Search Results for author: Jun Wang

Found 428 papers, 136 papers with code

Measuring and Mitigating Name Biases in Neural Machine Translation

no code implementations ACL 2022 Jun Wang, Benjamin Rubinstein, Trevor Cohn

In this paper we describe a new source of bias prevalent in NMT systems, relating to translations of sentences containing person names.

Data Augmentation Machine Translation +2

数字人文视角下的《史记》《汉书》比较研究(A Comparative Study of Shiji and Hanshu from the Perspective of Digital Humanities)

no code implementations CCL 2022 Zekun Deng, Hao Yang, Jun Wang

"《史记》和《汉书》具有经久不衰的研究价值。尽管两书异同的研究已经较为丰富, 但研究的全面性、完备性、科学性、客观性均仍显不足。在数字人文的视角下, 本文利用计算语言学方法, 通过对字、词、命名实体、段落等的多粒度、多角度分析, 开展对于《史》《汉》的比较研究。首先, 本文对于《史》《汉》中的字、词、命名实体的分布和特点进行对比, 以遍历穷举的考察方式提炼出两书在主要内容上的相同点与不同点, 揭示了汉武帝之前和汉武帝到西汉灭亡两段历史时期在政治、文化、思想上的重要变革与承袭。其次, 本文使用一种融入命名实体作为外部特征的文本相似度算法对于《史记》《汉书》的异文进行自动发现, 成功识别出过去研究者通过人工手段没有发现的袭用段落, 使得我们对于《史》《汉》的承袭关系形成更加完整和立体的认识。再次, 本文通过计算异文段落之间的最长公共子序列来自动得出两段异文之间存在的差异, 从宏观统计上证明了《汉书》文字风格《史记》的差别, 并从微观上进一步对二者语言特点进行了阐释, 为理解《史》《汉》异文特点提供了新的角度和启发。本研究站在数字人文的视域下, 利用先进的计算方法对于传世千年的中国古代经典进行了再审视、再发现, 其方法对于今人研究古籍有一定的借鉴价值。”

Eureka: Neural Insight Learning for Knowledge Graph Reasoning

no code implementations COLING 2022 Alex X. Zhang, Xun Liang, Bo Wu, Xiangping Zheng, Sensen Zhang, Yuhui Guo, Jun Wang, Xinyao Liu

The human recognition system has presented the remarkable ability to effortlessly learn novel knowledge from only a few trigger events based on prior knowledge, which is called insight learning.

Few-Shot Learning

Detecting Health Advice in Medical Research Literature

1 code implementation EMNLP 2021 Yingya Li, Jun Wang, Bei Yu

We also conducted a case study that applied this prediction model to retrieve specific health advice on COVID-19 treatments from LitCovid, a large COVID research literature portal, demonstrating the usefulness of retrieving health advice sentences as an advanced research literature navigation function for health researchers and the general public.


PA Ph&Tech at SemEval-2022 Task 11: NER Task with Ensemble Embedding from Reinforcement Learning

no code implementations SemEval (NAACL) 2022 Qizhi Lin, Changyu Hou, Xiaopeng Wang, Jun Wang, Yixuan Qiao, Peng Jiang, Xiandi Jiang, Benqi Wang, Qifeng Xiao

From pretrained contextual embedding to document-level embedding, the selection and construction of embedding have drawn more and more attention in the NER domain in recent research.

NER Zero-Shot Learning

Incorporating Deep Syntactic and Semantic Knowledge for Chinese Sequence Labeling with GCN

no code implementations3 Jun 2023 Xuemei Tang, Jun Wang, Qi Su

Recently, it is quite common to integrate Chinese sequence labeling results to enhance syntactic and semantic parsing.

Chinese Word Segmentation Part-Of-Speech Tagging +1

GRD: A Generative Approach for Interpretable Reward Redistribution in Reinforcement Learning

no code implementations28 May 2023 Yudi Zhang, Yali Du, Biwei Huang, Ziyan Wang, Jun Wang, Meng Fang, Mykola Pechenizkiy

While the majority of current approaches construct the reward redistribution in an uninterpretable manner, we propose to explicitly model the contributions of state and action from a causal perspective, resulting in an interpretable return decomposition.


Large language models improve Alzheimer's disease diagnosis using multi-modality data

no code implementations26 May 2023 Yingjie Feng, Jun Wang, Xianfeng GU, Xiaoyin Xu, Min Zhang

In diagnosing challenging conditions such as Alzheimer's disease (AD), imaging is an important reference.

Language Modelling

IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks

1 code implementation25 May 2023 Xuanli He, Jun Wang, Benjamin Rubinstein, Trevor Cohn

Backdoor attacks are an insidious security threat against machine learning models.

UNITE: A Unified Benchmark for Text-to-SQL Evaluation

no code implementations25 May 2023 Wuwei Lan, Zhiguo Wang, Anuj Chauhan, Henghui Zhu, Alexander Li, Jiang Guo, Sheng Zhang, Chung-Wei Hang, Joseph Lilien, Yiqun Hu, Lin Pan, Mingwen Dong, Jun Wang, Jiarong Jiang, Stephen Ash, Vittorio Castelli, Patrick Ng, Bing Xiang

A practical text-to-SQL system should generalize well on a wide variety of natural language questions, unseen database schemas, and novel SQL query structures.


Multi-scale Efficient Graph-Transformer for Whole Slide Image Classification

no code implementations25 May 2023 Saisai Ding, Juncheng Li, Jun Wang, Shihui Ying, Jun Shi

The key idea of MEGT is to adopt two independent Efficient Graph-based Transformer (EGT) branches to process the low-resolution and high-resolution patch embeddings (i. e., tokens in a Transformer) of WSIs, respectively, and then fuse these tokens via a multi-scale feature fusion module (MFFM).

Image Classification whole slide images

Collaborative Recommendation Model Based on Multi-modal Multi-view Attention Network: Movie and literature cases

no code implementations24 May 2023 Zheng Hu, Shi-Min Cai, Jun Wang, Tao Zhou

Thus, the representation of users' dislikes should be integrated into the user modelling when we construct a collaborative recommendation model.

Decoupled Rationalization with Asymmetric Learning Rates: A Flexible Lipschitz Restraint

1 code implementation23 May 2023 Wei Liu, Jun Wang, Haozhao Wang, Ruixuan Li, Yang Qiu, Yuankai Zhang, Jie Han, Yixiong Zou

However, such a cooperative game may incur the degeneration problem where the predictor overfits to the uninformative pieces generated by a not yet well-trained generator and in turn, leads the generator to converge to a sub-optimal model that tends to select senseless pieces.

Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation

no code implementations19 May 2023 Xuanli He, Qiongkai Xu, Jun Wang, Benjamin Rubinstein, Trevor Cohn

Modern NLP models are often trained over large untrusted datasets, raising the potential for a malicious adversary to compromise model behaviour.

An Empirical Study on Google Research Football Multi-agent Scenarios

1 code implementation16 May 2023 Yan Song, He Jiang, Zheng Tian, Haifeng Zhang, Yingping Zhang, Jiangcheng Zhu, Zonghong Dai, Weinan Zhang, Jun Wang

Few multi-agent reinforcement learning (MARL) research on Google Research Football (GRF) focus on the 11v11 multi-agent full-game scenario and to the best of our knowledge, no open benchmark on this scenario has been released to the public.

