and its coefficient is progressively suppressed by the field. For NaCu7, the specific heat exhibits the $T^2$ dependence at zero field and under fields. The ratio of the quadratic coefficients of KCu6 and NaCu7 at high fields is inversely proportional to ratio of the squared Weiss temperatures, which indicates these two compounds host the same ground state under fields. Our results suggest that the interlayer Cu$^{2+}$ ions in NaCu7 play a negligible role in determination of its ground state. We discuss the possible quantum-spin-liquid states in these compounds and further directions to pursue based our results.

preprint2022arXiv

Mean-Variance Policy Iteration for Risk-Averse Reinforcement Learning

We present a mean-variance policy iteration (MVPI) framework for risk-averse control in a discounted infinite horizon MDP optimizing the variance of a per-step reward random variable. MVPI enjoys great flexibility in that any policy evaluation method and risk-neutral control method can be dropped in for risk-averse control off the shelf, in both on- and off-policy settings. This flexibility reduces the gap between risk-neutral control and risk-averse control and is achieved by working on a novel augmented MDP directly. We propose risk-averse TD3 as an example instantiating MVPI, which outperforms vanilla TD3 and many previous risk-averse control methods in challenging Mujoco robot simulation tasks under a risk-aware performance metric. This risk-averse TD3 is the first to introduce deterministic policies and off-policy learning into risk-averse reinforcement learning, both of which are key to the performance boost we show in Mujoco domains.

preprint2022arXiv

Modeling User Behavior with Graph Convolution for Personalized Product Search

User preference modeling is a vital yet challenging problem in personalized product search. In recent years, latent space based methods have achieved state-of-the-art performance by jointly learning semantic representations of products, users, and text tokens. However, existing methods are limited in their ability to model user preferences. They typically represent users by the products they visited in a short span of time using attentive models and lack the ability to exploit relational information such as user-product interactions or item co-occurrence relations. In this work, we propose to address the limitations of prior arts by exploring local and global user behavior patterns on a user successive behavior graph, which is constructed by utilizing short-term actions of all users. To capture implicit user preference signals and collaborative patterns, we use an efficient jumping graph convolution to explore high-order relations to enrich product representations for user preference modeling. Our approach can be seamlessly integrated with existing latent space based methods and be potentially applied in any product retrieval method that uses purchase history to model user preferences. Extensive experiments on eight Amazon benchmarks demonstrate the effectiveness and potential of our approach. The source code is available at \url{https://github.com/floatSDSDS/SBG}.

preprint2022arXiv

Motion Planning and Control for Mobile Robot Navigation Using Machine Learning: a Survey

Moving in complex environments is an essential capability of intelligent mobile robots. Decades of research and engineering have been dedicated to developing sophisticated navigation systems to move mobile robots from one point to another. Despite their overall success, a recently emerging research thrust is devoted to developing machine learning techniques to address the same problem, based in large part on the success of deep learning. However, to date, there has not been much direct comparison between the classical and emerging paradigms to this problem. In this article, we survey recent works that apply machine learning for motion planning and control in mobile robot navigation, within the context of classical navigation systems. The surveyed works are classified into different categories, which delineate the relationship of the learning approaches to classical methods. Based on this classification, we identify common challenges and promising future directions.

preprint2022arXiv

Multi-wavelength Campaign on the Super-Eddington NLS1 RX J0134.2-4258 -- I. Peculiar X-ray Spectra and Variability

We have conducted a new long-term multi-wavelength campaign on one of the most super- Eddington narrow-line Seyfert 1s (NLS1s) known, namely RX J0134.2-4258. In this first paper, we report deep simultaneous X-ray observations performed by XMM-Newton and NuSTAR in 2019-12-19, during which RX J0134.2-4258 was fortuitously at one of its lowest X-ray flux states. However, there is a clear rise above 4 keV which implies that the intrinsic source flux may be higher. The X-ray spectra observed between 1996 and 2019 show drastic variability, probably due to complex, variable absorption along the line of sight. Unusually, the soft X-ray excess appears extremely weak in all these spectra, even when the hard X-ray spectrum has a steep slope of $Γ\simeq 2.2$. We explore the spectral-timing properties of the new (low X-ray flux) and archival (high X-ray flux) XMM-Newton data, fitting their time-average, rms and lag spectra simultaneously. The variability spectra indicate the presence of a very weak soft X-ray Comptonisation component, whose shape is similar to the soft excess in normal super-Eddington NLS1s, but with flux relative to the power law which is lower by more than one order of magnitude. Above 4 keV the low-flux data are dominated by a different component, which lags with respect to the lower energy emission. This is consistent with an origin of reflection or partial covering absorption from low ionization material located within 100 Rg. We interpret this as a further indication of the presence of a clumpy disc wind.

preprint2022arXiv

Neutron-diffraction and linear {Grüneisen} parameter studies of magnetism in NdFe$_2$Ga$_8$

We study the magnetism in NdFe$_2$Ga$_8$ by the neutron-diffraction and temperature-modulated linear {Grüneisen} parameter measurements. Previous thermodynamical measurements have demonstrated that there are two magnetic transitions at 10 and 14.5 K, respectively. Neutron-diffraction measurements confirm that the lower one is an antiferromagnetic (AFM) transition with a commensurate magnetic structure. Both the commensurate and the incommensurate (IC) magnetic peaks are found below the higher transition but their intensities only gradually increase with decreasing temperature. Below 10 K, the commensurate peak intensity increases quickly with decreasing temperature, signaling the AFM transition, while the IC peak intensity disappears below 5 K. The linear {Grüneisen} parameter along the $c$ axis, $Γ_c$, shows a hysteresis behavior that is different from the hysteresis behavior for the magnetization $M$. We give a discussion of the origin of the magnetism in NdFe$_2$Ga$_8$.

preprint2022arXiv

One Parameter Defense -- Defending against Data Inference Attacks via Differential Privacy

Machine learning models are vulnerable to data inference attacks, such as membership inference and model inversion attacks. In these types of breaches, an adversary attempts to infer a data record's membership in a dataset or even reconstruct this data record using a confidence score vector predicted by the target model. However, most existing defense methods only protect against membership inference attacks. Methods that can combat both types of attacks require a new model to be trained, which may not be time-efficient. In this paper, we propose a differentially private defense method that handles both types of attacks in a time-efficient manner by tuning only one parameter, the privacy budget. The central idea is to modify and normalize the confidence score vectors with a differential privacy mechanism which preserves privacy and obscures membership and reconstructed data. Moreover, this method can guarantee the order of scores in the vector to avoid any loss in classification accuracy. The experimental results show the method to be an effective and timely defense against both membership inference and model inversion attacks with no reduction in accuracy.

preprint2022arXiv

PRIMA: Planner-Reasoner Inside a Multi-task Reasoning Agent

We consider the problem of multi-task reasoning (MTR), where an agent can solve multiple tasks via (first-order) logic reasoning. This capability is essential for human-like intelligence due to its strong generalizability and simplicity for handling multiple tasks. However, a major challenge in developing effective MTR is the intrinsic conflict between reasoning capability and efficiency. An MTR-capable agent must master a large set of "skills" to tackle diverse tasks, but executing a particular task at the inference stage requires only a small subset of immediately relevant skills. How can we maintain broad reasoning capability and also efficient specific-task performance? To address this problem, we propose a Planner-Reasoner framework capable of state-of-the-art MTR capability and high efficiency. The Reasoner models shareable (first-order) logic deduction rules, from which the Planner selects a subset to compose into efficient reasoning paths. The entire model is trained in an end-to-end manner using deep reinforcement learning, and experimental studies over a variety of domains validate its effectiveness.

preprint2022arXiv

Real-world challenges for multi-agent reinforcement learning in grid-interactive buildings

Building upon prior research that highlighted the need for standardizing environments for building control research, and inspired by recently introduced challenges for real life reinforcement learning control, here we propose a non-exhaustive set of nine real world challenges for reinforcement learning control in grid-interactive buildings. We argue that research in this area should be expressed in this framework in addition to providing a standardized environment for repeatability. Advanced controllers such as model predictive control and reinforcement learning (RL) control have both advantages and disadvantages that prevent them from being implemented in real world problems. Comparisons between the two are rare, and often biased. By focusing on the challenges, we can investigate the performance of the controllers under a variety of situations and generate a fair comparison. As a demonstration, we implement the offline learning challenge in CityLearn and study the impact of different levels of domain knowledge and complexity of RL algorithms. We show that the sequence of operations utilized in a rule based controller (RBC) used for offline training affects the performance of the RL agents when evaluated on a set of four energy flexibility metrics. Longer offline learning from an optimized RBC leads to improved performance in the long run. RL agents that learn from a simplified RBC risk poorer performance as the offline learning period increases. We also observe no impact on performance from information sharing amongst agents. We call for a more interdisciplinary effort of the research community to address the real world challenges, and unlock the potential of grid-interactive building

preprint2022arXiv

Regional-Local Adversarially Learned One-Class Classifier Anomalous Sound Detection in Global Long-Term Space

