Search Results for author: Yu Wang

Found 353 papers, 141 papers with code

HIT: Nested Named Entity Recognition via Head-Tail Pair and Token Interaction

no code implementations EMNLP 2020 Yu Wang, Yun Li, Hanghang Tong, Ziye Zhu

Specifically, we design (1) Head-Tail Detector based on the multi-head self-attention mechanism and bi-affine classifier to detect boundary tokens, and (2) Token Interaction Tagger based on traditional sequence labeling approaches to characterize the internal token connection within the boundary.

named-entity-recognition Named Entity Recognition +2

NEURAL MALWARE CONTROL WITH DEEP REINFORCEMENT LEARNING

no code implementations ICLR 2019 Yu Wang, Jack W. Stokes, Mady Marinescu

Antimalware products are a key component in detecting malware attacks, and their engines typically execute unknown programs in a sandbox prior to running them on the native operating system.

reinforcement-learning Reinforcement Learning (RL)

CNNSAT: Fast, Accurate Boolean Satisfiability using Convolutional Neural Networks

no code implementations ICLR 2019 Yu Wang, Fengjuan Gao, Amin Alipour, Linzhang Wang, Xuandong Li, Zhendong Su

Boolean satisfiability (SAT) is one of the most well-known NP-complete problems and has been extensively studied.

基于规则的双重否定识别——以“不v1不v2”为例(Double Negative Recognition Based on Rules——Taking “不v1不v2” as an Example)

no code implementations CCL 2020 Yu Wang

“不v1不v2”是汉语中典型的双重否定结构形式之一, 它包括“不+助动词+不+v2”(不得不去)、“不+是+不v2”(不是不好)、述宾结构“不v1... 不v2”(不认为他不去)等多种双重否定结构, 情况复杂。本文以“不v1不v2”为例, 结合“元语否定”、“动词叙实性”、“否定焦点”等概念, 对“不v1不v2”进行了全面的考察, 制定了“不v1不v2”双重否定结构的识别策略。根据识别策略, 设计了双重否定自动识别程序, 并在此过程中补充了助动词表、非叙实动词表等词库。最终, 对28033句语料进行了识别, 识别正确率为97. 87%, 召回率约为93. 10%。

Pseudo-Masked Language Models for Unified Language Model Pre-Training

1 code implementation ICML 2020 Hangbo Bao, Li Dong, Furu Wei, Wenhui Wang, Nan Yang, Xiaodong Liu, Yu Wang, Jianfeng Gao, Songhao Piao, Ming Zhou, Hsiao-Wuen Hon

We propose to pre-train a unified language model for both autoencoding and partially autoregressive language modeling tasks using a novel training procedure, referred to as a pseudo-masked language model (PMLM).

Language Modelling Natural Language Understanding +1

双重否定结构自动识别研究(The Research on Automatic Recognition of the Double Negation Structure)

no code implementations CCL 2022 Yu Wang, Yulin Yuan

“双重否定结构是一种“通过两次否定表示肯定意义”的特殊结构, 其存在会对自然语言处理中的语义判断与情感分类产生重要影响。本文以“eg eg P== extgreater P”为标准, 对现代汉语中所有的“否定词+否定词”结构进行了遍历研究, 将双重否定结构按照格式分为了3大类, 25小类, 常用双重否定结构或构式132个。结合动词的叙实性、否定焦点、语义否定与语用否定等相关理论, 本文归纳了双重否定结构的三大成立条件, 并据此设计实现了基于规则的双重否定结构自动识别程序。程序实验的精确率为98. 85%, 召回率为98. 90%, F1值为98. 85%。同时, 程序还从96281句语料中获得了8640句精确率约为99%的含有双重否定结构的句子, 为后续基于统计的深度学习模型提供了语料支持的可能。”

Negation

AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting

1 code implementation14 Mar 2024 Yu Wang, Xiaogeng Liu, Yu Li, Muhao Chen, Chaowei Xiao

However, with the integration of additional modalities, MLLMs are exposed to new vulnerabilities, rendering them prone to structured-based jailbreak attacks, where semantic content (e. g., "harmful text") has been injected into the images to mislead MLLMs.

Automatic Interactive Evaluation for Large Language Models with State Aware Patient Simulator

no code implementations13 Mar 2024 Yusheng Liao, Yutong Meng, Yuhao Wang, Hongcheng Liu, Yanfeng Wang, Yu Wang

Large Language Models (LLMs) have demonstrated remarkable proficiency in human interactions, yet their application within the medical field remains insufficiently explored.

Towards Implicit Prompt For Text-To-Image Models

no code implementations4 Mar 2024 Yue Yang, Yuqi Lin, Hong Liu, Wenqi Shao, Runjian Chen, Hailong Shang, Yu Wang, Yu Qiao, Kaipeng Zhang, Ping Luo

We call for increased attention to the potential and risks of implicit prompts in the T2I community and further investigation into the capabilities and impacts of implicit prompts, advocating for a balanced approach that harnesses their benefits while mitigating their risks.

Position

A Tutorial on the Pretrain-Finetune Paradigm for Natural Language Processing

no code implementations4 Mar 2024 Yu Wang

Our tutorial offers a comprehensive introduction to the pretrain-finetune paradigm.

Multi-class Classification

COLA: Cross-city Mobility Transformer for Human Trajectory Simulation

1 code implementation4 Mar 2024 Yu Wang, Tongya Zheng, Yuxuan Liang, Shunyu Liu, Mingli Song

To address these challenges, we have tailored a Cross-city mObiLity trAnsformer (COLA) with a dedicated model-agnostic transfer framework by effectively transferring cross-city knowledge for human trajectory simulation.

CoLA Transfer Learning

Generating, Reconstructing, and Representing Discrete and Continuous Data: Generalized Diffusion with Learnable Encoding-Decoding

no code implementations29 Feb 2024 Guangyi Liu, Yu Wang, Zeyu Feng, Qiyu Wu, Liping Tang, Yuan Gao, Zhen Li, Shuguang Cui, Julian McAuley, Eric P. Xing, Zichao Yang, Zhiting Hu

The vast applications of deep generative models are anchored in three core capabilities -- generating new instances, reconstructing inputs, and learning compact representations -- across various data types, such as discrete text/protein sequences and continuous images.

Denoising

LLMs in Political Science: Heralding a New Era of Visual Analysis

no code implementations29 Feb 2024 Yu Wang, Mengying Xing

We find that Gemini is highly accurate in performing object detection, which is arguably the most common and fundamental task in image analysis for political scientists.

Face Identification object-detection +2

Evaluating Quantized Large Language Models

1 code implementation28 Feb 2024 Shiyao Li, Xuefei Ning, Luning Wang, Tengxuan Liu, Xiangsheng Shi, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang

Post-training quantization (PTQ) has emerged as a promising technique to reduce the cost of large language models (LLMs).

Quantization

Leveraging Diverse Modeling Contexts with Collaborating Learning for Neural Machine Translation

no code implementations28 Feb 2024 Yusheng Liao, Yanfeng Wang, Yu Wang

Autoregressive (AR) and Non-autoregressive (NAR) models are two types of generative models for Neural Machine Translation (NMT).

Contrastive Learning Machine Translation +2

Searching a Lightweight Network Architecture for Thermal Infrared Pedestrian Tracking

no code implementations26 Feb 2024 Peng Gao, Xiao Liu, Yu Wang, Ru-Yue Yuan

To expedite the search process, a random channel selection strategy is employed prior to assessing operation candidates.

Intelligent Director: An Automatic Framework for Dynamic Visual Composition using ChatGPT

no code implementations24 Feb 2024 Sixiao Zheng, Jingyang Huo, Yu Wang, Yanwei Fu

We propose an Intelligent Director framework, utilizing LENS to generate descriptions for images and video frames and combining ChatGPT to generate coherent captions while recommending appropriate music names.

Retrieval Style Transfer

Representation Learning for Frequent Subgraph Mining

no code implementations22 Feb 2024 Rex Ying, Tianyu Fu, Andrew Wang, Jiaxuan You, Yu Wang, Jure Leskovec

SPMiner combines graph neural networks, order embedding space, and an efficient search strategy to identify network subgraph patterns that appear most frequently in the target graph.