Benchmarking Multi-agent Reinforcement Learning +1

MGR: Multi-generator Based Rationalization

1 code implementation8 May 2023 Wei Liu, Haozhao Wang, Jun Wang, Ruixuan Li, Xinyang Li, Yuankai Zhang, Yang Qiu

Rationalization is to employ a generator and a predictor to construct a self-explaining NLP model in which the generator selects a subset of human-intelligible pieces of the input text to the following predictor.

Leaf Cultivar Identification via Prototype-enhanced Learning

no code implementations5 May 2023 Yiyi Zhang, Zhiwen Ying, Ying Zheng, Cuiling Wu, Nannan Li, Jun Wang, Xianzhong Feng, Xiaogang Xu

Plant leaf identification is crucial for biodiversity protection and conservation and has gradually attracted the attention of academia in recent years.

Fine-Grained Image Classification

Filter Pruning via Filters Similarity in Consecutive Layers

no code implementations26 Apr 2023 Xiaorui Wang, Jun Wang, Xin Tang, Peng Gao, Rui Fang, Guotong Xie

Filter pruning is widely adopted to compress and accelerate the Convolutional Neural Networks (CNNs), but most previous works ignore the relationship between filters and channels in different layers.

Structure Diagram Recognition in Financial Announcements

no code implementations26 Apr 2023 Meixuan Qiao, Jun Wang, Junfu Xiang, Qiyu Hou, Ruixuan Li

Accurately extracting structured data from structure diagrams in financial announcements is of great practical importance for building financial knowledge graphs and further improving the efficiency of various financial applications.

Knowledge Graphs

Selective and Collaborative Influence Function for Efficient Recommendation Unlearning

no code implementations20 Apr 2023 Yuyuan Li, Chaochao Chen, Xiaolin Zheng, Yizhao Zhang, Biao Gong, Jun Wang

In this paper, we first identify two main disadvantages of directly applying existing unlearning methods in the context of recommendation, i. e., (i) unsatisfactory efficiency for large-scale recommendation models and (ii) destruction of collaboration across users and items.

Recommendation Systems

Open Set Classification of GAN-based Image Manipulations via a ViT-based Hybrid Architecture

no code implementations11 Apr 2023 Jun Wang, Omran Alamayreh, Benedetta Tondi, Mauro Barni

Classification of AI-manipulated content is receiving great attention, for distinguishing different types of manipulations.

Classification Face Generation

AutoKary2022: A Large-Scale Densely Annotated Dataset for Chromosome Instance Segmentation

1 code implementation28 Mar 2023 Dan You, Pengcheng Xia, Qiuzhu Chen, Minghui Wu, Suncheng Xiang, Jun Wang

Automated chromosome instance segmentation from metaphase cell microscopic images is critical for the diagnosis of chromosomal disorders (i. e., karyotype analysis).

Instance Segmentation Semantic Segmentation

DOMINO: Visual Causal Reasoning with Time-Dependent Phenomena

no code implementations12 Mar 2023 Jun Wang, Klaus Mueller

Furthermore, since an effect can be a cause of other effects, we allow users to aggregate different temporal cause-effect relations found with our method into a visual flow diagram to enable the discovery of temporal causal networks.

Time Series Analysis

DistilPose: Tokenized Pose Regression with Heatmap Distillation

1 code implementation CVPR 2023 Suhang Ye, Yingyi Zhang, Jie Hu, Liujuan Cao, Shengchuan Zhang, Lei Shen, Jun Wang, Shouhong Ding, Rongrong Ji

Specifically, DistilPose maximizes the transfer of knowledge from the teacher model (heatmap-based) to the student model (regression-based) through Token-distilling Encoder (TDE) and Simulated Heatmaps.

Knowledge Distillation Pose Estimation +1

Order Matters: Agent-by-agent Policy Optimization

no code implementations13 Feb 2023 Xihuai Wang, Zheng Tian, Ziyu Wan, Ying Wen, Jun Wang, Weinan Zhang

In this paper, we propose the \textbf{A}gent-by-\textbf{a}gent \textbf{P}olicy \textbf{O}ptimization (A2PO) algorithm to improve the sample efficiency and retain the guarantees of monotonic improvement for each agent during training.

Building Intelligence in the Mechanical Domain -- Harvesting the Reservoir Computing Power in Origami to Achieve Information Perception Tasks

no code implementations10 Feb 2023 Jun Wang, Suyi Li

In this paper, we experimentally examine the cognitive capability of a simple, paper-based Miura-ori -- using the physical reservoir computing framework -- to achieve different information perception tasks.

Stability Constrained OPF in Microgrids: A Chance Constrained Optimization Framework with Non-Gaussian Uncertainty

no code implementations4 Feb 2023 Jun Wang, Yue Song, David John Hill, Yunhe Hou, Feilong Fan

To figure out the stability issues brought by renewable energy sources (RES) with non-Gaussian uncertainties in isolated microgrids, this paper proposes a chance constrained stability constrained optimal power flow (CC-SC-OPF) model.


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

no code implementations19 Jan 2023 Chengjie Zhao, Jun Wang, Wei Huang, Xiaonan Chen, Tianfu Qi

Under MGIN channel, classical communication signal schemes and corresponding detection methods usually can not achieve desirable performance as they are optimized with respect to WGN.

PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI Coordination

1 code implementation16 Jan 2023 Xingzhou Lou, Jiaxian Guo, Junge Zhang, Jun Wang, Kaiqi Huang, Yali Du

We conduct experiments on the Overcooked environment, and evaluate the zero-shot human-AI coordination performance of our method with both behavior-cloned human proxies and real humans.

On Realization of Intelligent Decision-Making in the Real World: A Foundation Decision Model Perspective

1 code implementation24 Dec 2022 Ying Wen, Ziyu Wan, Ming Zhou, Shufang Hou, Zhe Cao, Chenyang Le, Jingxiao Chen, Zheng Tian, Weinan Zhang, Jun Wang

The pervasive uncertainty and dynamic nature of real-world environments present significant challenges for the widespread implementation of machine-driven Intelligent Decision-Making (IDM) systems.

Decision Making Image Captioning +2

Importance of Synthesizing High-quality Data for Text-to-SQL Parsing

no code implementations17 Dec 2022 Yiyun Zhao, Jiarong Jiang, Yiqun Hu, Wuwei Lan, Henry Zhu, Anuj Chauhan, Alexander Li, Lin Pan, Jun Wang, Chung-Wei Hang, Sheng Zhang, Marvin Dong, Joe Lilien, Patrick Ng, Zhiguo Wang, Vittorio Castelli, Bing Xiang

In this paper, we first examined the existing synthesized datasets and discovered that state-of-the-art text-to-SQL algorithms did not further improve on popular benchmarks when trained with augmented synthetic data.

SQL Parsing SQL-to-Text +2

Sim-to-Real Transfer for Quadrupedal Locomotion via Terrain Transformer

no code implementations15 Dec 2022 Hang Lai, Weinan Zhang, Xialin He, Chen Yu, Zheng Tian, Yong Yu, Jun Wang

Deep reinforcement learning has recently emerged as an appealing alternative for legged locomotion over multiple terrains by training a policy in physical simulation and then transferring it to the real world (i. e., sim-to-real transfer).