Anomalous sound detection (ASD) is one of the most significant tasks of mechanical equipment monitoring and maintaining in complex industrial systems. In practice, it is vital to precisely identify abnormal status of the working mechanical system, which can further facilitate the failure troubleshooting. In this paper, we propose a multi-pattern adversarial learning one-class classification framework, which allows us to use both the generator and the discriminator of an adversarial model for efficient ASD. The core idea is learning to reconstruct the normal patterns of acoustic data through two different patterns of auto-encoding generators, which succeeds in extending the fundamental role of a discriminator from identifying real and fake data to distinguishing between regional and local pattern reconstructions. Furthermore, we present a global filter layer for long-term interactions in the frequency domain space, which directly learns from the original data without introducing any human priors. Extensive experiments performed on four real-world datasets from different industrial domains (three cavitation datasets provided by SAMSON AG, and one existing publicly) for anomaly detection show superior results, and outperform recent state-of-the-art ASD methods.

preprint2022arXiv

Semantic-diversity transfer network for generalized zero-shot learning via inner disagreement based OOD detector

Zero-shot learning (ZSL) aims to recognize objects from unseen classes, where the kernel problem is to transfer knowledge from seen classes to unseen classes by establishing appropriate mappings between visual and semantic features. The knowledge transfer in many existing works is limited mainly due to the facts that 1) the widely used visual features are global ones but not totally consistent with semantic attributes; 2) only one mapping is learned in existing works, which is not able to effectively model diverse visual-semantic relations; 3) the bias problem in the generalized ZSL (GZSL) could not be effectively handled. In this paper, we propose two techniques to alleviate these limitations. Firstly, we propose a Semantic-diversity transfer Network (SetNet) addressing the first two limitations, where 1) a multiple-attention architecture and a diversity regularizer are proposed to learn multiple local visual features that are more consistent with semantic attributes and 2) a projector ensemble that geometrically takes diverse local features as inputs is proposed to model visual-semantic relations from diverse local perspectives. Secondly, we propose an inner disagreement based domain detection module (ID3M) for GZSL to alleviate the third limitation, which picks out unseen-class data before class-level classification. Due to the absence of unseen-class data in training stage, ID3M employs a novel self-contained training scheme and detects out unseen-class data based on a designed inner disagreement criterion. Experimental results on three public datasets demonstrate that the proposed SetNet with the explored ID3M achieves a significant improvement against $30$ state-of-the-art methods.

preprint2022arXiv

STOPS: Short-Term-based Volatility-controlled Policy Search and its Global Convergence

It remains challenging to deploy existing risk-averse approaches to real-world applications. The reasons are multi-fold, including the lack of global optimality guarantee and the necessity of learning from long-term consecutive trajectories. Long-term consecutive trajectories are prone to involving visiting hazardous states, which is a major concern in the risk-averse setting. This paper proposes Short-Term VOlatility-controlled Policy Search (STOPS), a novel algorithm that solves risk-averse problems by learning from short-term trajectories instead of long-term trajectories. Short-term trajectories are more flexible to generate, and can avoid the danger of hazardous state visitations. By using an actor-critic scheme with an overparameterized two-layer neural network, our algorithm finds a globally optimal policy at a sublinear rate with proximal policy optimization and natural policy gradient, with effectiveness comparable to the state-of-the-art convergence rate of risk-neutral policy-search methods. The algorithm is evaluated on challenging Mujoco robot simulation tasks under the mean-variance evaluation metric. Both theoretical analysis and experimental results demonstrate a state-of-the-art level of STOPS' performance among existing risk-averse policy search methods.

preprint2022arXiv

Trustworthy AI: From Principles to Practices

The rapid development of Artificial Intelligence (AI) technology has enabled the deployment of various systems based on it. However, many current AI systems are found vulnerable to imperceptible attacks, biased against underrepresented groups, lacking in user privacy protection. These shortcomings degrade user experience and erode people's trust in all AI systems. In this review, we provide AI practitioners with a comprehensive guide for building trustworthy AI systems. We first introduce the theoretical framework of important aspects of AI trustworthiness, including robustness, generalization, explainability, transparency, reproducibility, fairness, privacy preservation, and accountability. To unify currently available but fragmented approaches toward trustworthy AI, we organize them in a systematic approach that considers the entire lifecycle of AI systems, ranging from data acquisition to model development, to system development and deployment, finally to continuous monitoring and governance. In this framework, we offer concrete action items for practitioners and societal stakeholders (e.g., researchers, engineers, and regulators) to improve AI trustworthiness. Finally, we identify key opportunities and challenges for the future development of trustworthy AI systems, where we identify the need for a paradigm shift toward comprehensively trustworthy AI systems.

preprint2022arXiv

Unravelling Token Ecosystem of EOSIO Blockchain

Being the largest Initial Coin Offering project, EOSIO has attracted great interest in cryptocurrency markets. Despite its popularity and prosperity (e.g., 26,311,585,008 token transactions occurred from June 8, 2018 to Aug. 5, 2020), there is almost no work investigating the EOSIO token ecosystem. To fill this gap, we are the first to conduct a systematic investigation on the EOSIO token ecosystem by conducting a comprehensive graph analysis on the entire on-chain EOSIO data (nearly 135 million blocks). We construct token creator graphs, token-contract creator graphs, token holder graphs, and token transfer graphs to characterize token creators, holders, and transfer activities. Through graph analysis, we have obtained many insightful findings and observed some abnormal trading patterns. Moreover, we propose a fake-token detection algorithm to identify tokens generated by fake users or fake transactions and analyze their corresponding manipulation behaviors. Evaluation results also demonstrate the effectiveness of our algorithm.

preprint2022arXiv

Video object tracking based on YOLOv7 and DeepSORT

Multiple object tracking (MOT) is an important technology in the field of computer vision, which is widely used in automatic driving, intelligent monitoring, behavior recognition and other directions. Among the current popular MOT methods based on deep learning, Detection Based Tracking (DBT) is the most widely used in industry, and the performance of them depend on their object detection network. At present, the DBT algorithm with good performance and the most widely used is YOLOv5-DeepSORT. Inspired by YOLOv5-DeepSORT, with the proposal of YOLOv7 network, which performs better in object detection, we apply YOLOv7 as the object detection part to the DeepSORT, and propose YOLOv7-DeepSORT. After experimental evaluation, compared with the previous YOLOv5-DeepSORT, YOLOv7-DeepSORT performances better in tracking accuracy.

preprint2021arXiv

A Lifelong Learning Approach to Mobile Robot Navigation

This paper presents a self-improving lifelong learning framework for a mobile robot navigating in different environments. Classical static navigation methods require environment-specific in-situ system adjustment, e.g. from human experts, or may repeat their mistakes regardless of how many times they have navigated in the same environment. Having the potential to improve with experience, learning-based navigation is highly dependent on access to training resources, e.g. sufficient memory and fast computation, and is prone to forgetting previously learned capability, especially when facing different environments. In this work, we propose Lifelong Learning for Navigation (LLfN) which (1) improves a mobile robot's navigation behavior purely based on its own experience, and (2) retains the robot's capability to navigate in previous environments after learning in new ones. LLfN is implemented and tested entirely onboard a physical robot with a limited memory and computation budget.

preprint2021arXiv

Agile Robot Navigation through Hallucinated Learning and Sober Deployment

Learning from Hallucination (LfH) is a recent machine learning paradigm for autonomous navigation, which uses training data collected in completely safe environments and adds numerous imaginary obstacles to make the environment densely constrained, to learn navigation planners that produce feasible navigation even in highly constrained (more dangerous) spaces. However, LfH requires hallucinating the robot perception during deployment to match with the hallucinated training data, which creates a need for sometimes-infeasible prior knowledge and tends to generate very conservative planning. In this work, we propose a new LfH paradigm that does not require runtime hallucination -- a feature we call "sober deployment" -- and can therefore adapt to more realistic navigation scenarios. This novel Hallucinated Learning and Sober Deployment (HLSD) paradigm is tested in a benchmark testbed of 300 simulated navigation environments with a wide range of difficulty levels, and in the real-world. In most cases, HLSD outperforms both the original LfH method and a classical navigation planner.