Representation Learning Subgraph Counting

Pushing Auto-regressive Models for 3D Shape Generation at Capacity and Scalability

no code implementations19 Feb 2024 Xuelin Qian, Yu Wang, Simian Luo, yinda zhang, Ying Tai, Zhenyu Zhang, Chengjie Wang, xiangyang xue, Bo Zhao, Tiejun Huang, Yunsheng Wu, Yanwei Fu

In this paper, we extend auto-regressive models to 3D domains, and seek a stronger ability of 3D shape generation by improving auto-regressive models at capacity and scalability simultaneously.

3D Shape Generation Image Generation +1

Leveraging Opposite Gender Interaction Ratio as a Path towards Fairness in Online Dating Recommendations Based on User Sexual Orientation

no code implementations19 Feb 2024 Yuying Zhao, Yu Wang, Yi Zhang, Pamela Wisniewski, Charu Aggarwal, Tyler Derr

While recommender systems have been designed to improve the user experience in dating platforms by providing personalized recommendations, increasing concerns about fairness have encouraged the development of fairness-aware recommender systems from various perspectives (e. g., gender and race).

Fairness Recommendation Systems +1

LVCHAT: Facilitating Long Video Comprehension

1 code implementation19 Feb 2024 Yu Wang, Zeyuan Zhang, Julian McAuley, Zexue He

To address this issue, we propose Long Video Chat (LVChat), where Frame-Scalable Encoding (FSE) is introduced to dynamically adjust the number of embeddings in alignment with the duration of the video to ensure long videos are not overly compressed into a few embeddings.

Video Captioning

M2K-VDG: Model-Adaptive Multimodal Knowledge Anchor Enhanced Video-grounded Dialogue Generation

no code implementations19 Feb 2024 Hongcheng Liu, Pingjie Wang, Yu Wang, Yanfeng Wang

Video-grounded dialogue generation (VDG) requires the system to generate a fluent and accurate answer based on multimodal knowledge.

counterfactual Dialogue Generation +1

Knowledge Graph-based Session Recommendation with Adaptive Propagation

no code implementations17 Feb 2024 Yu Wang, Amin Javari, Janani Balaji, Walid Shalaby, Tyler Derr, Xiquan Cui

Then, we adaptively aggregate items' neighbor information considering user intention within the learned session.

Recommendation Systems

MEMORYLLM: Towards Self-Updatable Large Language Models

no code implementations7 Feb 2024 Yu Wang, Xiusi Chen, Jingbo Shang, Julian McAuley

Existing Large Language Models (LLMs) usually remain static after deployment, which might make it hard to inject new knowledge into the model.

Model Editing

LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K

1 code implementation6 Feb 2024 Tao Yuan, Xuefei Ning, Dong Zhou, Zhijie Yang, Shiyao Li, Minghui Zhuang, Zheyue Tan, Zhuyu Yao, Dahua Lin, Boxun Li, Guohao Dai, Shengen Yan, Yu Wang

In contrast, the average context lengths of mainstream benchmarks are insufficient (5k-21k), and they suffer from potential knowledge leakage and inaccurate metrics, resulting in biased evaluation.

Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector

no code implementations5 Feb 2024 Yuqian Fu, Yu Wang, Yixuan Pan, Lian Huai, Xingyu Qiu, Zeyu Shangguan, Tong Liu, Lingjie Kong, Yanwei Fu, Luc van Gool, Xingqun Jiang

To address the first question, we introduce several metrics to quantify domain variances and establish a new CD-FSOD benchmark with diverse domain metric values.

Cross-Domain Few-Shot Few-Shot Object Detection +3

Peer-review-in-LLMs: Automatic Evaluation Method for LLMs in Open-environment

1 code implementation2 Feb 2024 Kun-Peng Ning, Shuo Yang, Yu-Yang Liu, Jia-Yu Yao, Zhen-Hui Liu, Yu Wang, Ming Pang, Li Yuan

Existing large language models (LLMs) evaluation methods typically focus on testing the performance on some closed-environment and domain-specific benchmarks with human annotations.

Disentangled Condensation for Large-scale Graphs

1 code implementation18 Jan 2024 Zhenbang Xiao, Shunyu Liu, Yu Wang, Tongya Zheng, Mingli Song

Graph condensation has emerged as an intriguing technique to provide Graph Neural Networks for large-scale graphs with a more compact yet informative small graph to save the expensive costs of large-scale graph learning.

Graph Learning Link Prediction +1

MM-SAP: A Comprehensive Benchmark for Assessing Self-Awareness of Multimodal Large Language Models in Perception

no code implementations15 Jan 2024 Yuhao Wang, Yusheng Liao, Heyang Liu, Hongcheng Liu, Yu Wang, Yanfeng Wang

We believe that these hallucinations are partially due to the models' struggle with understanding what they can and cannot perceive from images, a capability we refer to as self-awareness in perception.

Binding-Adaptive Diffusion Models for Structure-Based Drug Design

1 code implementation15 Jan 2024 Zhilin Huang, Ling Yang, Zaixi Zhang, Xiangxin Zhou, Yu Bao, Xiawu Zheng, Yuwei Yang, Yu Wang, Wenming Yang

Then the selected protein-ligand subcomplex is processed with SE(3)-equivariant neural networks, and transmitted back to each atom of the complex for augmenting the target-aware 3D molecule diffusion generation with binding interaction information.

Avg

Exploring Diverse Representations for Open Set Recognition

1 code implementation12 Jan 2024 Yu Wang, Junxian Mu, Pengfei Zhu, QinGhua Hu

We show that the differences in attention maps can lead to diverse representations so that the fused representations can well handle the open space.

Open Set Learning

Every Node is Different: Dynamically Fusing Self-Supervised Tasks for Attributed Graph Clustering

1 code implementation12 Jan 2024 Pengfei Zhu, Qian Wang, Yu Wang, Jialu Li, QinGhua Hu

In this paper, we propose to dynamically learn the weights of SSL tasks for different nodes and fuse the embeddings learned from different SSL tasks to boost performance.

Clustering Graph Clustering +1

FlightLLM: Efficient Large Language Model Inference with a Complete Mapping Flow on FPGAs

no code implementations8 Jan 2024 Shulin Zeng, Jun Liu, Guohao Dai, Xinhao Yang, Tianyu Fu, Hongyi Wang, Wenheng Ma, Hanbo Sun, Shiyao Li, Zixiao Huang, Yadong Dai, Jintao Li, Zehao Wang, Ruoyu Zhang, Kairui Wen, Xuefei Ning, Yu Wang

However, existing GPU and transformer-based accelerators cannot efficiently process compressed LLMs, due to the following unresolved challenges: low computational efficiency, underutilized memory bandwidth, and large compilation overheads.

Computational Efficiency Language Modelling +2

Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning

1 code implementation27 Dec 2023 Yan Fan, Yu Wang, Pengfei Zhu, QinGhua Hu

In this work, we focus on semi-supervised continual learning (SSCL), where the model progressively learns from partially labeled data with unknown categories.

Continual Learning graph construction +1

LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination

1 code implementation23 Dec 2023 Jijia Liu, Chao Yu, Jiaxuan Gao, Yuqing Xie, Qingmin Liao, Yi Wu, Yu Wang

AI agents powered by Large Language Models (LLMs) have made significant advances, enabling them to assist humans in diverse complex tasks and leading to a revolution in human-AI coordination.

Code Generation

EncryIP: A Practical Encryption-Based Framework for Model Intellectual Property Protection

no code implementations19 Dec 2023 Xin Mu, Yu Wang, Zhengan Huang, Junzuo Lai, Yehong Zhang, Hui Wang, Yue Yu

In the rapidly growing digital economy, protecting intellectual property (IP) associated with digital products has become increasingly important.

TaskFlex Solver for Multi-Agent Pursuit via Automatic Curriculum Learning

no code implementations19 Dec 2023 Jiayu Chen, Guosheng Li, Chao Yu, Xinyi Yang, Botian Xu, Huazhong Yang, Yu Wang

In this work, we combine RL and curriculum learning to introduce a flexible solver for multiagent pursuit problems, named TaskFlex Solver (TFS), which is capable of solving multi-agent pursuit problems with diverse and dynamically changing task conditions in both 2-dimensional and 3-dimensional scenarios.