Decision Making

TriNet: stabilizing self-supervised learning from complete or slow collapse on ASR

no code implementations12 Dec 2022 Lixin Cao, Jun Wang, Ben Yang, Dan Su, Dong Yu

Self-supervised learning (SSL) models confront challenges of abrupt informational collapse or slow dimensional collapse.

Self-Supervised Learning

Targeted Adversarial Attacks against Neural Network Trajectory Predictors

no code implementations8 Dec 2022 Kaiyuan Tan, Jun Wang, Yiannis Kantaros

To bridge this gap, in this paper, we propose a targeted adversarial attack against DNN models for trajectory forecasting tasks.

Adversarial Attack Trajectory Forecasting

C3N:Content-Constrained Convolutional Network for Mural Image Completion

1 code implementation Neural Computing and Applications 2022 Xianlin Peng, Huayu Zhao, Xiaoyu Wang, Yongqin Zhang, Zhan Li, Qunxi Zhang, Jun Wang, Jinye Peng, Haida Liang

Our network also uses dual-domain partial convolution with a mask for computing on only valid points, whereas the mask is updated for the next layer.

Image Inpainting

WAIR-D: Wireless AI Research Dataset

no code implementations5 Dec 2022 Yourui Huangfu, Jian Wang, Shengchen Dai, Rong Li, Jun Wang, Chongwen Huang, Zhaoyang Zhang

The statistical data hinder the trained AI models from further fine-tuning for a specific scenario, and ray-tracing data with limited environments lower down the generalization capability of the trained AI models.

Intelligent Communication

Long-tail Cross Modal Hashing

no code implementations28 Nov 2022 Zijun Gao, Jun Wang, Guoxian Yu, Zhongmin Yan, Carlotta Domeniconi, Jinglin Zhang

LtCMH firstly adopts auto-encoders to mine the individuality and commonality of different modalities by minimizing the dependency between the individuality of respective modalities and by enhancing the commonality of these modalities.

Reinforcement Causal Structure Learning on Order Graph

no code implementations22 Nov 2022 Dezhi Yang, Guoxian Yu, Jun Wang, Zhengtian Wu, Maozu Guo

In this paper, we propose {Reinforcement Causal Structure Learning on Order Graph} (RCL-OG) that uses order graph instead of MCMC to model different DAG topological orderings and to reduce the problem size.

Causal Discovery Q-Learning

Learning Cooperative Oversubscription for Cloud by Chance-Constrained Multi-Agent Reinforcement Learning

no code implementations21 Nov 2022 Junjie Sheng, Lu Wang, Fangkai Yang, Bo Qiao, Hang Dong, Xiangfeng Wang, Bo Jin, Jun Wang, Si Qin, Saravan Rajmohan, QIngwei Lin, Dongmei Zhang

To address these two limitations, this paper formulates the oversubscription for cloud as a chance-constrained optimization problem and propose an effective Chance Constrained Multi-Agent Reinforcement Learning (C2MARL) method to solve this problem.

Multi-agent Reinforcement Learning reinforcement-learning +1

Contextual Transformer for Offline Meta Reinforcement Learning

no code implementations15 Nov 2022 Runji Lin, Ye Li, Xidong Feng, Zhaowei Zhang, Xian Hong Wu Fung, Haifeng Zhang, Jun Wang, Yali Du, Yaodong Yang

Firstly, we propose prompt tuning for offline RL, where a context vector sequence is concatenated with the input to guide the conditional policy generation.

D4RL Meta Reinforcement Learning +4

CAMANet: Class Activation Map Guided Attention Network for Radiology Report Generation

no code implementations2 Nov 2022 Jun Wang, Abhir Bhalerao, Terry Yin, Simon See, Yulan He

Radiology report generation (RRG) has gained increasing research attention because of its huge potential to mitigate medical resource shortages and aid the process of disease decision making by radiologists.

Decision Making

Number-Adaptive Prototype Learning for 3D Point Cloud Semantic Segmentation

no code implementations18 Oct 2022 Yangheng Zhao, Jun Wang, Xiaolong Li, Yue Hu, Ce Zhang, Yanfeng Wang, Siheng Chen

Instead of learning a single prototype for each class, in this paper, we propose to use an adaptive number of prototypes to dynamically describe the different point patterns within a semantic class.

3D Semantic Segmentation Scene Understanding

Optimizing Vision Transformers for Medical Image Segmentation

1 code implementation14 Oct 2022 Qianying Liu, Chaitanya Kaul, Jun Wang, Christos Anagnostopoulos, Roderick Murray-Smith, Fani Deligianni

For medical image semantic segmentation (MISS), Vision Transformers have emerged as strong alternatives to convolutional neural networks thanks to their inherent ability to capture long-range correlations.

Domain Adaptation Image Segmentation +2

Detecting Backdoors in Deep Text Classifiers

no code implementations11 Oct 2022 You Guo, Jun Wang, Trevor Cohn

Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word or phrase to an input.

Data Poisoning text-classification +1

DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases

1 code implementation30 Sep 2022 Donghan Yu, Sheng Zhang, Patrick Ng, Henghui Zhu, Alexander Hanbo Li, Jun Wang, Yiqun Hu, William Wang, Zhiguo Wang, Bing Xiang

Question answering over knowledge bases (KBs) aims to answer natural language questions with factual information such as entities and relations in KBs.

Entity Linking Question Answering +2

Improving Text-to-SQL Semantic Parsing with Fine-grained Query Understanding

no code implementations28 Sep 2022 Jun Wang, Patrick Ng, Alexander Hanbo Li, Jiarong Jiang, Zhiguo Wang, Ramesh Nallapati, Bing Xiang, Sudipta Sengupta

When synthesizing a SQL query, there is no explicit semantic information of NLQ available to the parser which leads to undesirable generalization performance.

NER Semantic Parsing +1

A Spatial-channel-temporal-fused Attention for Spiking Neural Networks

no code implementations22 Sep 2022 Wuque Cai, Hongze Sun, Rui Liu, Yan Cui, Jun Wang, Yang Xia, Dezhong Yao, Daqing Guo

Spiking neural networks (SNNs) mimic brain computational strategies, and exhibit substantial capabilities in spatiotemporal information processing.

Scale Attention for Learning Deep Face Representation: A Study Against Visual Scale Variation

no code implementations19 Sep 2022 Hailin Shi, Hang Du, Yibo Hu, Jun Wang, Dan Zeng, Ting Yao

Such multi-shot scheme brings inference burden, and the predefined scales inevitably have gap from real data.

Face Recognition

FR: Folded Rationalization with a Unified Encoder

1 code implementation17 Sep 2022 Wei Liu, Haozhao Wang, Jun Wang, Ruixuan Li, Chao Yue, Yuankai Zhang

Conventional works generally employ a two-phase model in which a generator selects the most important pieces, followed by a predictor that makes predictions based on the selected pieces.

ESSumm: Extractive Speech Summarization from Untranscribed Meeting

no code implementations14 Sep 2022 Jun Wang

Extensive results on two well-known meeting datasets (AMI and ICSI corpora) show the effectiveness of our direct speech-based method to improve the summarization quality with untranscribed data.

speech-recognition Speech Recognition

Parameter Estimation of Mixed Gaussian-Impulsive Noise: An U-net++ Based Method

no code implementations6 Sep 2022 Tianfu Qi, Jun Wang, Xiaonan Chen, Wei Huang

In many scenarios, the communication system suffers from both Gaussian white noise and non-Gaussian impulsive noise.