preprint2021arXiv

Artificial intelligence enabled radio propagation for communications-Part I: Channel characterization and antenna-channel optimization

To provide higher data rates, as well as better coverage, cost efficiency, security, adaptability, and scalability, the 5G and beyond 5G networks are developed with various artificial intelligence techniques. In this two-part paper, we investigate the application of artificial intelligence (AI) and in particular machine learning (ML) to the study of wireless propagation channels. It firstly provides a comprehensive overview of ML for channel characterization and ML-based antenna-channel optimization in this first part, and then it gives a state-of-the-art literature review of channel scenario identification and channel modeling in Part II. Fundamental results and key concepts of ML for communication networks are presented, and widely used ML methods for channel data processing, propagation channel estimation, and characterization are analyzed and compared. A discussion of challenges and future research directions for ML-enabled next generation networks of the topics covered in this part rounds off the paper.

preprint2021arXiv

Artificial intelligence enabled radio propagation for communications-Part II: Scenario identification and channel modeling

This two-part paper investigates the application of artificial intelligence (AI) and in particular machine learning (ML) to the study of wireless propagation channels. In Part I, we introduced AI and ML as well as provided a comprehensive survey on ML enabled channel characterization and antenna-channel optimization, and in this part (Part II) we review state-of-the-art literature on scenario identification and channel modeling here. In particular, the key ideas of ML for scenario identification and channel modeling/prediction are presented, and the widely used ML methods for propagation scenario identification and channel modeling and prediction are analyzed and compared. Based on the state-of-art, the future challenges of AI/ML-based channel data processing techniques are given as well.

preprint2021arXiv

Discrete Knowledge Graph Embedding based on Discrete Optimization

This paper proposes a discrete knowledge graph (KG) embedding (DKGE) method, which projects KG entities and relations into the Hamming space based on a computationally tractable discrete optimization algorithm, to solve the formidable storage and computation cost challenges in traditional continuous graph embedding methods. The convergence of DKGE can be guaranteed theoretically. Extensive experiments demonstrate that DKGE achieves superior accuracy than classical hashing functions that map the effective continuous embeddings into discrete codes. Besides, DKGE reaches comparable accuracy with much lower computational complexity and storage compared to many continuous graph embedding methods.

preprint2021arXiv

Enantio-conversion of chiral mixtures via optical pumping

Enantio-conversion with the help of electromagnetic fields is an essential issue due to the chirality-dependence of many chemical, biological, and pharmaceutical processes. Here, we propose a method for this issue based on a five-level double-$Δ$ model of chiral molecules. By utilizing the breaking of left-right symmetry in the two $Δ$-type sub-structures, we can establish the chiral-state-selective excitation with one chiral ground state being excited to an achiral excited state and the other one being undisturbed. In the meanwhile, the achiral excited state will relax to the two chiral ground states. The two effects simultaneously acting on the chiral mixtures can convert molecules of different chiralities to the ones of the same chirality, i.e., the enantio-conversion via optical pumping. With typical parameters in gas-phase experiments, we numerically show that highly efficient enantio-conversion can be achieved. Our method works in the appearance of decoherences and without the precise control of pulse-durations (pulse-areas) and/or pulse-shapes. These advantages offer it promising features in promoting the future exploring of enantio-conversion.

preprint2021arXiv

Enantio-specific state transfer for symmetric-top chiral molecules

We study the enantio-specific state transfer in a four-level model for symmetric-top chiral molecules. Such a model is formed by coupling the electric-dipole transitions among four appropriate working states with three electromagnetic fields. It includes two cyclic three-level substructures, where the overall phases differ by $π$ with enantiomers and reflect the chirality dependence of the molecule. Based on this four-level model, two dynamic ways are proposed to achieve the approximately perfect enantio-specific state transfer for symmetric-top chiral molecules.

preprint2021arXiv

Heterogeneous Hypergraph Embedding for Graph Classification

Recently, graph neural networks have been widely used for network embedding because of their prominent performance in pairwise relationship learning. In the real world, a more natural and common situation is the coexistence of pairwise relationships and complex non-pairwise relationships, which is, however, rarely studied. In light of this, we propose a graph neural network-based representation learning framework for heterogeneous hypergraphs, an extension of conventional graphs, which can well characterize multiple non-pairwise relations. Our framework first projects the heterogeneous hypergraph into a series of snapshots and then we take the Wavelet basis to perform localized hypergraph convolution. Since the Wavelet basis is usually much sparser than the Fourier basis, we develop an efficient polynomial approximation to the basis to replace the time-consuming Laplacian decomposition. Extensive evaluations have been conducted and the experimental results show the superiority of our method. In addition to the standard tasks of network embedding evaluation such as node classification, we also apply our method to the task of spammers detection and the superior performance of our framework shows that relationships beyond pairwise are also advantageous in the spammer detection.

preprint2021arXiv

IdentityDP: Differential Private Identification Protection for Face Images

Because of the explosive growth of face photos as well as their widespread dissemination and easy accessibility in social media, the security and privacy of personal identity information becomes an unprecedented challenge. Meanwhile, the convenience brought by advanced identity-agnostic computer vision technologies is attractive. Therefore, it is important to use face images while taking careful consideration in protecting people's identities. Given a face image, face de-identification, also known as face anonymization, refers to generating another image with similar appearance and the same background, while the real identity is hidden. Although extensive efforts have been made, existing face de-identification techniques are either insufficient in photo-reality or incapable of well-balancing privacy and utility. In this paper, we focus on tackling these challenges to improve face de-identification. We propose IdentityDP, a face anonymization framework that combines a data-driven deep neural network with a differential privacy (DP) mechanism. This framework encompasses three stages: facial representations disentanglement, $ε$-IdentityDP perturbation and image reconstruction. Our model can effectively obfuscate the identity-related information of faces, preserve significant visual similarity, and generate high-quality images that can be used for identity-agnostic computer vision tasks, such as detection, tracking, etc. Different from the previous methods, we can adjust the balance of privacy and utility through the privacy budget according to pratical demands and provide a diversity of results without pre-annotations. Extensive experiments demonstrate the effectiveness and generalization ability of our proposed anonymization framework.

preprint2021arXiv

Manipulating Goldstone modes via the superradiant light in a bosonic lattice gas inside a cavity

We study the low-energy excitations of a bosonic lattice gas with cavity-mediated interactions. By performing two successive Hubbard-Stratonovich transformations, we derive an effective field theory to study the strongly-coupling regime. Taking into account the quantum fluctuation, we report the unusual effect of the superradiant cavity light induced density imbalance, which has been shown to have a negligible effect on the single particle excitation in the previous studies. Instead, we show that such negligible fluctuation of density imbalance dramatically changes the behavior of the low-energy excitation and results in a free switching between two types of Goldstone modes in its single particle excitation, i.e., type I and type II with odd and even power energy-momentum dispersion, respectively. Our proposal would open a new horizon for manipulating Goldstone modes from bridging the cavity light and strongly interacting quantum matters.

preprint2021arXiv

Self-Amplification of Coherent Energy Modulation in Seeded Free-Electron Lasers

The spectroscopic techniques for time-resolved fine analysis of matter require coherent X-ray radiation with femtosecond duration and high average brightness. Seeded free-electron lasers (FELs), which use the frequency up-conversion of an external seed laser to improve temporal coherence, are ideal for providing fully coherent soft X-ray pulses. However, it is difficult to operate seeded FELs at a high repetition rate due to the limitations of present state-of-the-art laser systems. Here, we report the novel self-modulation method for enhancing laser-induced energy modulation, thereby significantly reducing the requirement of an external laser system. Driven by this scheme, we experimentally realize high harmonic generation in a seeded FEL using an unprecedentedly small energy modulation. An electron beam with a laser-induced energy modulation as small as 1.8 times the slice energy spread is used for lasing at the 7th harmonic of a 266-nm seed laser in a single-stage high-gain harmonic generation (HGHG) setup and the 30th harmonic of the seed laser in a two-stage HGHG setup. The results mark a major step towards a high-repetition-rate, fully coherent X-ray FEL.