Reinforcement Learning (RL)

DRDT: Dynamic Reflection with Divergent Thinking for LLM-based Sequential Recommendation

no code implementations18 Dec 2023 Yu Wang, Zhiwei Liu, JianGuo Zhang, Weiran Yao, Shelby Heinecke, Philip S. Yu

With our principle, we managed to outperform GPT-Turbo-3. 5 on three datasets using 7b models e. g., Vicuna-7b and Openchat-7b on NDCG@10.

In-Context Learning Sequential Recommendation

Deciphering Compatibility Relationships with Textual Descriptions via Extraction and Explanation

1 code implementation17 Dec 2023 Yu Wang, Zexue He, Zhankui He, Hao Xu, Julian McAuley

This fine-tuning allows the model to generate explanations that convey the compatibility relationships between items.

Spatial Knowledge-Infused Hierarchical Learning: An Application in Flood Mapping on Earth Imagery

1 code implementation12 Dec 2023 Zelin Xu, Tingsong Xiao, Wenchong He, Yu Wang, Zhe Jiang

The problem is challenging due to the sparse and noisy input labels, spatial uncertainty within the label inference process, and high computational costs associated with a large number of sample locations.

A Unified Sampling Framework for Solver Searching of Diffusion Probabilistic Models

no code implementations12 Dec 2023 Enshu Liu, Xuefei Ning, Huazhong Yang, Yu Wang

In this paper, we propose a unified sampling framework (USF) to study the optional strategies for solver.

MASP: Scalable GNN-based Planning for Multi-Agent Navigation

no code implementations5 Dec 2023 Xinyi Yang, Xinting Yang, Chao Yu, Jiayu Chen, Huazhong Yang, Yu Wang

Besides, to enhance generalization capabilities in scenarios with unseen team sizes, we divide agents into multiple groups, each with a previously trained number of agents.

Reinforcement Learning (RL) Zero-shot Generalization

Enabling Fast 2-bit LLM on GPUs: Memory Alignment and Asynchronous Dequantization

no code implementations28 Nov 2023 Jinhao Li, Shiyao Li, Jiaming Xu, Shan Huang, Yaoxiu Lian, Jun Liu, Yu Wang, Guohao Dai

Weights are quantized by groups, while the ranges of weights are large in some groups, resulting in large quantization errors and nonnegligible accuracy loss (e. g. >3% for Llama2-7b with 2-bit quantization in GPTQ and Greenbit).

Quantization

EPIM: Efficient Processing-In-Memory Accelerators based on Epitome

no code implementations12 Nov 2023 Chenyu Wang, Zhen Dong, Daquan Zhou, Zhenhua Zhu, Yu Wang, Jiashi Feng, Kurt Keutzer

On the hardware side, we modify the datapath of current PIM accelerators to accommodate epitomes and implement a feature map reuse technique to reduce computation cost.

Model Compression Neural Architecture Search +1

PepLand: a large-scale pre-trained peptide representation model for a comprehensive landscape of both canonical and non-canonical amino acids

1 code implementation8 Nov 2023 Ruochi Zhang, Haoran Wu, Yuting Xiu, Kewei Li, Ningning Chen, Yu Wang, Yan Wang, Xin Gao, Fengfeng Zhou

In recent years, the scientific community has become increasingly interested on peptides with non-canonical amino acids due to their superior stability and resistance to proteolytic degradation.

FlashDecoding++: Faster Large Language Model Inference on GPUs

no code implementations2 Nov 2023 Ke Hong, Guohao Dai, Jiaming Xu, Qiuli Mao, Xiuhong Li, Jun Liu, Kangdi Chen, Yuhan Dong, Yu Wang

A single and static dataflow may lead to a 50. 25% performance loss for GEMMs of different shapes in LLM inference.

Language Modelling Large Language Model

Active Neural Topological Mapping for Multi-Agent Exploration

no code implementations1 Nov 2023 Xinyi Yang, Yuxiang Yang, Chao Yu, Jiayu Chen, Jingchen Yu, Haibing Ren, Huazhong Yang, Yu Wang

In this paper, we propose Multi-Agent Neural Topological Mapping (MANTM) to improve exploration efficiency and generalization for multi-agent exploration tasks.

Large Trajectory Models are Scalable Motion Predictors and Planners

1 code implementation30 Oct 2023 Qiao Sun, Shiduo Zhang, Danjiao Ma, Jingzhe Shi, Derun Li, Simian Luo, Yu Wang, Ningyi Xu, Guangzhi Cao, Hang Zhao

STR reformulates the motion prediction and motion planning problems by arranging observations, states, and actions into one unified sequence modeling task.

Autonomous Driving Language Modelling +2

Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game

no code implementations29 Oct 2023 Zelai Xu, Chao Yu, Fei Fang, Yu Wang, Yi Wu

To mitigate the intrinsic bias in language actions, our agents use an LLM to perform deductive reasoning and generate a diverse set of action candidates.

Decision Making Reinforcement Learning (RL)

TorchSparse++: Efficient Training and Inference Framework for Sparse Convolution on GPUs

1 code implementation25 Oct 2023 Haotian Tang, Shang Yang, Zhijian Liu, Ke Hong, Zhongming Yu, Xiuyu Li, Guohao Dai, Yu Wang, Song Han

On top of this, we design the Sparse Autotuner, which extends the design space of existing sparse convolution libraries and searches for the best dataflow configurations for training and inference workloads.

Autonomous Driving Recommendation Systems

Semi-Supervised Learning of Dynamical Systems with Neural Ordinary Differential Equations: A Teacher-Student Model Approach

no code implementations19 Oct 2023 Yu Wang, Yuxuan Yin, Karthik Somayaji Nanjangud Suryanarayana, Jan Drgona, Malachi Schram, Mahantesh Halappanavar, Frank Liu, Peng Li

Modeling dynamical systems is crucial for a wide range of tasks, but it remains challenging due to complex nonlinear dynamics, limited observations, or lack of prior knowledge.

Relational Prior Knowledge Graphs for Detection and Instance Segmentation

1 code implementation11 Oct 2023 Osman Ülger, Yu Wang, Ysbrand Galama, Sezer Karaoglu, Theo Gevers, Martin R. Oswald

Humans have a remarkable ability to perceive and reason about the world around them by understanding the relationships between objects.

Instance Segmentation Knowledge Graphs +5

Learning Language-guided Adaptive Hyper-modality Representation for Multimodal Sentiment Analysis

1 code implementation9 Oct 2023 Haoyu Zhang, Yu Wang, Guanghao Yin, Kejun Liu, Yuanyuan Liu, Tianshu Yu

Though Multimodal Sentiment Analysis (MSA) proves effective by utilizing rich information from multiple sources (e. g., language, video, and audio), the potential sentiment-irrelevant and conflicting information across modalities may hinder the performance from being further improved.

Multimodal Sentiment Analysis

ITRE: Low-light Image Enhancement Based on Illumination Transmission Ratio Estimation

no code implementations8 Oct 2023 Yu Wang, Yihong Wang, Tong Liu, Xiubao Sui, Qian Chen

In this paper, we propose a novel Retinex-based method, called ITRE, which suppresses noise and artifacts from the origin of the model, prevents over-exposure throughout the enhancement process.

Low-Light Image Enhancement

Improving the Reliability of Large Language Models by Leveraging Uncertainty-Aware In-Context Learning

no code implementations7 Oct 2023 Yuchen Yang, Houqiang Li, Yanfeng Wang, Yu Wang

In this study, we introduce an uncertainty-aware in-context learning framework to empower the model to enhance or reject its output in response to uncertainty.

Hallucination In-Context Learning +1

A Topological Perspective on Demystifying GNN-Based Link Prediction Performance

1 code implementation6 Oct 2023 Yu Wang, Tong Zhao, Yuying Zhao, Yunchao Liu, Xueqi Cheng, Neil Shah, Tyler Derr

Despite the widespread belief that low-degree nodes exhibit poorer LP performance, our empirical findings provide nuances to this viewpoint and prompt us to propose a better metric, Topological Concentration (TC), based on the intersection of the local subgraph of each node with the ones of its neighbors.

Link Prediction

Fictitious Cross-Play: Learning Global Nash Equilibrium in Mixed Cooperative-Competitive Games

no code implementations5 Oct 2023 Zelai Xu, Yancheng Liang, Chao Yu, Yu Wang, Yi Wu

Alternatively, Policy-Space Response Oracles (PSRO) is an iterative framework for learning NE, where the best responses w. r. t.