SPCNet: Stepwise Point Cloud Completion Network

no code implementations5 Sep 2022 Fei Hu, Honghua Chen, Xuequan Lu, Zhe Zhu, Jun Wang, Weiming Wang, Fu Lee Wang, Mingqiang Wei

We propose a novel stepwise point cloud completion network (SPCNet) for various 3D models with large missings.

Point Cloud Completion

Semi-Centralised Multi-Agent Reinforcement Learning with Policy-Embedded Training

no code implementations2 Sep 2022 Taher Jafferjee, Juliusz Ziomek, Tianpei Yang, Zipeng Dai, Jianhong Wang, Matthew Taylor, Kun Shao, Jun Wang, David Mguni

Because MARL agents explore and update their policies during training, these observations often provide poor predictions about other agents' behaviour and the expected return for a given action.

Multi-agent Reinforcement Learning reinforcement-learning +2

Which country is this picture from? New data and methods for DNN-based country recognition

1 code implementation2 Sep 2022 Omran Alamayreh, Giovanna Maria Dimitri, Jun Wang, Benedetta Tondi, Mauro Barni

Notably, we found that asking the network to identify the country provides better results than estimating the geo-coordinates and then tracing them back to the country where the picture was taken.

Geometric and Learning-based Mesh Denoising: A Comprehensive Survey

no code implementations2 Sep 2022 Honghua Chen, Mingqiang Wei, Jun Wang

In this work, we provide a comprehensive review of the advances in mesh denoising, containing both traditional geometric approaches and recent learning-based methods.


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

no code implementations30 Aug 2022 Xintong Qin, Zhengyu Song, Tianwei Hou, Wenjuan Yu, Jun Wang, Xin Sun

The unmanned aerial vehicle (UAV) enabled mobile edge computing (MEC) has been deemed a promising paradigm to provide ubiquitous communication and computing services for the Internet of Things (IoT).


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

no code implementations30 Aug 2022 Zhengyu Song, Xintong Qin, Yuanyuan Hao, Tianwei Hou, Jun Wang, Xin Sun

Driven by the visions of Internet of Things (IoT), there is an ever-increasing demand for computation resources of IoT users to support diverse applications.

Edge-computing Scheduling

MODNet: Multi-offset Point Cloud Denoising Network Customized for Multi-scale Patches

1 code implementation30 Aug 2022 Anyi Huang, Qian Xie, Zhoutao Wang, Dening Lu, Mingqiang Wei, Jun Wang

Second, a multi-scale perception module is designed to embed multi-scale geometric information for each scale feature and regress multi-scale weights to guide a multi-offset denoising displacement.


Dual Representation Learning for One-Step Clustering of Multi-View Data

no code implementations30 Aug 2022 Wei zhang, Zhaohong Deng, Kup-Sze Choi, Jun Wang, Shitong Wang

Meanwhile, to make the representation learning more specific to the clustering task, a one-step learning framework is proposed to integrate representation learning and clustering partition as a whole.

Representation Learning

Lane Change Classification and Prediction with Action Recognition Networks

no code implementations24 Aug 2022 Kai Liang, Jun Wang, Abhir Bhalerao

Previous works often adopt physical variables such as driving speed, acceleration and so forth for lane change classification.

Action Recognition Autonomous Driving +2

AA-Forecast: Anomaly-Aware Forecast for Extreme Events

1 code implementation21 Aug 2022 Ashkan Farhangi, Jiang Bian, Arthur Huang, Haoyi Xiong, Jun Wang, Zhishan Guo

Moreover, the framework employs a dynamic uncertainty optimization algorithm that reduces the uncertainty of forecasts in an online manner.

Management Time Series Analysis

Multi-View Pre-Trained Model for Code Vulnerability Identification

no code implementations10 Aug 2022 Xuxiang Jiang, Yinhao Xiao, Jun Wang, Wei zhang

Vulnerability identification is crucial for cyber security in the software-related industry.

Contrastive Learning

A high-resolution dynamical view on momentum methods for over-parameterized neural networks

no code implementations8 Aug 2022 Xin Liu, Wei Tao, Jun Wang, Zhisong Pan

Due to the simplicity and efficiency of the first-order gradient method, it has been widely used in training neural networks.

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

1 code implementation4 Aug 2022 Zhilei Chen, Honghua Chen, Lina Gong, Xuefeng Yan, Jun Wang, Yanwen Guo, Jing Qin, Mingqiang Wei

High-confidence overlap prediction and accurate correspondences are critical for cutting-edge models to align paired point clouds in a partial-to-partial manner.

Point Cloud Registration

TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation

1 code implementation3 Aug 2022 Jun Wang, Mingfei Gao, Yuqian Hu, Ramprasaath R. Selvaraju, Chetan Ramaiah, ran Xu, Joseph F. JaJa, Larry S. Davis

To address this deficiency, we develop a new method to generate high-quality and diverse QA pairs by explicitly utilizing the existing rich text available in the scene context of each image.

Answer Generation Question-Answer-Generation +3

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

1 code implementation2 Aug 2022 Jakub Grudzien Kuba, Xidong Feng, Shiyao Ding, Hao Dong, Jun Wang, Yaodong Yang

The necessity for cooperation among intelligent machines has popularised cooperative multi-agent reinforcement learning (MARL) in the artificial intelligence (AI) research community.

Multi-agent Reinforcement Learning

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

no code implementations1 Aug 2022 Zhe Zhu, Liangliang Nan, Haoran Xie, Honghua Chen, Mingqiang Wei, Jun Wang, Jing Qin

The first module transfers the intrinsic shape characteristics from single images to guide the geometry generation of the missing regions of point clouds, in which we propose IPAdaIN to embed the global features of both the image and the partial point cloud into completion.

Point Cloud Completion

Scalable Model-based Policy Optimization for Decentralized Networked Systems

2 code implementations13 Jul 2022 Yali Du, Chengdong Ma, Yuchen Liu, Runji Lin, Hao Dong, Jun Wang, Yaodong Yang

Reinforcement learning algorithms require a large amount of samples; this often limits their real-world applications on even simple tasks.

Cross-modal Prototype Driven Network for Radiology Report Generation

1 code implementation11 Jul 2022 Jun Wang, Abhir Bhalerao, Yulan He

Radiology report generation (RRG) aims to describe automatically a radiology image with human-like language and could potentially support the work of radiologists, reducing the burden of manual reporting.

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

1 code implementation7 Jul 2022 Chengfeng Zhou, Songchang Chen, Chenming Xu, Jun Wang, Feng Liu, Chun Zhang, Juan Ye, Hefeng Huang, Dahong Qian

In this study, we present a novel normalization technique called window normalization (WIN) to improve the model generalization on heterogeneous medical images, which is a simple yet effective alternative to existing normalization methods.

Breast Cancer Detection Out-of-Distribution Generalization

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

no code implementations2 Jul 2022 Honghua Chen, Zeyong Wei, Yabin Xu, Mingqiang Wei, Jun Wang

Low-overlap regions between paired point clouds make the captured features very low-confidence, leading cutting edge models to point cloud registration with poor quality.