preprint2021arXiv

SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering

Medical visual question answering (Med-VQA) has tremendous potential in healthcare. However, the development of this technology is hindered by the lacking of publicly-available and high-quality labeled datasets for training and evaluation. In this paper, we present a large bilingual dataset, SLAKE, with comprehensive semantic labels annotated by experienced physicians and a new structural medical knowledge base for Med-VQA. Besides, SLAKE includes richer modalities and covers more human body parts than the currently available dataset. We show that SLAKE can be used to facilitate the development and evaluation of Med-VQA systems. The dataset can be downloaded from http://www.med-vqa.com/slake.

preprint2021arXiv

Spurious Local Minima Are Common for Deep Neural Networks with Piecewise Linear Activations

In this paper, it is shown theoretically that spurious local minima are common for deep fully-connected networks and convolutional neural networks (CNNs) with piecewise linear activation functions and datasets that cannot be fitted by linear models. A motivating example is given to explain the reason for the existence of spurious local minima: each output neuron of deep fully-connected networks and CNNs with piecewise linear activations produces a continuous piecewise linear (CPWL) output, and different pieces of CPWL output can fit disjoint groups of data samples when minimizing the empirical risk. Fitting data samples with different CPWL functions usually results in different levels of empirical risk, leading to prevalence of spurious local minima. This result is proved in general settings with any continuous loss function. The main proof technique is to represent a CPWL function as a maximization over minimization of linear pieces. Deep ReLU networks are then constructed to produce these linear pieces and implement maximization and minimization operations.

preprint2021arXiv

Superpoint-guided Semi-supervised Semantic Segmentation of 3D Point Clouds

3D point cloud semantic segmentation is a challenging topic in the computer vision field. Most of the existing methods in literature require a large amount of fully labeled training data, but it is extremely time-consuming to obtain these training data by manually labeling massive point clouds. Addressing this problem, we propose a superpoint-guided semi-supervised segmentation network for 3D point clouds, which jointly utilizes a small portion of labeled scene point clouds and a large number of unlabeled point clouds for network training. The proposed network is iteratively updated with its predicted pseudo labels, where a superpoint generation module is introduced for extracting superpoints from 3D point clouds, and a pseudo-label optimization module is explored for automatically assigning pseudo labels to the unlabeled points under the constraint of the extracted superpoints. Additionally, there are some 3D points without pseudo-label supervision. We propose an edge prediction module to constrain features of edge points. A superpoint feature aggregation module and a superpoint feature consistency loss function are introduced to smooth superpoint features. Extensive experimental results on two 3D public datasets demonstrate that our method can achieve better performance than several state-of-the-art point cloud segmentation networks and several popular semi-supervised segmentation methods with few labeled scenes.

preprint2021arXiv

Topological semimetal and superfluid of s-wave interacting fermionic atoms in an orbital optical lattice

Recent advanced experimental implementations of optical lattices with highly tunable geometry open up new regimes for quantum many-body states of matter that previously had not been accessible. Here we introduce a symmetry-based method of utilizing the geometry of optical lattice to systematically control topologically non-trivial orbital hybridization. Such an orbital mixing leads to an unexpected and yet robust topological semimetal at single-particle level for a gas of fermionic atoms. When considering s-wave attractive interaction between atoms as for instance tuned by Feshbach resonance, topological superfluid state with high Chern number is unveiled in the presence of on-site rotation. This state supports chiral edge excitations, manifesting its topological nature. An experimental realization scheme is designed, which introduces a systematic way of achieving a new universality class (such as Chern number of 2) of orbital-hybridized topological phases beyond geometrically standard optical lattices.

preprint2021arXiv

Toward Agile Maneuvers in Highly Constrained Spaces: Learning from Hallucination

While classical approaches to autonomous robot navigation currently enable operation in certain environments, they break down in tightly constrained spaces, e.g., where the robot needs to engage in agile maneuvers to squeeze between obstacles. Recent machine learning techniques have the potential to address this shortcoming, but existing approaches require vast amounts of navigation experience for training, during which the robot must operate in close proximity to obstacles and risk collision. In this paper, we propose to side-step this requirement by introducing a new machine learning paradigm for autonomous navigation called learning from hallucination (LfH), which can use training data collected in completely safe environments to compute navigation controllers that result in fast, smooth, and safe navigation in highly constrained environments. Our experimental results show that the proposed LfH system outperforms three autonomous navigation baselines on a real robot and generalizes well to unseen environments, including those based on both classical and machine learning techniques.

preprint2020arXiv

A Convolutional Neural Network with Parallel Multi-Scale Spatial Pooling to Detect Temporal Changes in SAR Images

In synthetic aperture radar (SAR) image change detection, it is quite challenging to exploit the changing information from the noisy difference image subject to the speckle. In this paper, we propose a multi-scale spatial pooling (MSSP) network to exploit the changed information from the noisy difference image. Being different from the traditional convolutional network with only mono-scale pooling kernels, in the proposed method, multi-scale pooling kernels are equipped in a convolutional network to exploit the spatial context information on changed regions from the difference image. Furthermore, to verify the generalization of the proposed method, we apply our proposed method to the cross-dataset bitemporal SAR image change detection, where the MSSP network (MSSP-Net) is trained on a dataset and then applied to an unknown testing dataset. We compare the proposed method with other state-of-arts and the comparisons are performed on four challenging datasets of bitemporal SAR images. Experimental results demonstrate that our proposed method obtains comparable results with S-PCA-Net on YR-A and YR-B dataset and outperforms other state-of-art methods, especially on the Sendai-A and Sendai-B datasets with more complex scenes. More important, MSSP-Net is more efficient than S-PCA-Net and convolutional neural networks (CNN) with less executing time in both training and testing phases.

preprint2020arXiv

A Light-Weighted Convolutional Neural Network for Bitemporal SAR Image Change Detection

Recently, many Convolution Neural Networks (CNN) have been successfully employed in bitemporal SAR image change detection. However, most of the existing networks are too heavy and occupy a large volume of memory for storage and calculation. Motivated by this, in this paper, we propose a lightweight neural network to reduce the computational and spatial complexity and facilitate the change detection on an edge device. In the proposed network, we replace normal convolutional layers with bottleneck layers that keep the same number of channels between input and output. Next, we employ dilated convolutional kernels with a few non-zero entries that reduce the running time in convolutional operators. Comparing with the conventional convolutional neural network, our light-weighted neural network will be more efficient with fewer parameters. We verify our light-weighted neural network on four sets of bitemporal SAR images. The experimental results show that the proposed network can obtain better performance than the conventional CNN and has better model generalization, especially on the challenging datasets with complex scenes.

preprint2020arXiv

Adaptive Graph Convolutional Network with Attention Graph Clustering for Co-saliency Detection

Co-saliency detection aims to discover the common and salient foregrounds from a group of relevant images. For this task, we present a novel adaptive graph convolutional network with attention graph clustering (GCAGC). Three major contributions have been made, and are experimentally shown to have substantial practical merits. First, we propose a graph convolutional network design to extract information cues to characterize the intra- and interimage correspondence. Second, we develop an attention graph clustering algorithm to discriminate the common objects from all the salient foreground objects in an unsupervised fashion. Third, we present a unified framework with encoder-decoder structure to jointly train and optimize the graph convolutional network, attention graph cluster, and co-saliency detection decoder in an end-to-end manner. We evaluate our proposed GCAGC method on three cosaliency detection benchmark datasets (iCoseg, Cosal2015 and COCO-SEG). Our GCAGC method obtains significant improvements over the state-of-the-arts on most of them.

preprint2020arXiv

APPLD: Adaptive Planner Parameter Learning from Demonstration

Existing autonomous robot navigation systems allow robots to move from one point to another in a collision-free manner. However, when facing new environments, these systems generally require re-tuning by expert roboticists with a good understanding of the inner workings of the navigation system. In contrast, even users who are unversed in the details of robot navigation algorithms can generate desirable navigation behavior in new environments via teleoperation. In this paper, we introduce APPLD, Adaptive Planner Parameter Learning from Demonstration, that allows existing navigation systems to be successfully applied to new complex environments, given only a human teleoperated demonstration of desirable navigation. APPLD is verified on two robots running different navigation systems in different environments. Experimental results show that APPLD can outperform navigation systems with the default and expert-tuned parameters, and even the human demonstrator themselves.

preprint2020arXiv

Differential K-theory and localization formula for $η$-invariants

In this paper, we obtain a localization formula in differential K-theory for $S^1$-action. Then by combining an extension of Goette's result on the comparison of two types of equivariant $η$-invariants, we establish a version of localization formula for equivariant $η$-invariants. An important step of our approach is to construct a pre-$λ$-ring structure in differential K-theory which is interesting in its own right.