Multi-agent Reinforcement Learning

Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models

no code implementations4 Oct 2023 An Yan, Yu Wang, Yiwu Zhong, Zexue He, Petros Karypis, Zihan Wang, chengyu dong, Amilcare Gentili, Chun-Nan Hsu, Jingbo Shang, Julian McAuley

Medical image classification is a critical problem for healthcare, with the potential to alleviate the workload of doctors and facilitate diagnoses of patients.

Image Classification Language Modelling +1

OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Control

1 code implementation22 Sep 2023 Botian Xu, Feng Gao, Chao Yu, Ruize Zhang, Yi Wu, Yu Wang

In this work, we introduce OmniDrones, an efficient and flexible platform tailored for reinforcement learning in drone control, built on Nvidia's Omniverse Isaac Sim.

reinforcement-learning

A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applications

1 code implementation31 Aug 2023 Yi Zhang, Yuying Zhao, Zhaoqing Li, Xueqi Cheng, Yu Wang, Olivera Kotevska, Philip S. Yu, Tyler Derr

Despite this progress, there is a lack of a comprehensive overview of the attacks and the techniques for preserving privacy in the graph domain.

Privacy Preserving

Unsupervised Active Learning: Optimizing Labeling Cost-Effectiveness for Automatic Speech Recognition

no code implementations28 Aug 2023 Zhisheng Zheng, Ziyang Ma, Yu Wang, Xie Chen

In recent years, speech-based self-supervised learning (SSL) has made significant progress in various tasks, including automatic speech recognition (ASR).

Active Learning Automatic Speech Recognition +3

Label Denoising through Cross-Model Agreement

no code implementations27 Aug 2023 Yu Wang, Xin Xin, Zaiqiao Meng, Joemon Jose, Fuli Feng

We employ the proposed DeCA on both the binary label scenario and the multiple label scenario.

Denoising Image Classification

Extreme Risk Mitigation in Reinforcement Learning using Extreme Value Theory

no code implementations24 Aug 2023 Karthik Somayaji NS, Yu Wang, Malachi Schram, Jan Drgona, Mahantesh Halappanavar, Frank Liu, Peng Li

Our work proposes to enhance the resilience of RL agents when faced with very rare and risky events by focusing on refining the predictions of the extreme values predicted by the state-action value function distribution.

reinforcement-learning Reinforcement Learning (RL)

Knowledge Graph Prompting for Multi-Document Question Answering

1 code implementation22 Aug 2023 Yu Wang, Nedim Lipka, Ryan A. Rossi, Alexa Siu, Ruiyi Zhang, Tyler Derr

Concurrently, the graph traversal agent acts as a local navigator that gathers pertinent context to progressively approach the question and guarantee retrieval quality.

graph construction Open-Domain Question Answering +1

LibriSQA: Advancing Free-form and Open-ended Spoken Question Answering with a Novel Dataset and Framework

1 code implementation20 Aug 2023 Zihan Zhao, Yiyang Jiang, Heyang Liu, Yanfeng Wang, Yu Wang

While Large Language Models (LLMs) have demonstrated commendable performance across a myriad of domains and tasks, existing LLMs still exhibit a palpable deficit in handling multimodal functionalities, especially for the Spoken Question Answering (SQA) task which necessitates precise alignment and deep interaction between speech and text features.

Multiple-choice Question Answering

DeSCo: Towards Generalizable and Scalable Deep Subgraph Counting

1 code implementation16 Aug 2023 Tianyu Fu, Chiyue Wei, Yu Wang, Rex Ying

We introduce DeSCo, a scalable neural deep subgraph counting pipeline, designed to accurately predict both the count and occurrence position of queries on target graphs post single training.

Graph Regression Position +1

Isomer: Isomerous Transformer for Zero-shot Video Object Segmentation

1 code implementation ICCV 2023 Yichen Yuan, Yifan Wang, Lijun Wang, Xiaoqi Zhao, Huchuan Lu, Yu Wang, Weibo Su, Lei Zhang

Recent leading zero-shot video object segmentation (ZVOS) works devote to integrating appearance and motion information by elaborately designing feature fusion modules and identically applying them in multiple feature stages.

Semantic Segmentation Video Object Segmentation +2

Learning Concise and Descriptive Attributes for Visual Recognition

1 code implementation ICCV 2023 An Yan, Yu Wang, Yiwu Zhong, chengyu dong, Zexue He, Yujie Lu, William Wang, Jingbo Shang, Julian McAuley

Recent advances in foundation models present new opportunities for interpretable visual recognition -- one can first query Large Language Models (LLMs) to obtain a set of attributes that describe each class, then apply vision-language models to classify images via these attributes.

Descriptive

Model Provenance via Model DNA

no code implementations4 Aug 2023 Xin Mu, Yu Wang, Yehong Zhang, JiaQi Zhang, Hui Wang, Yang Xiang, Yue Yu

Understanding the life cycle of the machine learning (ML) model is an intriguing area of research (e. g., understanding where the model comes from, how it is trained, and how it is used).

Representation Learning

Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation

1 code implementation28 Jul 2023 Xuefei Ning, Zinan Lin, Zixuan Zhou, Zifu Wang, Huazhong Yang, Yu Wang

This work aims at decreasing the end-to-end generation latency of large language models (LLMs).

Audio-aware Query-enhanced Transformer for Audio-Visual Segmentation

no code implementations25 Jul 2023 Jinxiang Liu, Chen Ju, Chaofan Ma, Yanfeng Wang, Yu Wang, Ya zhang

The goal of the audio-visual segmentation (AVS) task is to segment the sounding objects in the video frames using audio cues.

Segmentation

Ada3D : Exploiting the Spatial Redundancy with Adaptive Inference for Efficient 3D Object Detection

no code implementations ICCV 2023 Tianchen Zhao, Xuefei Ning, Ke Hong, Zhongyuan Qiu, Pu Lu, Yali Zhao, Linfeng Zhang, Lipu Zhou, Guohao Dai, Huazhong Yang, Yu Wang

One reason for this high resource consumption is the presence of a large number of redundant background points in Lidar point clouds, resulting in spatial redundancy in both 3D voxel and dense BEV map representations.

3D Object Detection Autonomous Driving +1

A Novel Multi-Task Model Imitating Dermatologists for Accurate Differential Diagnosis of Skin Diseases in Clinical Images

no code implementations17 Jul 2023 Yan-Jie Zhou, Wei Liu, Yuan Gao, Jing Xu, Le Lu, Yuping Duan, Hao Cheng, Na Jin, Xiaoyong Man, Shuang Zhao, Yu Wang

Skin diseases are among the most prevalent health issues, and accurate computer-aided diagnosis methods are of importance for both dermatologists and patients.

Multi-Task Learning

LINFA: a Python library for variational inference with normalizing flow and annealing

1 code implementation10 Jul 2023 Yu Wang, Emma R. Cobian, Jubilee Lee, Fang Liu, Jonathan D. Hauenstein, Daniele E. Schiavazzi

Variational inference is an increasingly popular method in statistics and machine learning for approximating probability distributions.

Variational Inference

Fairness and Diversity in Recommender Systems: A Survey

no code implementations10 Jul 2023 Yuying Zhao, Yu Wang, Yunchao Liu, Xueqi Cheng, Charu Aggarwal, Tyler Derr

Additionally, motivated by the concepts of user-level and item-level fairness, we broaden the understanding of diversity to encompass not only the item level but also the user level.

Fairness Recommendation Systems

Pushing the Limits of 3D Shape Generation at Scale

no code implementations20 Jun 2023 Yu Wang, Xuelin Qian, Jingyang Huo, Tiejun Huang, Bo Zhao, Yanwei Fu

Through the adaptation of the Auto-Regressive model and the utilization of large language models, we have developed a remarkable model with an astounding 3. 6 billion trainable parameters, establishing it as the largest 3D shape generation model to date, named Argus-3D.