Point Cloud Registration

Effects of Safety State Augmentation on Safe Exploration

1 code implementation6 Jun 2022 Aivar Sootla, Alexander I. Cowen-Rivers, Jun Wang, Haitham Bou Ammar

We further show that Simmer can stabilize training and improve the performance of safe RL with average constraints.

Reinforcement Learning (RL) Safe Exploration +1

Timing is Everything: Learning to Act Selectively with Costly Actions and Budgetary Constraints

no code implementations31 May 2022 David Mguni, Aivar Sootla, Juliusz Ziomek, Oliver Slumbers, Zipeng Dai, Kun Shao, Jun Wang

In this paper, we introduce a reinforcement learning (RL) framework named \textbf{L}earnable \textbf{I}mpulse \textbf{C}ontrol \textbf{R}einforcement \textbf{A}lgorithm (LICRA), for learning to optimally select both when to act and which actions to take when actions incur costs.

Reinforcement Learning (RL)

Pseudo-Data based Self-Supervised Federated Learning for Classification of Histopathological Images

no code implementations31 May 2022 Jun Shi, Yuanming Zhang, Zheng Li, Xiangmin Han, Saisai Ding, Jun Wang, Shihui Ying

In this work, we propose a pseudo-data based self-supervised federated learning (FL) framework, named SSL-FT-BT, to improve both the diagnostic accuracy and generalization of CAD models.

Contrastive Learning Federated Learning +1

A Game-Theoretic Framework for Managing Risk in Multi-Agent Systems

no code implementations30 May 2022 Oliver Slumbers, David Henry Mguni, Stephen Marcus McAleer, Stefano B. Blumberg, Jun Wang, Yaodong Yang

Although there are equilibrium concepts in game theory that take into account risk aversion, they either assume that agents are risk-neutral with respect to the uncertainty caused by the actions of other agents, or they are not guaranteed to exist.

Autonomous Driving Multi-agent Reinforcement Learning

SEREN: Knowing When to Explore and When to Exploit

no code implementations30 May 2022 Changmin Yu, David Mguni, Dong Li, Aivar Sootla, Jun Wang, Neil Burgess

Efficient reinforcement learning (RL) involves a trade-off between "exploitative" actions that maximise expected reward and "explorative'" ones that sample unvisited states.

Reinforcement Learning (RL)

Multi-Agent Reinforcement Learning is a Sequence Modeling Problem

1 code implementation30 May 2022 Muning Wen, Jakub Grudzien Kuba, Runji Lin, Weinan Zhang, Ying Wen, Jun Wang, Yaodong Yang

In this paper, we introduce a novel architecture named Multi-Agent Transformer (MAT) that effectively casts cooperative multi-agent reinforcement learning (MARL) into SM problems wherein the task is to map agents' observation sequence to agents' optimal action sequence.

Decision Making Multi-agent Reinforcement Learning +2

Sample-Efficient Optimisation with Probabilistic Transformer Surrogates

no code implementations27 May 2022 Alexandre Maraval, Matthieu Zimmer, Antoine Grosnit, Rasul Tutunov, Jun Wang, Haitham Bou Ammar

First, we notice that these models are trained on uniformly distributed inputs, which impairs predictive accuracy on non-uniform data - a setting arising from any typical BO loop due to exploration-exploitation trade-offs.

Bayesian Optimisation Gaussian Processes

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

no code implementations26 May 2022 Jun Wang, Sixian Wang, Jincheng Dai, Zhongwei Si, Dekun Zhou, Kai Niu

However, current deep JSCC image transmission systems are typically optimized for traditional distortion metrics such as peak signal-to-noise ratio (PSNR) or multi-scale structural similarity (MS-SSIM).


Multi-Agent Feedback Enabled Neural Networks for Intelligent Communications

1 code implementation22 May 2022 Fanglei Sun, Yang Li, Ying Wen, Jingchen Hu, Jun Wang, Yang Yang, Kai Li

The design of MAFENN framework and algorithm are dedicated to enhance the learning capability of the feedfoward DL networks or their variations with the simple data feedback.

Denoising Intelligent Communication

A Review of Safe Reinforcement Learning: Methods, Theory and Applications

1 code implementation20 May 2022 Shangding Gu, Long Yang, Yali Du, Guang Chen, Florian Walter, Jun Wang, Yaodong Yang, Alois Knoll

To establish a good foundation for future research in this thread, in this paper, we provide a review for safe RL from the perspectives of methods, theory and applications.

Autonomous Driving Decision Making +3

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

no code implementations14 May 2022 Jun Wang, Omran Alamayreh, Benedetta Tondi, Mauro Barni

In this paper, we address a new image forensics task, namely the detection of fake flood images generated by ClimateGAN architecture.

Image Forensics

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

1 code implementation ACL 2022 Yang Li, Cheng Yu, Guangzhi Sun, Hua Jiang, Fanglei Sun, Weiqin Zu, Ying Wen, Yang Yang, Jun Wang

Modelling prosody variation is critical for synthesizing natural and expressive speech in end-to-end text-to-speech (TTS) systems.

On the Convergence of Fictitious Play: A Decomposition Approach

no code implementations3 May 2022 Yurong Chen, Xiaotie Deng, Chenchen Li, David Mguni, Jun Wang, Xiang Yan, Yaodong Yang

Fictitious play (FP) is one of the most fundamental game-theoretical learning frameworks for computing Nash equilibrium in $n$-player games, which builds the foundation for modern multi-agent learning algorithms.

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

no code implementations28 Apr 2022 Guochang Lin, Fukai Chen, Pipi Hu, Xiang Chen, Junqing Chen, Jun Wang, Zuoqiang Shi

In addition, we also use the Green's function calculated by our method to solve a class of PDE, and also obtain high-precision solutions, which shows the good generalization ability of our method on solving PDEs.

M2N: Mesh Movement Networks for PDE Solvers

no code implementations24 Apr 2022 Wenbin Song, Mingrui Zhang, Joseph G. Wallwork, Junpeng Gao, Zheng Tian, Fanglei Sun, Matthew D. Piggott, Junqing Chen, Zuoqiang Shi, Xiang Chen, Jun Wang

However, mesh movement methods, such as the Monge-Ampere method, require the solution of auxiliary equations, which can be extremely expensive especially when the mesh is adapted frequently.

Graph Attention

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

2 code implementations21 Apr 2022 Rongjie Huang, Max W. Y. Lam, Jun Wang, Dan Su, Dong Yu, Yi Ren, Zhou Zhao

Also, FastDiff enables a sampling speed of 58x faster than real-time on a V100 GPU, making diffusion models practically applicable to speech synthesis deployment for the first time.

Ranked #7 on Text-To-Speech Synthesis on LJSpeech (using extra training data)

Denoising Speech Synthesis +2

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

no code implementations2 Apr 2022 Zeyong Wei, Honghua Chen, Hao Tang, Qian Xie, Mingqiang Wei, Jun Wang

The shape of circle is one of fundamental geometric primitives of man-made engineering objects.

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

1 code implementation ICLR 2022 Max W. Y. Lam, Jun Wang, Dan Su, Dong Yu

We propose a new bilateral denoising diffusion model (BDDM) that parameterizes both the forward and reverse processes with a schedule network and a score network, which can train with a novel bilateral modeling objective.