preprint2020arXiv

Dual Temporal Memory Network for Efficient Video Object Segmentation

Video Object Segmentation (VOS) is typically formulated in a semi-supervised setting. Given the ground-truth segmentation mask on the first frame, the task of VOS is to track and segment the single or multiple objects of interests in the rest frames of the video at the pixel level. One of the fundamental challenges in VOS is how to make the most use of the temporal information to boost the performance. We present an end-to-end network which stores short- and long-term video sequence information preceding the current frame as the temporal memories to address the temporal modeling in VOS. Our network consists of two temporal sub-networks including a short-term memory sub-network and a long-term memory sub-network. The short-term memory sub-network models the fine-grained spatial-temporal interactions between local regions across neighboring frames in video via a graph-based learning framework, which can well preserve the visual consistency of local regions over time. The long-term memory sub-network models the long-range evolution of object via a Simplified-Gated Recurrent Unit (S-GRU), making the segmentation be robust against occlusions and drift errors. In our experiments, we show that our proposed method achieves a favorable and competitive performance on three frequently-used VOS datasets, including DAVIS 2016, DAVIS 2017 and Youtube-VOS in terms of both speed and accuracy.

preprint2020arXiv

DualSMC: Tunneling Differentiable Filtering and Planning under Continuous POMDPs

A major difficulty of solving continuous POMDPs is to infer the multi-modal distribution of the unobserved true states and to make the planning algorithm dependent on the perceived uncertainty. We cast POMDP filtering and planning problems as two closely related Sequential Monte Carlo (SMC) processes, one over the real states and the other over the future optimal trajectories, and combine the merits of these two parts in a new model named the DualSMC network. In particular, we first introduce an adversarial particle filter that leverages the adversarial relationship between its internal components. Based on the filtering results, we then propose a planning algorithm that extends the previous SMC planning approach [Piche et al., 2018] to continuous POMDPs with an uncertainty-dependent policy. Crucially, not only can DualSMC handle complex observations such as image input but also it remains highly interpretable. It is shown to be effective in three continuous POMDP domains: the floor positioning domain, the 3D light-dark navigation domain, and a modified Reacher domain.

preprint2020arXiv

Effect of Dzyaloshinskii-Moriya interaction on magnetic vortex switching driven by radial spin waves

We theoretically investigate the radial-spin-wave induced magnetic vortex switching in the presence of Dzyaloshinskii-Moriya interaction (DMI). From micromagnetic simulations, we observe a circular-to-radial vortex phase transition by increasing the DMI strength. The radial spin-wave excitation spectrum for each magnetization configuration is analyzed, showing that the frequency of spin-wave mode with a given radial node number monotonically increases (decreases) with the DMI parameter of the radial (circular) vortex. Interestingly, we find that the DMI can significantly facilitate the polarity switching of the circular vortex driven by radial spin waves. Our work provides a new insight into the DMI effect on the vortex dynamics and is helpful for designing fast all-magnonic memory devices.

preprint2020arXiv

Estimation of genome size using k-mer frequencies from corrected long reads

The third-generation long reads sequencing technologies, such as PacBio and Nanopore, have great advantages over second-generation Illumina sequencing in de novo assembly studies. However, due to the inherent low base accuracy, third-generation sequencing data cannot be used for k-mer counting and estimating genomic profile based on k-mer frequencies. Thus, in current genome projects, second-generation data is also necessary for accurately determining genome size and other genomic characteristics. We show that corrected third-generation data can be used to count k-mer frequencies and estimate genome size reliably, in replacement of using second-generation data. Therefore, future genome projects can depend on only one sequencing technology to finish both assembly and k-mer analysis, which will largely decrease sequencing cost in both time and money. Moreover, we present a fast light-weight tool kmerfreq and use it to perform all the k-mer counting tasks in this work. We have demonstrated that corrected third-generation sequencing data can be used to estimate genome size and developed a new open-source C/C++ k-mer counting tool, kmerfreq, which is freely available at https://github.com/fanagislab/kmerfreq.

preprint2020arXiv

Evolving the pulmonary nodules diagnosis from classical approaches to deep learning aided decision support: three decades development course and future prospect

Lung cancer is the commonest cause of cancer deaths worldwide, and its mortality can be reduced significantly by performing early diagnosis and screening. Since the 1960s, driven by the pressing needs to accurately and effectively interpret the massive volume of chest images generated daily, computer-assisted diagnosis of pulmonary nodule has opened up new opportunities to relax the limitation from physicians' subjectivity, experiences and fatigue. And the fair access to the reliable and affordable computer-assisted diagnosis will fight the inequalities in incidence and mortality between populations. It has been witnessed that significant and remarkable advances have been achieved since the 1980s, and consistent endeavors have been exerted to deal with the grand challenges on how to accurately detect the pulmonary nodules with high sensitivity at low false-positives rate as well as on how to precisely differentiate between benign and malignant nodules. There is a lack of comprehensive examination of the techniques' development which is evolving the pulmonary nodules diagnosis from classical approaches to machine learning-assisted decision support. The main goal of this investigation is to provide a comprehensive state-of-the-art review of the computer-assisted nodules detection and benign-malignant classification techniques developed over 3 decades, which have evolved from the complicated ad hoc analysis pipeline of conventional approaches to the simplified seamlessly integrated deep learning techniques. This review also identifies challenges and highlights opportunities for future work in learning models, learning algorithms and enhancement schemes for bridging current state to future prospect and satisfying future demand.

preprint2020arXiv

Exploit Clues from Views: Self-Supervised and Regularized Learning for Multiview Object Recognition

Multiview recognition has been well studied in the literature and achieves decent performance in object recognition and retrieval task. However, most previous works rely on supervised learning and some impractical underlying assumptions, such as the availability of all views in training and inference time. In this work, the problem of multiview self-supervised learning (MV-SSL) is investigated, where only image to object association is given. Given this setup, a novel surrogate task for self-supervised learning is proposed by pursuing "object invariant" representation. This is solved by randomly selecting an image feature of an object as object prototype, accompanied with multiview consistency regularization, which results in view invariant stochastic prototype embedding (VISPE). Experiments shows that the recognition and retrieval results using VISPE outperform that of other self-supervised learning methods on seen and unseen data. VISPE can also be applied to semi-supervised scenario and demonstrates robust performance with limited data available. Code is available at https://github.com/chihhuiho/VISPE

preprint2020arXiv

Fast Enhancement for Non-Uniform Illumination Images using Light-weight CNNs

This paper proposes a new light-weight convolutional neural network (5k parameters) for non-uniform illumination image enhancement to handle color, exposure, contrast, noise and artifacts, etc., simultaneously and effectively. More concretely, the input image is first enhanced using Retinex model from dual different aspects (enhancing under-exposure and suppressing over-exposure), respectively. Then, these two enhanced results and the original image are fused to obtain an image with satisfactory brightness, contrast and details. Finally, the extra noise and compression artifacts are removed to get the final result. To train this network, we propose a semi-supervised retouching solution and construct a new dataset (82k images) contains various scenes and light conditions. Our model can enhance 0.5 mega-pixel (like 600*800) images in real time (50 fps), which is faster than existing enhancement methods. Extensive experiments show that our solution is fast and effective to deal with non-uniform illumination images.

preprint2020arXiv

Few-Shot Open-Set Recognition using Meta-Learning

The problem of open-set recognition is considered. While previous approaches only consider this problem in the context of large-scale classifier training, we seek a unified solution for this and the low-shot classification setting. It is argued that the classic softmax classifier is a poor solution for open-set recognition, since it tends to overfit on the training classes. Randomization is then proposed as a solution to this problem. This suggests the use of meta-learning techniques, commonly used for few-shot classification, for the solution of open-set recognition. A new oPen sEt mEta LEaRning (PEELER) algorithm is then introduced. This combines the random selection of a set of novel classes per episode, a loss that maximizes the posterior entropy for examples of those classes, and a new metric learning formulation based on the Mahalanobis distance. Experimental results show that PEELER achieves state of the art open set recognition performance for both few-shot and large-scale recognition. On CIFAR and miniImageNet, it achieves substantial gains in seen/unseen class detection AUROC for a given seen-class classification accuracy.