3D Shape Generation Quantization +1

Multiverse Transformer: 1st Place Solution for Waymo Open Sim Agents Challenge 2023

no code implementations20 Jun 2023 Yu Wang, Tiebiao Zhao, Fan Yi

This technical report presents our 1st place solution for the Waymo Open Sim Agents Challenge (WOSAC) 2023.

motion prediction

Spatiotemporal-Augmented Graph Neural Networks for Human Mobility Simulation

no code implementations15 Jun 2023 Yu Wang, Tongya Zheng, Shunyu Liu, KaiXuan Chen, Zunlei Feng, Yunzhi Hao, Mingli Song

The human mobility simulation task aims to generate human mobility trajectories given a small set of trajectory data, which have aroused much concern due to the scarcity and sparsity of human mobility data.

OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models

1 code implementation15 Jun 2023 Enshu Liu, Xuefei Ning, Zinan Lin, Huazhong Yang, Yu Wang

Diffusion probabilistic models (DPMs) are a new class of generative models that have achieved state-of-the-art generation quality in various domains.

Pushing the Limits of Unsupervised Unit Discovery for SSL Speech Representation

1 code implementation15 Jun 2023 Ziyang Ma, Zhisheng Zheng, Guanrou Yang, Yu Wang, Chao Zhang, Xie Chen

Our models outperform other SSL models significantly on the LibriSpeech benchmark without the need for iterative re-clustering and re-training.

Automatic Speech Recognition Clustering +4

Enhanced Multimodal Representation Learning with Cross-modal KD

no code implementations CVPR 2023 Mengxi Chen, Linyu Xing, Yu Wang, Ya zhang

This paper explores the tasks of leveraging auxiliary modalities which are only available at training to enhance multimodal representation learning through cross-modal Knowledge Distillation (KD).

Contrastive Learning Emotion Classification +5

Design Principles for Model Generalization and Scalable AI Integration in Radio Access Networks

no code implementations9 Jun 2023 Pablo Soldati, Euhanna Ghadimi, Burak Demirel, Yu Wang, Raimundas Gaigalas, Mathias Sintorn

Artificial intelligence (AI) has emerged as a powerful tool for addressing complex and dynamic tasks in radio communication systems.

Management

SelfEvolve: A Code Evolution Framework via Large Language Models

no code implementations5 Jun 2023 Shuyang Jiang, Yuhao Wang, Yu Wang

However, while various methods have been proposed to augment LLMs with retrieved knowledge and enhance the quality of code generation, the performance of these retrieval-based methods is limited by the strength of the retrievers used.

Code Generation Retrieval

CDLT: A Dataset with Concept Drift and Long-Tailed Distribution for Fine-Grained Visual Categorization

no code implementations4 Jun 2023 Shuo Ye, Yufeng Shi, Ruxin Wang, Yu Wang, Jiamiao Xu, Chuanwu Yang, Xinge You

Data is the foundation for the development of computer vision, and the establishment of datasets plays an important role in advancing the techniques of fine-grained visual categorization~(FGVC).

Fine-Grained Visual Categorization

Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learning

1 code implementation CVPR 2023 Yu Wang, Pengchong Qiao, Chang Liu, Guoli Song, Xiawu Zheng, Jie Chen

We argue that an overlooked problem of robust SSL is its corrupted information on semantic level, practically limiting the development of the field.

Annotation-free Audio-Visual Segmentation

no code implementations18 May 2023 Jinxiang Liu, Yu Wang, Chen Ju, Chaofan Ma, Ya zhang, Weidi Xie

The objective of Audio-Visual Segmentation (AVS) is to localise the sounding objects within visual scenes by accurately predicting pixel-wise segmentation masks.

Image Segmentation Segmentation +1

V2Meow: Meowing to the Visual Beat via Video-to-Music Generation

no code implementations11 May 2023 Kun Su, Judith Yue Li, Qingqing Huang, Dima Kuzmin, Joonseok Lee, Chris Donahue, Fei Sha, Aren Jansen, Yu Wang, Mauro Verzetti, Timo I. Denk

Video-to-music generation demands both a temporally localized high-quality listening experience and globally aligned video-acoustic signatures.

Music Generation

Conditional Denoising Diffusion for Sequential Recommendation

no code implementations22 Apr 2023 Yu Wang, Zhiwei Liu, Liangwei Yang, Philip S. Yu

Generative models have attracted significant interest due to their ability to handle uncertainty by learning the inherent data distributions.

Denoising Sequential Recommendation

OpenMix+: Revisiting Data Augmentation for Open Set Recognition

1 code implementation IEEE Transactions on Circuits and Systems for Video Technology 2023 Guosong Jiang, Pengfei Zhu, Yu Wang, QinGhua Hu

In this paper, we point out that balancing between structural risk and open space risk is crucial for open set recognition, and re-formalize it as open set structural risk.

Data Augmentation Open Set Learning

HybridFusion: LiDAR and Vision Cross-Source Point Cloud Fusion

no code implementations10 Apr 2023 Yu Wang, Shuhui Bu, Lin Chen, Yifei Dong, Kun Li, Xuefeng Cao, Ke Li

First, the point cloud is divided into small patches, and a matching patch set is selected based on global descriptors and spatial distribution, which constitutes the coarse matching process.

Point Cloud Registration

Generalization Matters: Loss Minima Flattening via Parameter Hybridization for Efficient Online Knowledge Distillation

1 code implementation CVPR 2023 Tianli Zhang, Mengqi Xue, Jiangtao Zhang, Haofei Zhang, Yu Wang, Lechao Cheng, Jie Song, Mingli Song

Most existing online knowledge distillation(OKD) techniques typically require sophisticated modules to produce diverse knowledge for improving students' generalization ability.

Knowledge Distillation

LiDARFormer: A Unified Transformer-based Multi-task Network for LiDAR Perception

no code implementations21 Mar 2023 Zixiang Zhou, Dongqiangzi Ye, Weijia Chen, Yufei Xie, Yu Wang, Panqu Wang, Hassan Foroosh

The proposed LiDARFormer utilizes cross-space global contextual feature information and exploits cross-task synergy to boost the performance of LiDAR perception tasks across multiple large-scale datasets and benchmarks.

Multi-Task Learning Segmentation +1

DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery

no code implementations17 Mar 2023 Chaofan Ma, Yuhuan Yang, Chen Ju, Fei Zhang, Jinxiang Liu, Yu Wang, Ya zhang, Yanfeng Wang

However, the challenges exist as there is one structural difference between generative and discriminative models, which limits the direct use.

Object Object Discovery +1

Interpretable Outlier Summarization

no code implementations11 Mar 2023 Yu Wang, Lei Cao, Yizhou Yan, Samuel Madden

Moreover, to effectively handle high dimensional, highly complex data sets which are hard to summarize with simple rules, we propose a localized STAIR approach, called L-STAIR.

Anomaly Detection Outlier Detection

Demystifying What Code Summarization Models Learned

no code implementations4 Mar 2023 Yu Wang, Ke Wang

Based on these findings, we present two example uses of the formal definition of patterns: a new method for evaluating the robustness and a new technique for improving the accuracy of code summarization models.

Code Summarization Image Classification

A Targeted Accuracy Diagnostic for Variational Approximations

1 code implementation24 Feb 2023 Yu Wang, Mikołaj Kasprzak, Jonathan H. Huggins

Variational Inference (VI) is an attractive alternative to Markov Chain Monte Carlo (MCMC) due to its computational efficiency in the case of large datasets and/or complex models with high-dimensional parameters.

Computational Efficiency Variational Inference

Knowledge-aware Bayesian Co-attention for Multimodal Emotion Recognition

no code implementations20 Feb 2023 Zihan Zhao, Yu Wang, Yanfeng Wang

Multimodal emotion recognition is a challenging research area that aims to fuse different modalities to predict human emotion.

Multimodal Emotion Recognition

Differentially Private Normalizing Flows for Density Estimation, Data Synthesis, and Variational Inference with Application to Electronic Health Records

1 code implementation11 Feb 2023 Bingyue Su, Yu Wang, Daniele E. Schiavazzi, Fang Liu

We use normalizing flows (NF), a family of deep generative models, to estimate the probability density of a dataset with differential privacy (DP) guarantees, from which privacy-preserving synthetic data are generated.