Image Generation Speech Synthesis

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

1 code implementation23 Mar 2022 Haoran Zhou, Honghua Chen, Yingkui Zhang, Mingqiang Wei, Haoran Xie, Jun Wang, Tong Lu, Jing Qin, Xiao-Ping Zhang

Differently, our network is designed to refine the initial normal of each point by extracting additional information from multiple feature representations.

PointAttN: You Only Need Attention for Point Cloud Completion

1 code implementation16 Mar 2022 Jun Wang, Ying Cui, Dongyan Guo, Junxia Li, Qingshan Liu, Chunhua Shen

To solve the problems, we leverage the cross-attention and self-attention mechanisms to design novel neural network for processing point cloud in a per-point manner to eliminate kNNs.

Point Cloud Completion

Plan Your Target and Learn Your Skills: Transferable State-Only Imitation Learning via Decoupled Policy Optimization

2 code implementations4 Mar 2022 Minghuan Liu, Zhengbang Zhu, Yuzheng Zhuang, Weinan Zhang, Jianye Hao, Yong Yu, Jun Wang

Recent progress in state-only imitation learning extends the scope of applicability of imitation learning to real-world settings by relieving the need for observing expert actions.

Imitation Learning Transfer Learning

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

no code implementations2 Mar 2022 Xianbin Ye, Ziliang Li, Fei Ma, Zongbi Yi, Pengyong Li, Jun Wang, Peng Gao, Yixuan Qiao, Guotong Xie

Anti-cancer drug discoveries have been serendipitous, we sought to present the Open Molecular Graph Learning Benchmark, named CandidateDrug4Cancer, a challenging and realistic benchmark dataset to facilitate scalable, robust, and reproducible graph machine learning research for anti-cancer drug discovery.

Drug Discovery Graph Learning

How Well Do Self-Supervised Methods Perform in Cross-Domain Few-Shot Learning?

no code implementations18 Feb 2022 Yiyi Zhang, Ying Zheng, Xiaogang Xu, Jun Wang

In this paper, we investigate the role of self-supervised representation learning in the context of CDFSL via a thorough evaluation of existing methods.

cross-domain few-shot learning Representation Learning +1

Generalizable Information Theoretic Causal Representation

no code implementations17 Feb 2022 Mengyue Yang, Xinyu Cai, Furui Liu, Xu Chen, Zhitang Chen, Jianye Hao, Jun Wang

It is evidence that representation learning can improve model's performance over multiple downstream tasks in many real-world scenarios, such as image classification and recommender systems.

Image Classification Recommendation Systems +1

Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation

1 code implementation14 Feb 2022 Aivar Sootla, Alexander I. Cowen-Rivers, Taher Jafferjee, Ziyan Wang, David Mguni, Jun Wang, Haitham Bou-Ammar

Satisfying safety constraints almost surely (or with probability one) can be critical for the deployment of Reinforcement Learning (RL) in real-life applications.

reinforcement-learning Reinforcement Learning (RL) +1

Reinforcement Learning in Presence of Discrete Markovian Context Evolution

no code implementations ICLR 2022 Hang Ren, Aivar Sootla, Taher Jafferjee, Junxiao Shen, Jun Wang, Haitham Bou-Ammar

We consider a context-dependent Reinforcement Learning (RL) setting, which is characterized by: a) an unknown finite number of not directly observable contexts; b) abrupt (discontinuous) context changes occurring during an episode; and c) Markovian context evolution.

reinforcement-learning Reinforcement Learning (RL) +1

Settling the Communication Complexity for Distributed Offline Reinforcement Learning

no code implementations10 Feb 2022 Juliusz Krysztof Ziomek, Jun Wang, Yaodong Yang

We study a novel setting in offline reinforcement learning (RL) where a number of distributed machines jointly cooperate to solve the problem but only one single round of communication is allowed and there is a budget constraint on the total number of information (in terms of bits) that each machine can send out.

Multi-Armed Bandits Offline RL +2

AD-NEGF: An End-to-End Differentiable Quantum Transport Simulator for Sensitivity Analysis and Inverse Problems

no code implementations10 Feb 2022 Yingzhanghao Zhou, Xiang Chen, Peng Zhang, Jun Wang, Lei Wang, Hong Guo

Since proposed in the 70s, the Non-Equilibrium Green Function (NEGF) method has been recognized as a standard approach to quantum transport simulations.

Obtaining Dyadic Fairness by Optimal Transport

1 code implementation9 Feb 2022 Moyi Yang, Junjie Sheng, Xiangfeng Wang, Wenyan Liu, Bo Jin, Jun Wang, Hongyuan Zha

Fairness has been taken as a critical metric in machine learning models, which is considered as an important component of trustworthy machine learning.

Fairness Link Prediction

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

1 code implementation3 Feb 2022 Yabin Xu, Liangliang Nan, Laishui Zhou, Jun Wang, Charlie C. L. Wang

However, due to the discrete nature and limited resolution of their surface representations (e. g., point- or voxel-based), existing approaches suffer from the accumulation of errors in camera tracking and distortion in the reconstruction, which leads to an unsatisfactory 3D reconstruction.

3D Reconstruction

Efficient Policy Space Response Oracles

no code implementations28 Jan 2022 Ming Zhou, Jingxiao Chen, Ying Wen, Weinan Zhang, Yaodong Yang, Yong Yu, Jun Wang

Policy Space Response Oracle methods (PSRO) provide a general solution to learn Nash equilibrium in two-player zero-sum games but suffer from two drawbacks: (1) the computation inefficiency due to the need for consistent meta-game evaluation via simulations, and (2) the exploration inefficiency due to finding the best response against a fixed meta-strategy at every epoch.

Efficient Exploration

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

no code implementations25 Jan 2022 Jianwei Xu, Ran Zhao, Yizhou Yu, Qingwei Zhang, Xianzhang Bian, Jun Wang, Zhizheng Ge, Dahong Qian

In order to solve these problems, our method combines the two-dimensional (2-D) CNN-based real-time object detector network with spatiotemporal information.

Specificity SSIM +1

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

no code implementations24 Jan 2022 Wei Huang, Tianfu Qi, Yundi Guan, Qihang Peng, Jun Wang

In this paper, we investigate the waveform design from a novel perspective and propose a new waveform design paradigm with the knowledge graph (KG)-based intelligent recommendation system.

Collaborative Filtering Intelligent Communication +1

Chinese Word Segmentation with Heterogeneous Graph Neural Network

no code implementations22 Jan 2022 Xuemei Tang, Jun Wang, Qi Su

In recent years, deep learning has achieved significant success in the Chinese word segmentation (CWS) task.

Chinese Word Segmentation Language Modelling

Debiased Recommendation with User Feature Balancing

no code implementations16 Jan 2022 Mengyue Yang, Guohao Cai, Furui Liu, Zhenhua Dong, Xiuqiang He, Jianye Hao, Jun Wang, Xu Chen

To alleviate these problems, in this paper, we propose a novel debiased recommendation framework based on user feature balancing.