preprint2020arXiv

Finite-Sample Analysis of Proximal Gradient TD Algorithms

In this paper, we analyze the convergence rate of the gradient temporal difference learning (GTD) family of algorithms. Previous analyses of this class of algorithms use ODE techniques to prove asymptotic convergence, and to the best of our knowledge, no finite-sample analysis has been done. Moreover, there has been not much work on finite-sample analysis for convergent off-policy reinforcement learning algorithms. In this paper, we formulate GTD methods as stochastic gradient algorithms w.r.t.~a primal-dual saddle-point objective function, and then conduct a saddle-point error analysis to obtain finite-sample bounds on their performance. Two revised algorithms are also proposed, namely projected GTD2 and GTD2-MP, which offer improved convergence guarantees and acceleration, respectively. The results of our theoretical analysis show that the GTD family of algorithms are indeed comparable to the existing LSTD methods in off-policy learning scenarios.

preprint2020arXiv

Meta-Learning with Network Pruning

Meta-learning is a powerful paradigm for few-shot learning. Although with remarkable success witnessed in many applications, the existing optimization based meta-learning models with over-parameterized neural networks have been evidenced to ovetfit on training tasks. To remedy this deficiency, we propose a network pruning based meta-learning approach for overfitting reduction via explicitly controlling the capacity of network. A uniform concentration analysis reveals the benefit of network capacity constraint for reducing generalization gap of the proposed meta-learner. We have implemented our approach on top of Reptile assembled with two network pruning routines: Dense-Sparse-Dense (DSD) and Iterative Hard Thresholding (IHT). Extensive experimental results on benchmark datasets with different over-parameterized deep networks demonstrate that our method not only effectively alleviates meta-overfitting but also in many cases improves the overall generalization performance when applied to few-shot classification tasks.

preprint2020arXiv

Neutron spin resonance in a quasi-two-dimensional iron-based superconductor

Magnetically mediated Cooper pairing is generally regarded as a key to establish the unified mechanism of unconventional superconductivity. One crucial evidence is the neutron spin resonance arising in the superconducting state, which is commonly interpreted as a spin-exciton from collective particle-hole excitations confined below the superconducting pair-breaking gap ($2Δ$). Here, on the basis of inelastic neutron scattering measurements on a quasi-two-dimensional iron-based superconductor KCa$_2$Fe$_4$As$_4$F$_2$, we have discovered a two-dimensional spin resonant mode with downward dispersions, a behavior closely resembling the low branch of the hour-glass-type spin resonance in cuprates. The resonant intensity is predominant by two broad incommensurate peaks near $Q=$(0.5, 0.5) with a sharp energy peak at $E_R=16$ meV. The overall energy dispersion of the mode exceeds the measured maximum total gap $Δ_{\rm tot}=|Δ_k|+|Δ_{k+Q}|$. These experimental results deeply challenge the conventional understanding of the resonance modes as magnetic excitons regardless of underlining pairing symmetry schemes, and it also points out that when the iron-based superconductivity becomes very quasi-two-dimensional, the electronic behaviors are similar to those in cuprates.

preprint2020arXiv

Operational definition of a quantum speed limit

The quantum speed limit is a fundamental concept in quantum mechanics, which aims at finding the minimum time scale or the maximum dynamical speed for some fixed targets. In a large number of studies in this field, the construction of valid bounds for the evolution time is always the core mission, yet the physics behind it and some fundamental questions like which states can really fulfill the target, are ignored. Understanding the physics behind the bounds is at least as important as constructing attainable bounds. Here we provide an operational approach for the definition of the quantum speed limit, which utilizes the set of states that can fulfill the target to define the speed limit. Its performances in various scenarios have been investigated. For time-independent Hamiltonians, it is inverse-proportional to the difference between the highest and lowest energies. The fact that its attainability does not require a zero ground-state energy suggests it can be used as an indicator of quantum phase transitions. For time-dependent Hamiltonians, it is shown that contrary to the results given by existing bounds, the true speed limit should be independent of the time. Moreover, in the case of spontaneous emission, we find a counterintuitive phenomenon that a lousy purity can benefit the reduction of the quantum speed limit.

preprint2020arXiv

Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectors

Oriented object detection in aerial images is a challenging task as the objects in aerial images are displayed in arbitrary directions and are usually densely packed. Current oriented object detection methods mainly rely on two-stage anchor-based detectors. However, the anchor-based detectors typically suffer from a severe imbalance issue between the positive and negative anchor boxes. To address this issue, in this work we extend the horizontal keypoint-based object detector to the oriented object detection task. In particular, we first detect the center keypoints of the objects, based on which we then regress the box boundary-aware vectors (BBAVectors) to capture the oriented bounding boxes. The box boundary-aware vectors are distributed in the four quadrants of a Cartesian coordinate system for all arbitrarily oriented objects. To relieve the difficulty of learning the vectors in the corner cases, we further classify the oriented bounding boxes into horizontal and rotational bounding boxes. In the experiment, we show that learning the box boundary-aware vectors is superior to directly predicting the width, height, and angle of an oriented bounding box, as adopted in the baseline method. Besides, the proposed method competes favorably with state-of-the-art methods. Code is available at https://github.com/yijingru/BBAVectors-Oriented-Object-Detection.

preprint2020arXiv

Proximal Gradient Temporal Difference Learning: Stable Reinforcement Learning with Polynomial Sample Complexity

In this paper, we introduce proximal gradient temporal difference learning, which provides a principled way of designing and analyzing true stochastic gradient temporal difference learning algorithms. We show how gradient TD (GTD) reinforcement learning methods can be formally derived, not by starting from their original objective functions, as previously attempted, but rather from a primal-dual saddle-point objective function. We also conduct a saddle-point error analysis to obtain finite-sample bounds on their performance. Previous analyses of this class of algorithms use stochastic approximation techniques to prove asymptotic convergence, and do not provide any finite-sample analysis. We also propose an accelerated algorithm, called GTD2-MP, that uses proximal ``mirror maps'' to yield an improved convergence rate. The results of our theoretical analysis imply that the GTD family of algorithms are comparable and may indeed be preferred over existing least squares TD methods for off-policy learning, due to their linear complexity. We provide experimental results showing the improved performance of our accelerated gradient TD methods.

preprint2020arXiv

RDP-GAN: A Rényi-Differential Privacy based Generative Adversarial Network

Generative adversarial network (GAN) has attracted increasing attention recently owing to its impressive ability to generate realistic samples with high privacy protection. Without directly interactive with training examples, the generative model can be fully used to estimate the underlying distribution of an original dataset while the discriminative model can examine the quality of the generated samples by comparing the label values with the training examples. However, when GANs are applied on sensitive or private training examples, such as medical or financial records, it is still probable to divulge individuals' sensitive and private information. To mitigate this information leakage and construct a private GAN, in this work we propose a Rényi-differentially private-GAN (RDP-GAN), which achieves differential privacy (DP) in a GAN by carefully adding random noises on the value of the loss function during training. Moreover, we derive the analytical results of the total privacy loss under the subsampling method and cumulated iterations, which show its effectiveness on the privacy budget allocation. In addition, in order to mitigate the negative impact brought by the injecting noise, we enhance the proposed algorithm by adding an adaptive noise tuning step, which will change the volume of added noise according to the testing accuracy. Through extensive experimental results, we verify that the proposed algorithm can achieve a better privacy level while producing high-quality samples compared with a benchmark DP-GAN scheme based on noise perturbation on training gradients.

preprint2020arXiv

Regularized Off-Policy TD-Learning

We present a novel $l_1$ regularized off-policy convergent TD-learning method (termed RO-TD), which is able to learn sparse representations of value functions with low computational complexity. The algorithmic framework underlying RO-TD integrates two key ideas: off-policy convergent gradient TD methods, such as TDC, and a convex-concave saddle-point formulation of non-smooth convex optimization, which enables first-order solvers and feature selection using online convex regularization. A detailed theoretical and experimental analysis of RO-TD is presented. A variety of experiments are presented to illustrate the off-policy convergence, sparse feature selection capability and low computational cost of the RO-TD algorithm.

preprint2020arXiv

Robust Conditional GAN from Uncertainty-Aware Pairwise Comparisons

Conditional generative adversarial networks have shown exceptional generation performance over the past few years. However, they require large numbers of annotations. To address this problem, we propose a novel generative adversarial network utilizing weak supervision in the form of pairwise comparisons (PC-GAN) for image attribute editing. In the light of Bayesian uncertainty estimation and noise-tolerant adversarial training, PC-GAN can estimate attribute rating efficiently and demonstrate robust performance in noise resistance. Through extensive experiments, we show both qualitatively and quantitatively that PC-GAN performs comparably with fully-supervised methods and outperforms unsupervised baselines.

