Search Results for author: Wei Chen

Found 395 papers, 114 papers with code

A Structure-Aware Argument Encoder for Literature Discourse Analysis

1 code implementation COLING 2022 Yinzi Li, Wei Chen, Zhongyu Wei, Yujun Huang, Chujun Wang, Siyuan Wang, Qi Zhang, Xuanjing Huang, Libo Wu

Existing research for argument representation learning mainly treats tokens in the sentence equally and ignores the implied structure information of argumentative context.

Position Representation Learning +1

Dual Refinement Underwater Object Detection Network

1 code implementation ECCV 2020 Baojie Fan, Wei Chen, Yang Cong, Jiandong Tian

Due to the complex underwater environment, underwater imaging often encounters some problems such as blur, scale variation, color shift, and texture distortion.

Object object-detection +1

Combinatorial Pure Exploration for Dueling Bandit

no code implementations ICML 2020 Wei Chen, Yihan Du, Longbo Huang, Haoyu Zhao

For Borda winner, we establish a reduction of the problem to the original CPE-MAB setting and design PAC and exact algorithms that achieve both the sample complexity similar to that in the CPE-MAB setting (which is nearly optimal for a subclass of problems) and polynomial running time per round.

Position

Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning

no code implementations21 Feb 2024 Zhaorui Yang, Qian Liu, Tianyu Pang, Han Wang, Haozhe Feng, Minfeng Zhu, Wei Chen

The surge in Large Language Models (LLMs) has revolutionized natural language processing, but fine-tuning them for specific tasks often encounters challenges in balancing performance and preserving general instruction-following abilities.

Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective

no code implementations18 Feb 2024 Jiaxi Hu, Yuehong Hu, Wei Chen, Ming Jin, Shirui Pan, Qingsong Wen, Yuxuan Liang

In long-term time series forecasting (LTSF) tasks, existing deep learning models overlook the crucial characteristic that discrete time series originate from underlying continuous dynamic systems, resulting in a lack of extrapolation and evolution capabilities.

Time Series Time Series Forecasting

AI Hospital: Interactive Evaluation and Collaboration of LLMs as Intern Doctors for Clinical Diagnosis

1 code implementation15 Feb 2024 Zhihao Fan, Jialong Tang, Wei Chen, Siyuan Wang, Zhongyu Wei, Jun Xi, Fei Huang, Jingren Zhou

To simulate the procedure, we collect high-quality medical records to create patient, examiner, and medical director agents.

Question Answering

Model Compression and Efficient Inference for Large Language Models: A Survey

no code implementations15 Feb 2024 Wenxiao Wang, Wei Chen, Yicong Luo, Yongliu Long, Zhengkai Lin, Liye Zhang, Binbin Lin, Deng Cai, Xiaofei He

However, Large language models have two prominent characteristics compared to smaller models: (1) Most of compression algorithms require finetuning or even retraining the model after compression.

Knowledge Distillation Model Compression +1

AgentLens: Visual Analysis for Agent Behaviors in LLM-based Autonomous Systems

no code implementations14 Feb 2024 Jiaying Lu, Bo Pan, Jieyi Chen, Yingchaojie Feng, Jingyuan Hu, Yuchen Peng, Wei Chen

Recently, Large Language Model based Autonomous system(LLMAS) has gained great popularity for its potential to simulate complicated behaviors of human societies.

Language Modelling Large Language Model

Prismatic: Interactive Multi-View Cluster Analysis of Concept Stocks

no code implementations14 Feb 2024 Wong Kam-Kwai, Yan Luo, Xuanwu Yue, Wei Chen, Huamin Qu

Financial cluster analysis allows investors to discover investment alternatives and avoid undertaking excessive risks.

Clustering

A Unified Causal View of Instruction Tuning

no code implementations9 Feb 2024 Lu Chen, Wei Huang, Ruqing Zhang, Wei Chen, Jiafeng Guo, Xueqi Cheng

The key idea is to learn task-required causal factors and only use those to make predictions for a given task.

Reinforcement Learning as a Catalyst for Robust and Fair Federated Learning: Deciphering the Dynamics of Client Contributions

no code implementations8 Feb 2024 Jialuo He, Wei Chen, Xiaojin Zhang

Recent advancements in federated learning (FL) have produced models that retain user privacy by training across multiple decentralized devices or systems holding local data samples.

Continuous Control Fairness +1

Learning by Doing: An Online Causal Reinforcement Learning Framework with Causal-Aware Policy

no code implementations7 Feb 2024 Ruichu Cai, Siyang Huang, Jie Qiao, Wei Chen, Yan Zeng, Keli Zhang, Fuchun Sun, Yang Yu, Zhifeng Hao

As a key component to intuitive cognition and reasoning solutions in human intelligence, causal knowledge provides great potential for reinforcement learning (RL) agents' interpretability towards decision-making by helping reduce the searching space.