Causal Inference Recommendation Systems

Learning to Identify Top Elo Ratings: A Dueling Bandits Approach

1 code implementation12 Jan 2022 Xue Yan, Yali Du, Binxin Ru, Jun Wang, Haifeng Zhang, Xu Chen

The Elo rating system is widely adopted to evaluate the skills of (chess) game and sports players.


Differentiable and Scalable Generative Adversarial Models for Data Imputation

no code implementations10 Jan 2022 Yangyang Wu, Jun Wang, Xiaoye Miao, Wenjia Wang, Jianwei Yin

DIM leverages a new masking Sinkhorn divergence function to make an arbitrary generative adversarial imputation model differentiable, while for such a differentiable imputation model, SSE can estimate an appropriate sample size to ensure the user-specified imputation accuracy of the final model.


Data-Free Knowledge Transfer: A Survey

no code implementations31 Dec 2021 Yuang Liu, Wei zhang, Jun Wang, Jianyong Wang

In this paper, we provide a comprehensive survey on data-free knowledge transfer from the perspectives of knowledge distillation and unsupervised domain adaptation, to help readers have a better understanding of the current research status and ideas.

Knowledge Distillation Model Compression +2

A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning

1 code implementation31 Dec 2021 Bo Liu, Xidong Feng, Jie Ren, Luo Mai, Rui Zhu, Haifeng Zhang, Jun Wang, Yaodong Yang

Gradient-based Meta-RL (GMRL) refers to methods that maintain two-level optimisation procedures wherein the outer-loop meta-learner guides the inner-loop gradient-based reinforcement learner to achieve fast adaptations.

Atari Games Meta Reinforcement Learning +3

Superpixel-Based Building Damage Detection from Post-earthquake Very High Resolution Imagery Using Deep Neural Networks

no code implementations9 Dec 2021 Jun Wang, Zhoujing Li, Yixuan Qiao, Qiming Qin, Peng Gao, Guotong Xie

This paper presents a novel superpixel based approach combining DNN and a modified segmentation method, to detect damaged buildings from VHR imagery.

Denoising Semantic Similarity +1

Understanding Square Loss in Training Overparametrized Neural Network Classifiers

no code implementations7 Dec 2021 Tianyang Hu, Jun Wang, Wenjia Wang, Zhenguo Li

Comparing to cross-entropy, square loss has comparable generalization error but noticeable advantages in robustness and model calibration.

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

1 code implementation6 Dec 2021 Linghui Meng, Muning Wen, Yaodong Yang, Chenyang Le, Xiyun Li, Weinan Zhang, Ying Wen, Haifeng Zhang, Jun Wang, Bo Xu

In this paper, we facilitate the research by providing large-scale datasets, and use them to examine the usage of the Decision Transformer in the context of MARL.

Offline RL reinforcement-learning +4

Neural Auto-Curricula in Two-Player Zero-Sum Games

1 code implementation NeurIPS 2021 Xidong Feng, Oliver Slumbers, Ziyu Wan, Bo Liu, Stephen Mcaleer, Ying Wen, Jun Wang, Yaodong Yang

When solving two-player zero-sum games, multi-agent reinforcement learning (MARL) algorithms often create populations of agents where, at each iteration, a new agent is discovered as the best response to a mixture over the opponent population.

Multi-agent Reinforcement Learning Vocal Bursts Valence Prediction

Learning State Representations via Retracing in Reinforcement Learning

1 code implementation ICLR 2022 Changmin Yu, Dong Li, Jianye Hao, Jun Wang, Neil Burgess

We propose learning via retracing, a novel self-supervised approach for learning the state representation (and the associated dynamics model) for reinforcement learning tasks.

Continuous Control Model-based Reinforcement Learning +3

BOiLS: Bayesian Optimisation for Logic Synthesis

no code implementations11 Nov 2021 Antoine Grosnit, Cedric Malherbe, Rasul Tutunov, Xingchen Wan, Jun Wang, Haitham Bou Ammar

Optimising the quality-of-results (QoR) of circuits during logic synthesis is a formidable challenge necessitating the exploration of exponentially sized search spaces.

Bayesian Optimisation Navigate

MetaMIML: Meta Multi-Instance Multi-Label Learning

no code implementations7 Nov 2021 Yuanlin Yang, Guoxian Yu, Jun Wang, Lei Liu, Carlotta Domeniconi, Maozu Guo

Multi-Instance Multi-Label learning (MIML) models complex objects (bags), each of which is associated with a set of interrelated labels and composed with a set of instances.

Meta-Learning Multi-Label Learning +1

Dispensed Transformer Network for Unsupervised Domain Adaptation

no code implementations28 Oct 2021 Yunxiang Li, Jingxiong Li, Ruilong Dan, Shuai Wang, Kai Jin, Guodong Zeng, Jun Wang, Xiangji Pan, Qianni Zhang, Huiyu Zhou, Qun Jin, Li Wang, Yaqi Wang

To mitigate this problem, a novel unsupervised domain adaptation (UDA) method named dispensed Transformer network (DTNet) is introduced in this paper.

Unsupervised Domain Adaptation

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

no code implementations28 Oct 2021 Chenguang Wang, Yaodong Yang, Oliver Slumbers, Congying Han, Tiande Guo, Haifeng Zhang, Jun Wang

In this paper, we introduce a two-player zero-sum framework between a trainable \emph{Solver} and a \emph{Data Generator} to improve the generalization ability of deep learning-based solvers for Traveling Salesman Problem (TSP).

Traveling Salesman Problem

DESTA: A Framework for Safe Reinforcement Learning with Markov Games of Intervention

no code implementations27 Oct 2021 David Mguni, Usman Islam, Yaqi Sun, Xiuling Zhang, Joel Jennings, Aivar Sootla, Changmin Yu, Ziyan Wang, Jun Wang, Yaodong Yang

In this paper, we introduce a new generation of RL solvers that learn to minimise safety violations while maximising the task reward to the extent that can be tolerated by the safe policy.

OpenAI Gym reinforcement-learning +3

Measuring the Non-Transitivity in Chess

no code implementations22 Oct 2021 Ricky Sanjaya, Jun Wang, Yaodong Yang

In this paper, we quantify the non-transitivity in Chess through real-world data from human players.

A channel attention based MLP-Mixer network for motor imagery decoding with EEG

no code implementations21 Oct 2021 Yanbin He, Zhiyang Lu, Jun Wang, Jun Shi

Convolutional neural networks (CNNs) and their variants have been successfully applied to the electroencephalogram (EEG) based motor imagery (MI) decoding task.

Electroencephalogram (EEG)

Online Markov Decision Processes with Non-oblivious Strategic Adversary

no code implementations7 Oct 2021 Le Cong Dinh, David Henry Mguni, Long Tran-Thanh, Jun Wang, Yaodong Yang

In this setting, we first demonstrate that MDP-Expert, an existing algorithm that works well with oblivious adversaries can still apply and achieve a policy regret bound of $\mathcal{O}(\sqrt{T \log(L)}+\tau^2\sqrt{ T \log(|A|)})$ where $L$ is the size of adversary's pure strategy set and $|A|$ denotes the size of agent's action space.

Multi-Agent Constrained Policy Optimisation

3 code implementations6 Oct 2021 Shangding Gu, Jakub Grudzien Kuba, Munning Wen, Ruiqing Chen, Ziyan Wang, Zheng Tian, Jun Wang, Alois Knoll, Yaodong Yang

To fill these gaps, in this work, we formulate the safe MARL problem as a constrained Markov game and solve it with policy optimisation methods.