preprint2020arXiv

Shannon-Limit Approached Information Reconciliation for Quantum Key Distribution

Information reconciliation (IR) corrects the errors in sifted keys and ensures the correctness of quantum key distribution (QKD) systems. Polar codes-based IR schemes can achieve high reconciliation efficiency, however, the incidental high frame error rate decreases the secure key rate of QKD systems. In this article, we propose a Shannon-limit approached (SLA) IR scheme, which mainly contains two phases: the forward reconciliation phase and the acknowledgment reconciliation phase. In the forward reconciliation phase, the sifted key is divided into sub-blocks and performed with the improved block checked successive cancellation list (BC-SCL) decoder of polar codes. Afterwards, only the failure corrected sub-blocks perform the additional acknowledgment reconciliation phase, which decreases the frame error rate of the SLA IR scheme. The experimental results show that the overall failure probability of SLA IR scheme is decreased to $10^{-8}$ and the efficiency is improved to 1.091 with the IR block length of 128Mb. Furthermore, the efficiency of the proposed SLA IR scheme is 1.055, approached to Shannon-limit, when quantum bit error rate is 0.02 and the input scale of 1Gb, which is hundred times larger than the state-of-art implemented polar codes-based IR schemes.

preprint2020arXiv

Strategies for achieving high key rates in satellite-based QKD

Quantum key distribution (QKD) is a pioneering quantum technology on the brink of widespread deployment. Nevertheless, the distribution of secret keys beyond a few 100 kilometers at practical rates remains a major challenge. One approach to circumvent lossy terrestrial transmission of entangled photon pairs is the deployment of optical satellite links. Optimizing these non-static quantum links to yield the highest possible key rate is essential for their successful operation. We therefore developed a high-brightness polarization-entangled photon pair source and a receiver module with a fast steering mirror capable of satellite tracking. We employed this state-of-the-art hardware to distribute photons over a terrestrial free-space link with a distance of 143 km, and extracted secure key rates up to 300 bits per second. Contrary to fiber-based links, the channel loss in satellite downlinks is time-varying and the link time is limited to a few minutes. We therefore propose a model-based optimization of link parameters based on current channel and receiver conditions. This model and our field test will prove helpful in the design and operation of future satellite missions and advance the distribution of secret keys at high rates on a global scale.

preprint2020arXiv

Towards Playing Full MOBA Games with Deep Reinforcement Learning

MOBA games, e.g., Honor of Kings, League of Legends, and Dota 2, pose grand challenges to AI systems such as multi-agent, enormous state-action space, complex action control, etc. Developing AI for playing MOBA games has raised much attention accordingly. However, existing work falls short in handling the raw game complexity caused by the explosion of agent combinations, i.e., lineups, when expanding the hero pool in case that OpenAI's Dota AI limits the play to a pool of only 17 heroes. As a result, full MOBA games without restrictions are far from being mastered by any existing AI system. In this paper, we propose a MOBA AI learning paradigm that methodologically enables playing full MOBA games with deep reinforcement learning. Specifically, we develop a combination of novel and existing learning techniques, including curriculum self-play learning, policy distillation, off-policy adaption, multi-head value estimation, and Monte-Carlo tree-search, in training and playing a large pool of heroes, meanwhile addressing the scalability issue skillfully. Tested on Honor of Kings, a popular MOBA game, we show how to build superhuman AI agents that can defeat top esports players. The superiority of our AI is demonstrated by the first large-scale performance test of MOBA AI agent in the literature.

preprint2020arXiv

Understanding Global Loss Landscape of One-hidden-layer ReLU Networks, Part 1: Theory

For one-hidden-layer ReLU networks, we prove that all differentiable local minima are global inside differentiable regions. We give the locations and losses of differentiable local minima, and show that these local minima can be isolated points or continuous hyperplanes, depending on an interplay between data, activation pattern of hidden neurons and network size. Furthermore, we give necessary and sufficient conditions for the existence of saddle points as well as non-differentiable local minima, and their locations if they exist.

preprint2020arXiv

Understanding Global Loss Landscape of One-hidden-layer ReLU Networks, Part 2: Experiments and Analysis

The existence of local minima for one-hidden-layer ReLU networks has been investigated theoretically in [8]. Based on the theory, in this paper, we first analyze how big the probability of existing local minima is for 1D Gaussian data and how it varies in the whole weight space. We show that this probability is very low in most regions. We then design and implement a linear programming based approach to judge the existence of genuine local minima, and use it to predict whether bad local minima exist for the MNIST and CIFAR-10 datasets, and find that there are no bad differentiable local minima almost everywhere in weight space once some hidden neurons are activated by samples. These theoretical predictions are verified experimentally by showing that gradient descent is not trapped in the cells from which it starts. We also perform experiments to explore the count and size of differentiable cells in the weight space.

preprint2020arXiv

Variance-Reduced Off-Policy Memory-Efficient Policy Search

Off-policy policy optimization is a challenging problem in reinforcement learning (RL). The algorithms designed for this problem often suffer from high variance in their estimators, which results in poor sample efficiency, and have issues with convergence. A few variance-reduced on-policy policy gradient algorithms have been recently proposed that use methods from stochastic optimization to reduce the variance of the gradient estimate in the REINFORCE algorithm. However, these algorithms are not designed for the off-policy setting and are memory-inefficient, since they need to collect and store a large ``reference'' batch of samples from time to time. To achieve variance-reduced off-policy-stable policy optimization, we propose an algorithm family that is memory-efficient, stochastically variance-reduced, and capable of learning from off-policy samples. Empirical studies validate the effectiveness of the proposed approaches.

preprint2020arXiv

Video Saliency Prediction Using Enhanced Spatiotemporal Alignment Network

Due to a variety of motions across different frames, it is highly challenging to learn an effective spatiotemporal representation for accurate video saliency prediction (VSP). To address this issue, we develop an effective spatiotemporal feature alignment network tailored to VSP, mainly including two key sub-networks: a multi-scale deformable convolutional alignment network (MDAN) and a bidirectional convolutional Long Short-Term Memory (Bi-ConvLSTM) network. The MDAN learns to align the features of the neighboring frames to the reference one in a coarse-to-fine manner, which can well handle various motions. Specifically, the MDAN owns a pyramidal feature hierarchy structure that first leverages deformable convolution (Dconv) to align the lower-resolution features across frames, and then aggregates the aligned features to align the higher-resolution features, progressively enhancing the features from top to bottom. The output of MDAN is then fed into the Bi-ConvLSTM for further enhancement, which captures the useful long-time temporal information along forward and backward timing directions to effectively guide attention orientation shift prediction under complex scene transformation. Finally, the enhanced features are decoded to generate the predicted saliency map. The proposed model is trained end-to-end without any intricate post processing. Extensive evaluations on four VSP benchmark datasets demonstrate that the proposed method achieves favorable performance against state-of-the-art methods. The source codes and all the results will be released.

preprint2020arXiv

Zero-Shot Learning from Adversarial Feature Residual to Compact Visual Feature

Recently, many zero-shot learning (ZSL) methods focused on learning discriminative object features in an embedding feature space, however, the distributions of the unseen-class features learned by these methods are prone to be partly overlapped, resulting in inaccurate object recognition. Addressing this problem, we propose a novel adversarial network to synthesize compact semantic visual features for ZSL, consisting of a residual generator, a prototype predictor, and a discriminator. The residual generator is to generate the visual feature residual, which is integrated with a visual prototype predicted via the prototype predictor for synthesizing the visual feature. The discriminator is to distinguish the synthetic visual features from the real ones extracted from an existing categorization CNN. Since the generated residuals are generally numerically much smaller than the distances among all the prototypes, the distributions of the unseen-class features synthesized by the proposed network are less overlapped. In addition, considering that the visual features from categorization CNNs are generally inconsistent with their semantic features, a simple feature selection strategy is introduced for extracting more compact semantic visual features. Extensive experimental results on six benchmark datasets demonstrate that our method could achieve a significantly better performance than existing state-of-the-art methods by 1.2-13.2% in most cases.

preprint2019arXiv

Anharmonicity Induced Supersolidity In Spin-Orbit Coupled Bose-Einstein Condensates