Density Estimation Privacy Preserving +1

Toward Extremely Lightweight Distracted Driver Recognition With Distillation-Based Neural Architecture Search and Knowledge Transfer

1 code implementation9 Feb 2023 Dichao Liu, Toshihiko Yamasaki, Yu Wang, Kenji Mase, Jien Kato

Experimental results on the Statefarm Distracted Driver Detection Dataset and AUC Distracted Driver Dataset show that the proposed approach is highly effective for recognizing distracted driving behaviors from photos: (1) the teacher network's accuracy surpasses the previous best accuracy; (2) the student network achieves very high accuracy with only 0. 42M parameters (around 55% of the previous most lightweight model).

Knowledge Distillation Neural Architecture Search +1

Learning Graph-Enhanced Commander-Executor for Multi-Agent Navigation

1 code implementation8 Feb 2023 Xinyi Yang, Shiyu Huang, Yiwen Sun, Yuxiang Yang, Chao Yu, Wei-Wei Tu, Huazhong Yang, Yu Wang

Goal-conditioned hierarchical reinforcement learning (HRL) provides a promising direction to tackle this challenge by introducing a hierarchical structure to decompose the search space, where the low-level policy predicts primitive actions in the guidance of the goals derived from the high-level policy.

Hierarchical Reinforcement Learning Multi-agent Reinforcement Learning +2

Dynamic Ensemble of Low-fidelity Experts: Mitigating NAS "Cold-Start"

1 code implementation2 Feb 2023 Junbo Zhao, Xuefei Ning, Enshu Liu, Binxin Ru, Zixuan Zhou, Tianchen Zhao, Chen Chen, Jiajin Zhang, Qingmin Liao, Yu Wang

In the first step, we train different sub-predictors on different types of available low-fidelity information to extract beneficial knowledge as low-fidelity experts.

Neural Architecture Search

Interpretable and Scalable Graphical Models for Complex Spatio-temporal Processes

no code implementations15 Jan 2023 Yu Wang

Fourth, it proposes a modular and interpretable framework for unsupervised and weakly-supervised probabilistic topic modeling of time-varying data that combines generative statistical models with computational geometric methods.

EEG Electroencephalogram (EEG) +2

RealGraph: A Multiview Dataset for 4D Real-world Context Graph Generation

no code implementations ICCV 2023 Haozhe Lin, Zequn Chen, Jinzhi Zhang, Bing Bai, Yu Wang, Ruqi Huang, Lu Fang

The CGG task capitalizes on the calibrated multiview videos of a dynamic scene, and targets at recovering semantic information (coordination, trajectories and relationships) of the presented objects in the form of spatio-temporal context graph in 4D space.

Graph Generation Scene Understanding

DDH-QA: A Dynamic Digital Humans Quality Assessment Database

1 code implementation24 Dec 2022 ZiCheng Zhang, Yingjie Zhou, Wei Sun, Wei Lu, Xiongkuo Min, Yu Wang, Guangtao Zhai

In recent years, large amounts of effort have been put into pushing forward the real-world application of dynamic digital human (DDH).

Video Quality Assessment

Detecting Objects with Context-Likelihood Graphs and Graph Refinement

no code implementations ICCV 2023 Aritra Bhowmik, Yu Wang, Nora Baka, Martin R. Oswald, Cees G. M. Snoek

Contrary to existing methods, which learn objects and relations separately, our key idea is to learn the object-relation distribution jointly.

Object object-detection +2

Hybrid Rule-Neural Coreference Resolution System based on Actor-Critic Learning

no code implementations20 Dec 2022 Yu Wang, Hongxia Jin

A coreference resolution system is to cluster all mentions that refer to the same entity in a given context.

coreference-resolution

A Robust Semantic Frame Parsing Pipeline on a New Complex Twitter Dataset

no code implementations18 Dec 2022 Yu Wang, Hongxia Jin

In this paper, we introduce a robust semantic frame parsing pipeline that can handle both \emph{OOD} patterns and \emph{OOV} tokens in conjunction with a new complex Twitter dataset that contains long tweets with more \emph{OOD} patterns and \emph{OOV} tokens.

Semantic Frame Parsing Spoken Language Understanding

Neural Coreference Resolution based on Reinforcement Learning

no code implementations18 Dec 2022 Yu Wang, Hongxia Jin

The target of a coreference resolution system is to cluster all mentions that refer to the same entity in a given context.

Clustering coreference-resolution +2

Localized Contrastive Learning on Graphs

no code implementations8 Dec 2022 Hengrui Zhang, Qitian Wu, Yu Wang, Shaofeng Zhang, Junchi Yan, Philip S. Yu

Contrastive learning methods based on InfoNCE loss are popular in node representation learning tasks on graph-structured data.

Contrastive Learning Data Augmentation +1

Fairness and Explainability: Bridging the Gap Towards Fair Model Explanations

1 code implementation7 Dec 2022 Yuying Zhao, Yu Wang, Tyler Derr

Although research efforts have been devoted to measuring and mitigating bias, they mainly study bias from the result-oriented perspective while neglecting the bias encoded in the decision-making procedure.

Decision Making Fairness

Multi-view deep learning based molecule design and structural optimization accelerates the SARS-CoV-2 inhibitor discovery

no code implementations3 Dec 2022 Chao Pang, Yu Wang, Yi Jiang, Ruheng Wang, Ran Su, Leyi Wei

Moreover, case study results on targeted molecule generation for the SARS-CoV-2 main protease (Mpro) show that by integrating molecule docking into our model as chemical priori, we successfully generate new small molecules with desired drug-like properties for the Mpro, potentially accelerating the de novo design of Covid-19 drugs.

Benchmarking Representation Learning

Few-Shot Specific Emitter Identification via Hybrid Data Augmentation and Deep Metric Learning

1 code implementation1 Dec 2022 Cheng Wang, Xue Fu, Yu Wang, Guan Gui, Haris Gacanin, Hikmet Sari, Fumiyuki Adachi

Specific emitter identification (SEI) is a potential physical layer authentication technology, which is one of the most critical complements of upper layer authentication.

Data Augmentation Metric Learning

A Bayesian Approach to Reconstructing Interdependent Infrastructure Networks from Cascading Failures

no code implementations28 Nov 2022 Yu Wang, Jin-Zhu Yu, Hiba Baroud

We propose a scalable nonparametric Bayesian approach to reconstruct the topology of interdependent infrastructure networks from observations of cascading failures.

SPE-Net: Boosting Point Cloud Analysis via Rotation Robustness Enhancement

1 code implementation15 Nov 2022 Zhaofan Qiu, Yehao Li, Yu Wang, Yingwei Pan, Ting Yao, Tao Mei

In this paper, we propose a novel deep architecture tailored for 3D point cloud applications, named as SPE-Net.

Cross-layer Attention Network for Fine-grained Visual Categorization

no code implementations17 Oct 2022 Ranran Huang, Yu Wang, Huazhong Yang

Learning discriminative representations for subtle localized details plays a significant role in Fine-grained Visual Categorization (FGVC).

Fine-Grained Visual Categorization

Controlling Bias Exposure for Fair Interpretable Predictions

1 code implementation14 Oct 2022 Zexue He, Yu Wang, Julian McAuley, Bodhisattwa Prasad Majumder

However, when sensitive information is semantically entangled with the task information of the input, e. g., gender information is predictive for a profession, a fair trade-off between task performance and bias mitigation is difficult to achieve.

Attribute Task 2 +2

Out-of-Distribution Detection with Hilbert-Schmidt Independence Optimization

1 code implementation26 Sep 2022 Jingyang Lin, Yu Wang, Qi Cai, Yingwei Pan, Ting Yao, Hongyang Chao, Tao Mei

Existing works attempt to solve the problem by explicitly imposing uncertainty on classifiers when OOD inputs are exposed to the classifier during training.

Outlier Detection Out-of-Distribution Detection +1

LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perception

no code implementations19 Sep 2022 Dongqiangzi Ye, Zixiang Zhou, Weijia Chen, Yufei Xie, Yu Wang, Panqu Wang, Hassan Foroosh

LidarMultiNet is extensively tested on both Waymo Open Dataset and nuScenes dataset, demonstrating for the first time that major LiDAR perception tasks can be unified in a single strong network that is trained end-to-end and achieves state-of-the-art performance.

3D Object Detection 3D Semantic Segmentation +3

Infrared: A Meta Bug Detector

no code implementations18 Sep 2022 Chi Zhang, Yu Wang, Linzhang Wang

The recent breakthroughs in deep learning methods have sparked a wave of interest in learning-based bug detectors.