Multi-agent Reinforcement Learning reinforcement-learning +1

GT U-Net: A U-Net Like Group Transformer Network for Tooth Root Segmentation

1 code implementation30 Sep 2021 Yunxiang Li, Shuai Wang, Jun Wang, Guodong Zeng, Wenjun Liu, Qianni Zhang, Qun Jin, Yaqi Wang

In this paper, we propose a novel end-to-end U-Net like Group Transformer Network (GT U-Net) for the tooth root segmentation.


Model-Based Robust Adaptive Semantic Segmentation

no code implementations29 Sep 2021 Jun Wang, Yiannis Kantaros

To mitigate this challenge, in this paper, we propose model-based robust adaptive training algorithm (MRTAdapt), a new training algorithm to enhance the robustness of DNN-based semantic segmentation methods against natural variations that leverages model-based robust training algorithms and generative adversarial networks.

Autonomous Vehicles Image Segmentation +1

Learning Explicit Credit Assignment for Multi-agent Joint Q-learning

no code implementations29 Sep 2021 Hangyu Mao, Jianye Hao, Dong Li, Jun Wang, Weixun Wang, Xiaotian Hao, Bin Wang, Kun Shao, Zhen Xiao, Wulong Liu

In contrast, we formulate an \emph{explicit} credit assignment problem where each agent gives its suggestion about how to weight individual Q-values to explicitly maximize the joint Q-value, besides guaranteeing the Bellman optimality of the joint Q-value.


Modeling Variable Space with Residual Tensor Networks for Multivariate Time Series

no code implementations29 Sep 2021 Jing Zhang, Peng Zhang, Yupeng He, Siwei Rao, Jun Wang, Guangjian Tian

In this framework, we derive the mathematical representation of the variable space, and then use a tensor network based on the idea of low-rank approximation to model the variable space.

Multivariate Time Series Forecasting Tensor Networks +1

Continual Learning of Neural Networks for Realtime Wireline Cable Position Inference

no code implementations29 Sep 2021 Jun Wang, Tianxiang Su

In our experiments, we compared the proposed method with multiple state-of-the-art continual learning methods and the mREMIND network outperformed others both in accuracy and in disk space usage.

Continual Learning

A neural network framework for learning Green's function

no code implementations29 Sep 2021 Guochang Lin, Fukai Chen, Pipi Hu, Xiang Chen, Junqing Chen, Jun Wang, Zuoqiang Shi

Green's function plays a significant role in both theoretical analysis and numerical computing of partial differential equations (PDEs).

SynCLR: A Synthesis Framework for Contrastive Learning of out-of-domain Speech Representations

no code implementations29 Sep 2021 Rongjie Huang, Max W. Y. Lam, Jun Wang, Dan Su, Dong Yu, Zhou Zhao, Yi Ren

Learning generalizable speech representations for unseen samples in different domains has been a challenge with ever increasing importance to date.

Contrastive Learning Data Augmentation +4

Informative Robust Causal Representation for Generalizable Deep Learning

no code implementations29 Sep 2021 Mengyue Yang, Furui Liu, Xu Chen, Zhitang Chen, Jianye Hao, Jun Wang

In many real-world scenarios, such as image classification and recommender systems, it is evidence that representation learning can improve model's performance over multiple downstream tasks.

Image Classification Recommendation Systems +1

Performance-Guaranteed ODE Solvers with Complexity-Informed Neural Networks

no code implementations NeurIPS Workshop DLDE 2021 Feng Zhao, Xiang Chen, Jun Wang, Zuoqiang Shi, Shao-Lun Huang

Traditionally, we provide technical parameters for ODE solvers, such as the order, the stepsize and the local error threshold.

Cross Attention-guided Dense Network for Images Fusion

1 code implementation23 Sep 2021 Zhengwen Shen, Jun Wang, Zaiyu Pan, Yulian Li, Jiangyu Wang

In this paper, we propose a novel cross-attention-guided image fusion network, which is a unified and unsupervised framework for multi-modal image fusion, multi-exposure image fusion, and multi-focus image fusion.

Multi-Exposure Image Fusion

Revisiting the Characteristics of Stochastic Gradient Noise and Dynamics

no code implementations20 Sep 2021 Yixin Wu, Rui Luo, Chen Zhang, Jun Wang, Yaodong Yang

In this paper, we characterize the noise of stochastic gradients and analyze the noise-induced dynamics during training deep neural networks by gradient-based optimizers.

Recommendation Fairness: From Static to Dynamic

no code implementations5 Sep 2021 Dell Zhang, Jun Wang

Driven by the need to capture users' evolving interests and optimize their long-term experiences, more and more recommender systems have started to model recommendation as a Markov decision process and employ reinforcement learning to address the problem.

Fairness Recommendation Systems +2

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

no code implementations4 Sep 2021 Xiaotie Deng, Ningyuan Li, David Mguni, Jun Wang, Yaodong Yang

Similar to the role of Markov decision processes in reinforcement learning, Stochastic Games (SGs) lay the foundation for the study of multi-agent reinforcement learning (MARL) and sequential agent interactions.

Multi-agent Reinforcement Learning reinforcement-learning +1

Top-N Recommendation with Counterfactual User Preference Simulation

no code implementations2 Sep 2021 Mengyue Yang, Quanyu Dai, Zhenhua Dong, Xu Chen, Xiuqiang He, Jun Wang

To alleviate this problem, in this paper, we propose to reformulate the recommendation task within the causal inference framework, which enables us to counterfactually simulate user ranking-based preferences to handle the data scarce problem.

Causal Inference Recommendation Systems

Bilateral Denoising Diffusion Models

no code implementations26 Aug 2021 Max W. Y. Lam, Jun Wang, Rongjie Huang, Dan Su, Dong Yu

In this paper, we propose novel bilateral denoising diffusion models (BDDMs), which take significantly fewer steps to generate high-quality samples.

Denoising Scheduling

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

no code implementations25 Aug 2021 Jun Wang, Hefeng Zhou, Xiaohan Yu

There are two main problems hindering the performance of the two-phase WSOD approaches, i. e., insufficient learning problem and strict reliance between the FSD and the pseudo ground truth (PGT) generated by the WSOD model.

object-detection Weakly Supervised Object Detection

CMML: Contextual Modulation Meta Learning for Cold-Start Recommendation

1 code implementation24 Aug 2021 Xidong Feng, Chen Chen, Dong Li, Mengchen Zhao, Jianye Hao, Jun Wang

Meta learning, especially gradient based one, can be adopted to tackle this problem by learning initial parameters of the model and thus allowing fast adaptation to a specific task from limited data examples.

Meta-Learning Recommendation Systems

Settling the Variance of Multi-Agent Policy Gradients

1 code implementation NeurIPS 2021 Jakub Grudzien Kuba, Muning Wen, Yaodong Yang, Linghui Meng, Shangding Gu, Haifeng Zhang, David Henry Mguni, Jun Wang

In multi-agent RL (MARL), although the PG theorem can be naturally extended, the effectiveness of multi-agent PG (MAPG) methods degrades as the variance of gradient estimates increases rapidly with the number of agents.

Reinforcement Learning (RL) Starcraft