Supersolid, a fascinating quantum state of matter, features novel phenomena such as the non-classical rotational inertia and transport anomalies. It is a long standing issue of the coexistence of superfluidity and broken translational symmetry in condensed matter physics. By recent experimental advances to create tunable synthetic spin-orbit coupling in ultracold gases, such highly controllable atomic systems would provide new possibilities to access supersolidity with no counterpart in solids. Here we report that the combination of anharmonicity of trapping potential and spin-orbit coupling will provide a new paradigm to achieve supersolids. By means of imaginary time evolution of the Gross-Pitaevskii equation, we demonstrate that a supersolid state can be found when considering a trapped Rashba-type spin-orbit coupled bosonic atoms loaded in a one-dimensional optical lattice. Furthermore, a skyrmion-anti-skyrmion lattice is associated with the appearance of such supersoildity, indicating the topological nontrivial properties of our proposed supersolids.

preprint2019arXiv

FeCaffe: FPGA-enabled Caffe with OpenCL for Deep Learning Training and Inference on Intel Stratix 10

Deep learning and Convolutional Neural Network (CNN) have becoming increasingly more popular and important in both academic and industrial areas in recent years cause they are able to provide better accuracy and result in classification, detection and recognition areas, compared to traditional approaches. Currently, there are many popular frameworks in the market for deep learning development, such as Caffe, TensorFlow, Pytorch, and most of frameworks natively support CPU and consider GPU as the mainline accelerator by default. FPGA device, viewed as a potential heterogeneous platform, still cannot provide a comprehensive support for CNN development in popular frameworks, in particular to the training phase. In this paper, we firstly propose the FeCaffe, i.e. FPGA-enabled Caffe, a hierarchical software and hardware design methodology based on the Caffe to enable FPGA to support mainline deep learning development features, e.g. training and inference with Caffe. Furthermore, we provide some benchmarks with FeCaffe by taking some classical CNN networks as examples, and further analysis of kernel execution time in details accordingly. Finally, some optimization directions including FPGA kernel design, system pipeline, network architecture, user case application and heterogeneous platform levels, have been proposed gradually to improve FeCaffe performance and efficiency. The result demonstrates the proposed FeCaffe is capable of supporting almost full features during CNN network training and inference respectively with high degree of design flexibility, expansibility and reusability for deep learning development. Compared to prior studies, our architecture can support more network and training settings, and current configuration can achieve 6.4x and 8.4x average execution time improvement for forward and backward respectively for LeNet.

preprint2019arXiv

Passively stable distribution of polarisation entanglement over 192 km of deployed optical fibre

Quantum key distribution (QKD) based on entangled photon pairs holds the potential for repeater-based quantum networks connecting clients over long distance. We demonstrate long-distance entanglement distribution by means of polarisation-entangled photon pairs through two successive deployed 96 km-long telecommunications fibres in the same submarine cable. One photon of each pair was detected directly after the source, while the other travelled the fibre cable in both directions for a total distance of 192 km and attenuation of 48 dB. The observed two-photon Bell state exhibited a fidelity 85% $\pm$ 2% and was stable over several hours. We employed neither active stabilisation of the quantum state nor chromatic dispersion compensation for the fibre.

Bo Liu

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

89 published item(s)

Cutscene Agent: An LLM Agent Framework for Automated 3D Cutscene Generation

MGML: A Plug-and-Play Meta-Guided Multi-Modal Learning Framework for Incomplete Multimodal Brain Tumor Segmentation

DeepSeek LLM: Scaling Open-Source Language Models with Longtermism

Query-Based Knowledge Sharing for Open-Vocabulary Multi-Label Classification

Async-fork: Mitigating Query Latency Spikes Incurred by the Fork-based Snapshot Mechanism from the OS Level

Metric Residual Networks for Sample Efficient Goal-Conditioned Reinforcement Learning

Principal Stratification with Time-to-Event Outcomes

Self-supervised Hypergraph Representation Learning for Sociological Analysis

A multi-task learning for cavitation detection and cavitation intensity recognition of valve acoustic signals

An acoustic signal cavitation detection framework based on XGBoost with adaptive selection feature engineering

An Iterative Co-Training Transductive Framework for Zero Shot Learning

Appending Information Reconciliation for Quantum Key Distribution

APPL: Adaptive Planner Parameter Learning

Bismut-Cheeger eta form and higher spectral flow

Boosting Multi-Label Image Classification with Complementary Parallel Self-Distillation

Broad Emission and Absorption Line Outflows in the Quasar SDSS J163345.22+512748.4

Continual Learning and Private Unlearning

D-Unet: A Dual-encoder U-Net for Image Splicing Forgery Detection and Localization

Design and Commissioning of A Beam Distribution System for Multiple Undulator Line Operation of the SXFEL-UF

Effective Mutation Rate Adaptation through Group Elite Selection

Enantiodiscrimination of chiral molecules via quantum correlation function

HardBoost: Boosting Zero-Shot Learning with Hard Classes

Implicit semantic-based personalized micro-videos recommendation

Label-only Model Inversion Attack: The Attack that Requires the Least Information

Language-Level Semantics Conditioned 3D Point Cloud Segmentation

Low-temperature specific-heat studies on two square-kagome antiferromagnets

Mean-Variance Policy Iteration for Risk-Averse Reinforcement Learning

Modeling User Behavior with Graph Convolution for Personalized Product Search

Motion Planning and Control for Mobile Robot Navigation Using Machine Learning: a Survey

Multi-wavelength Campaign on the Super-Eddington NLS1 RX J0134.2-4258 -- I. Peculiar X-ray Spectra and Variability

Neutron-diffraction and linear {Grüneisen} parameter studies of magnetism in NdFe$_2$Ga$_8$

One Parameter Defense -- Defending against Data Inference Attacks via Differential Privacy

PRIMA: Planner-Reasoner Inside a Multi-task Reasoning Agent

Real-world challenges for multi-agent reinforcement learning in grid-interactive buildings

Regional-Local Adversarially Learned One-Class Classifier Anomalous Sound Detection in Global Long-Term Space

Semantic-diversity transfer network for generalized zero-shot learning via inner disagreement based OOD detector

STOPS: Short-Term-based Volatility-controlled Policy Search and its Global Convergence

Trustworthy AI: From Principles to Practices

Unravelling Token Ecosystem of EOSIO Blockchain

Video object tracking based on YOLOv7 and DeepSORT

A Lifelong Learning Approach to Mobile Robot Navigation

Agile Robot Navigation through Hallucinated Learning and Sober Deployment

Artificial intelligence enabled radio propagation for communications-Part I: Channel characterization and antenna-channel optimization

Artificial intelligence enabled radio propagation for communications-Part II: Scenario identification and channel modeling

Discrete Knowledge Graph Embedding based on Discrete Optimization

Enantio-conversion of chiral mixtures via optical pumping

Enantio-specific state transfer for symmetric-top chiral molecules

Heterogeneous Hypergraph Embedding for Graph Classification

IdentityDP: Differential Private Identification Protection for Face Images

Manipulating Goldstone modes via the superradiant light in a bosonic lattice gas inside a cavity

Self-Amplification of Coherent Energy Modulation in Seeded Free-Electron Lasers

SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering

Spurious Local Minima Are Common for Deep Neural Networks with Piecewise Linear Activations

Superpoint-guided Semi-supervised Semantic Segmentation of 3D Point Clouds

Topological semimetal and superfluid of s-wave interacting fermionic atoms in an orbital optical lattice

Toward Agile Maneuvers in Highly Constrained Spaces: Learning from Hallucination

A Convolutional Neural Network with Parallel Multi-Scale Spatial Pooling to Detect Temporal Changes in SAR Images

A Light-Weighted Convolutional Neural Network for Bitemporal SAR Image Change Detection

Adaptive Graph Convolutional Network with Attention Graph Clustering for Co-saliency Detection

APPLD: Adaptive Planner Parameter Learning from Demonstration

Differential K-theory and localization formula for $η$-invariants

Dual Temporal Memory Network for Efficient Video Object Segmentation

DualSMC: Tunneling Differentiable Filtering and Planning under Continuous POMDPs

Effect of Dzyaloshinskii-Moriya interaction on magnetic vortex switching driven by radial spin waves

Estimation of genome size using k-mer frequencies from corrected long reads

Evolving the pulmonary nodules diagnosis from classical approaches to deep learning aided decision support: three decades development course and future prospect

Exploit Clues from Views: Self-Supervised and Regularized Learning for Multiview Object Recognition

Fast Enhancement for Non-Uniform Illumination Images using Light-weight CNNs

Few-Shot Open-Set Recognition using Meta-Learning

Finite-Sample Analysis of Proximal Gradient TD Algorithms

Meta-Learning with Network Pruning

Neutron spin resonance in a quasi-two-dimensional iron-based superconductor