Anomaly Detection

ContrastVAE: Contrastive Variational AutoEncoder for Sequential Recommendation

1 code implementation27 Aug 2022 Yu Wang, Hengrui Zhang, Zhiwei Liu, Liangwei Yang, Philip S. Yu

Then we propose Contrastive Variational AutoEncoder (ContrastVAE in short), a two-branched VAE model with contrastive regularization as an embodiment of ContrastELBO for sequential recommendation.

Contrastive Learning Sequential Recommendation

Implementation of improved RGBD 3D target detection model based on FPGA heterogeneous computing architecture

no code implementations 2022/08/15 2022 Yu Wang, Wenbin, FENG Chongchong YU, Xinyu Hu, Yuqiu ZHANG4

In order to solve the problems of low model accuracy, poor computing power, poor parallel ability and excessive power consumption in the deployment of RGBD based 3 D target detection model at the embedded end, this paper first proposes an improved RGBD 3 D target detection model based on ENet semantic segmentation model, which takes ENet as the semantic segmentation network, RGB image and depth information are fused to realize 3 D target detection. Secondly, in order to apply the model at the edge, this paper constructs a lightweight network and cuts the network in the down-sampling stage of ENet model. Finally, this paper uses Xilinx ZCU104 as the hardware development kit, which takes FPGA as the auxiliary parallel operation unit and ARM as the main operation unit. It is a heterogeneous computing architecture with the ability to deal with complex operations. The architecture uses FPGA to accelerate the depth model in parallel, which improves the operation speed and reduces the power consumption. The test results of the model on ZCU104 are compared with other hardware. The results show that while ensuring the accuracy, the power consumption of the heterogeneous computing architecture used in this paper is 93% lowerthan that of Intel Xeon e5-2620 v4 CPU, the speed is 12 times higher, and the speed is more than 180 times higher than that of ARM Cortex-A53 commonly used at the edge.

Semantic Segmentation

Ultra Lite Convolutional Neural Network for Fast Automatic Modulation Classification in Low-Resource Scenarios

1 code implementation9 Aug 2022 Lantu Guo, Yu Wang, Yun Lin, Haitao Zhao, Guan Gui

Automatic modulation classification (AMC) is a key technique for designing non-cooperative communication systems, and deep learning (DL) is applied effectively to AMC for improving classification accuracy.

Classification Data Augmentation

BSDGAN: Balancing Sensor Data Generative Adversarial Networks for Human Activity Recognition

no code implementations7 Aug 2022 Yifan Hu, Yu Wang

However, due to the inconsistent frequency of human activities, the amount of data for each activity in the human activity dataset is imbalanced.

Human Activity Recognition

CLOSE: Curriculum Learning On the Sharing Extent Towards Better One-shot NAS

1 code implementation16 Jul 2022 Zixuan Zhou, Xuefei Ning, Yi Cai, Jiashu Han, Yiping Deng, Yuhan Dong, Huazhong Yang, Yu Wang

Specifically, we train the supernet with a large sharing extent (an easier curriculum) at the beginning and gradually decrease the sharing extent of the supernet (a harder curriculum).

Neural Architecture Search

Few-Shot Specific Emitter Identification via Deep Metric Ensemble Learning

2 code implementations14 Jul 2022 Yu Wang, Guan Gui, Yun Lin, Hsiao-Chun Wu, Chau Yuen, Fumiyuki Adachi

Thus, we focus on few-shot SEI (FS-SEI) for aircraft identification via automatic dependent surveillance-broadcast (ADS-B) signals, and a novel FS-SEI method is proposed, based on deep metric ensemble learning (DMEL).

Ensemble Learning Metric Learning

Multi-level Fusion of Wav2vec 2.0 and BERT for Multimodal Emotion Recognition

no code implementations11 Jul 2022 Zihan Zhao, Yanfeng Wang, Yu Wang

The research and applications of multimodal emotion recognition have become increasingly popular recently.

Multimodal Emotion Recognition Transfer Learning

Dual Vision Transformer

1 code implementation11 Jul 2022 Ting Yao, Yehao Li, Yingwei Pan, Yu Wang, Xiao-Ping Zhang, Tao Mei

Dual-ViT is henceforth able to reduce the computational complexity without compromising much accuracy.

Class-Specific Semantic Reconstruction for Open Set Recognition

no code implementations5 Jul 2022 Hongzhi Huang, Yu Wang, QinGhua Hu, Ming-Ming Cheng

In this study, we propose a novel method, called Class-Specific Semantic Reconstruction (CSSR), that integrates the power of AE and prototype learning.

Open Set Learning

Collaboration-Aware Graph Convolutional Network for Recommender Systems

1 code implementation3 Jul 2022 Yu Wang, Yuying Zhao, Yi Zhang, Tyler Derr

Graph Neural Networks (GNNs) have been successfully adopted in recommender systems by virtue of the message-passing that implicitly captures collaborative effect.

Recommendation Systems

Multi-Granularity Regularized Re-Balancing for Class Incremental Learning

1 code implementation30 Jun 2022 Huitong Chen, Yu Wang, QinGhua Hu

Re-balancing methods are used to alleviate the influence of data imbalance; however, we empirically discover that they would under-fit new classes.

Class Incremental Learning Incremental Learning

On Structural Explanation of Bias in Graph Neural Networks

1 code implementation24 Jun 2022 Yushun Dong, Song Wang, Yu Wang, Tyler Derr, Jundong Li

The low transparency on how the structure of the input network influences the bias in GNN outcome largely limits the safe adoption of GNNs in various decision-critical scenarios.

Decision Making Fairness

Improving Fairness in Graph Neural Networks via Mitigating Sensitive Attribute Leakage

1 code implementation7 Jun 2022 Yu Wang, Yuying Zhao, Yushun Dong, Huiyuan Chen, Jundong Li, Tyler Derr

Motivated by our analysis, we propose Fair View Graph Neural Network (FairVGNN) to generate fair views of features by automatically identifying and masking sensitive-correlated features considering correlation variation after feature propagation.

Attribute Fairness +1

Differentiable Invariant Causal Discovery

no code implementations31 May 2022 Yu Wang, An Zhang, Xiang Wang, Yancheng Yuan, Xiangnan He, Tat-Seng Chua

This paper proposes Differentiable Invariant Causal Discovery (DICD), utilizing the multi-environment information based on a differentiable framework to avoid learning spurious edges and wrong causal directions.

Causal Discovery

Efficient Reinforcement Learning from Demonstration Using Local Ensemble and Reparameterization with Split and Merge of Expert Policies

no code implementations23 May 2022 Yu Wang, Fang Liu

The current work on reinforcement learning (RL) from demonstrations often assumes the demonstrations are samples from an optimal policy, an unrealistic assumption in practice.

Continuous Control Reinforcement Learning (RL)

Brachial Plexus Nerve Trunk Segmentation Using Deep Learning: A Comparative Study with Doctors' Manual Segmentation

no code implementations17 May 2022 Yu Wang, Binbin Zhu, Lingsi Kong, Jianlin Wang, Bin Gao, Jianhua Wang, Dingcheng Tian, YuDong Yao

With the help of deep learning methods, the automatic identification or segmentation of nerves can be realized, assisting doctors in completing nerve block anesthesia accurately and efficiently.

Segmentation

BronchusNet: Region and Structure Prior Embedded Representation Learning for Bronchus Segmentation and Classification

no code implementations14 May 2022 Wenhao Huang, Haifan Gong, huan zhang, Yu Wang, Haofeng Li, Guanbin Li, Hong Shen

CT-based bronchial tree analysis plays an important role in the computer-aided diagnosis for respiratory diseases, as it could provide structured information for clinicians.

Classification Graph Learning +3

Self-Supervised Masking for Unsupervised Anomaly Detection and Localization

no code implementations13 May 2022 Chaoqin Huang, Qinwei Xu, Yanfeng Wang, Yu Wang, Ya zhang

To extend the reconstruction-based anomaly detection architecture to the localized anomalies, we propose a self-supervised learning approach through random masking and then restoring, named Self-Supervised Masking (SSM) for unsupervised anomaly detection and localization.

Defect Detection Medical Diagnosis +2

GypSum: Learning Hybrid Representations for Code Summarization

1 code implementation26 Apr 2022 Yu Wang, Yu Dong, Xuesong Lu, Aoying Zhou

Current deep learning models for code summarization generally follow the principle in neural machine translation and adopt the encoder-decoder framework, where the encoder learns the semantic representations from source code and the decoder transforms the learnt representations into human-readable text that describes the functionality of code snippets.

Code Summarization Graph Attention +3

R2-Trans:Fine-Grained Visual Categorization with Redundancy Reduction

no code implementations21 Apr 2022 Yu Wang, Shuo Ye, Shujian Yu, Xinge You

In this paper, we present a novel approach for FGVC, which can simultaneously make use of partial yet sufficient discriminative information in environmental cues and also compress the redundant information in class-token with respect to the target.

Fine-Grained Visual Categorization

Predicting Solar Flares Using CNN and LSTM on Two Solar Cycles of Active Region Data

1 code implementation7 Apr 2022 Zeyu Sun, Monica G. Bobra, Xiantong Wang, Yu Wang, Hu Sun, Tamas Gombosi, Yang Chen, Alfred Hero

We consider the flare prediction problem that distinguishes flare-imminent active regions that produce an M- or X-class flare in the future 24 hours, from quiet active regions that do not produce any flare within $\pm 24$ hours.

Attribute

Primal-dual Estimator Learning: an Offline Constrained Moving Horizon Estimation Method with Feasibility and Near-optimality Guarantees

no code implementations6 Apr 2022 Wenhan Cao, Jingliang Duan, Shengbo Eben Li, Chen Chen, Chang Liu, Yu Wang

Both the primal and dual estimators are learned from data using supervised learning techniques, and the explicit sample size is provided, which enables us to guarantee the quality of each learned estimator in terms of feasibility and optimality.

Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentation

1 code implementation19 Mar 2022 Junwen Pan, Pengfei Zhu, Kaihua Zhang, Bing Cao, Yu Wang, Dingwen Zhang, Junwei Han, QinGhua Hu

Semantic segmentation with limited annotations, such as weakly supervised semantic segmentation (WSSS) and semi-supervised semantic segmentation (SSSS), is a challenging task that has attracted much attention recently.

Pseudo Label Segmentation +3

CodedVTR: Codebook-based Sparse Voxel Transformer with Geometric Guidance

no code implementations CVPR 2022 Tianchen Zhao, Niansong Zhang, Xuefei Ning, He Wang, Li Yi, Yu Wang

We propose CodedVTR (Codebook-based Voxel TRansformer), which improves data efficiency and generalization ability for 3D sparse voxel transformers.

3D Semantic Segmentation

Efficient Federated Learning on Knowledge Graphs via Privacy-preserving Relation Embedding Aggregation

1 code implementation17 Mar 2022 Kai Zhang, Yu Wang, Hongyi Wang, Lifu Huang, Carl Yang, Xun Chen, Lichao Sun

Furthermore, we propose a Federated learning paradigm with privacy-preserving Relation embedding aggregation (FedR) to tackle the privacy issue in FedE.

Entity Embeddings Federated Learning +4

A Data Augmentation Method for Fully Automatic Brain Tumor Segmentation

no code implementations13 Feb 2022 Yu Wang, Yarong Ji, Hongbing Xiao

Then the tensor was mapped to a matrix which was used to mix the one-hot encoded labels of the above image patches.

Brain Tumor Segmentation Data Augmentation +2

ChemicalX: A Deep Learning Library for Drug Pair Scoring

1 code implementation10 Feb 2022 Benedek Rozemberczki, Charles Tapley Hoyt, Anna Gogleva, Piotr Grabowski, Klas Karis, Andrej Lamov, Andriy Nikolov, Sebastian Nilsson, Michael Ughetto, Yu Wang, Tyler Derr, Benjamin M Gyori

In this paper, we introduce ChemicalX, a PyTorch-based deep learning library designed for providing a range of state of the art models to solve the drug pair scoring task.

BIG-bench Machine Learning

Evaluating the impact of quarantine measures on COVID-19 spread

no code implementations9 Feb 2022 Renquan Zhang, Yu Wang, Zheng Lv, Sen Pei

We generate counterfactual simulations to estimate effectiveness of quarantine measures.

counterfactual Decision Making

Large-scale Personalized Video Game Recommendation via Social-aware Contextualized Graph Neural Network

1 code implementation7 Feb 2022 Liangwei Yang, Zhiwei Liu, Yu Wang, Chen Wang, Ziwei Fan, Philip S. Yu

We conduct a comprehensive analysis of users' online game behaviors, which motivates the necessity of handling those three characteristics in the online game recommendation.

Recommendation Systems

Improving Out-of-Distribution Robustness via Selective Augmentation

2 code implementations2 Jan 2022 Huaxiu Yao, Yu Wang, Sai Li, Linjun Zhang, Weixin Liang, James Zou, Chelsea Finn

Machine learning algorithms typically assume that training and test examples are drawn from the same distribution.

LAR-SR: A Local Autoregressive Model for Image Super-Resolution

1 code implementation CVPR 2022 Baisong Guo, Xiaoyun Zhang, HaoNing Wu, Yu Wang, Ya zhang, Yan-Feng Wang

Previous super-resolution (SR) approaches often formulate SR as a regression problem and pixel wise restoration, which leads to a blurry and unreal SR output.

Image Super-Resolution

Transferrable Contrastive Learning for Visual Domain Adaptation

no code implementations14 Dec 2021 Yang Chen, Yingwei Pan, Yu Wang, Ting Yao, Xinmei Tian, Tao Mei

From this point, we present a particular paradigm of self-supervised learning tailored for domain adaptation, i. e., Transferrable Contrastive Learning (TCL), which links the SSL and the desired cross-domain transferability congruently.

Contrastive Learning Domain Adaptation +2

A Style and Semantic Memory Mechanism for Domain Generalization

no code implementations ICCV 2021 Yang Chen, Yu Wang, Yingwei Pan, Ting Yao, Xinmei Tian, Tao Mei

Correspondingly, we also propose a novel "jury" mechanism, which is particularly effective in learning useful semantic feature commonalities among domains.

Domain Generalization

Multi-Agent Vulnerability Discovery for Autonomous Driving with Hazard Arbitration Reward

no code implementations12 Dec 2021 Weilin Liu, Ye Mu, Chao Yu, Xuefei Ning, Zhong Cao, Yi Wu, Shuang Liang, Huazhong Yang, Yu Wang

These scenarios indeed correspond to the vulnerabilities of the under-test driving policies, thus are meaningful for their further improvements.

Autonomous Driving Multi-agent Reinforcement Learning

Multiway Ensemble Kalman Filter

1 code implementation8 Dec 2021 Yu Wang, Alfred Hero

In this work, we study the emergence of sparsity and multiway structures in second-order statistical characterizations of dynamical processes governed by partial differential equations (PDEs).

Imbalanced Graph Classification via Graph-of-Graph Neural Networks

2 code implementations1 Dec 2021 Yu Wang, Yuying Zhao, Neil Shah, Tyler Derr

To this end, we introduce a novel framework, Graph-of-Graph Neural Networks (G$^2$GNN), which alleviates the graph imbalance issue by deriving extra supervision globally from neighboring graphs and locally from stochastic augmentations of graphs.

Graph Classification Node Classification

Learning Dynamic Compact Memory Embedding for Deformable Visual Object Tracking

no code implementations23 Nov 2021 Pengfei Zhu, Hongtao Yu, Kaihua Zhang, Yu Wang, Shuai Zhao, Lei Wang, Tianzhu Zhang, QinGhua Hu

To address this issue, segmentation-based trackers have been proposed that employ per-pixel matching to improve the tracking performance of deformable objects effectively.

Segmentation Visual Object Tracking +1

Learning Dynamic Preference Structure Embedding From Temporal Networks

1 code implementation23 Nov 2021 Tongya Zheng, Zunlei Feng, Yu Wang, Chengchao Shen, Mingli Song, Xingen Wang, Xinyu Wang, Chun Chen, Hao Xu

Our proposed Dynamic Preference Structure (DPS) framework consists of two stages: structure sampling and graph fusion.

Graph Sampling

Cannot find the paper you are looking for? You can Submit a new open access paper.