Decision Making Reinforcement Learning (RL)

Position Paper: What Can Large Language Models Tell Us about Time Series Analysis

1 code implementation5 Feb 2024 Ming Jin, Yifan Zhang, Wei Chen, Kexin Zhang, Yuxuan Liang, Bin Yang, Jindong Wang, Shirui Pan, Qingsong Wen

Time series analysis is essential for comprehending the complexities inherent in various real-world systems and applications.

Decision Making Position +3

EasyFS: an Efficient Model-free Feature Selection Framework via Elastic Transformation of Features

no code implementations4 Feb 2024 Jianming Lv, Sijun Xia, Depin Liang, Wei Chen

Traditional model-free feature selection methods treat each feature independently while disregarding the interrelationships among features, which leads to relatively poor performance compared with the model-aware methods.

feature selection

Query-Efficient Correlation Clustering with Noisy Oracle

no code implementations2 Feb 2024 Yuko Kuroki, Atsushi Miyauchi, Francesco Bonchi, Wei Chen

We study a general clustering setting in which we have $n$ elements to be clustered, and we aim to perform as few queries as possible to an oracle that returns a noisy sample of the similarity between two elements.

Clustering Multi-Armed Bandits

Shapelet-based Model-agnostic Counterfactual Local Explanations for Time Series Classification

no code implementations2 Feb 2024 Qi Huang, Wei Chen, Thomas Bäck, Niki van Stein

In this work, we propose a model-agnostic instance-based post-hoc explainability method for time series classification.

Classification counterfactual +2

CauESC: A Causal Aware Model for Emotional Support Conversation

no code implementations31 Jan 2024 Wei Chen, Hengxu Lin, Qun Zhang, Xiaojin Zhang, Xiang Bai, Xuanjing Huang, Zhongyu Wei

Emotional Support Conversation aims at reducing the seeker's emotional distress through supportive response.

Synthetic data enables faster annotation and robust segmentation for multi-object grasping in clutter

no code implementations24 Jan 2024 Dongmyoung Lee, Wei Chen, Nicolas Rojas

In this work, we propose a synthetic data generation method that minimizes human intervention and makes downstream image segmentation algorithms more robust by combining a generated synthetic dataset with a smaller real-world dataset (hybrid dataset).

Image Segmentation Object +7

Cascading Reinforcement Learning

no code implementations17 Jan 2024 Yihan Du, R. Srikant, Wei Chen

In the cascading bandit model, at each timestep, an agent recommends an ordered subset of items (called an item list) from a pool of items, each associated with an unknown attraction probability.

Recommendation Systems reinforcement-learning

Attention-Based CNN-BiLSTM for Sleep State Classification of Spatiotemporal Wide-Field Calcium Imaging Data

1 code implementation16 Jan 2024 Xiaohui Zhang, Eric C. Landsness, Hanyang Miao, Wei Chen, Michelle Tang, Lindsey M. Brier, Joseph P. Culver, Jin-Moo Lee, Mark A. Anastasio

Comparison with Existing Method: On a 3-hour WFCI recording, the CNN-BiLSTM achieved a kappa of 0. 67, comparable to a kappa of 0. 65 corresponding to the human EEG/EMG-based scoring.

EEG

The NPU-ASLP-LiAuto System Description for Visual Speech Recognition in CNVSRC 2023

2 code implementations7 Jan 2024 He Wang, Pengcheng Guo, Wei Chen, Pan Zhou, Lei Xie

This paper delineates the visual speech recognition (VSR) system introduced by the NPU-ASLP-LiAuto (Team 237) in the first Chinese Continuous Visual Speech Recognition Challenge (CNVSRC) 2023, engaging in the fixed and open tracks of Single-Speaker VSR Task, and the open track of Multi-Speaker VSR Task.

speech-recognition Visual Speech Recognition

ICMC-ASR: The ICASSP 2024 In-Car Multi-Channel Automatic Speech Recognition Challenge

no code implementations7 Jan 2024 He Wang, Pengcheng Guo, Yue Li, Ao Zhang, Jiayao Sun, Lei Xie, Wei Chen, Pan Zhou, Hui Bu, Xin Xu, BinBin Zhang, Zhuo Chen, Jian Wu, Longbiao Wang, Eng Siong Chng, Sun Li

To promote speech processing and recognition research in driving scenarios, we build on the success of the Intelligent Cockpit Speech Recognition Challenge (ICSRC) held at ISCSLP 2022 and launch the ICASSP 2024 In-Car Multi-Channel Automatic Speech Recognition (ICMC-ASR) Challenge.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Large Language Models for Generative Information Extraction: A Survey

1 code implementation29 Dec 2023 Derong Xu, Wei Chen, Wenjun Peng, Chao Zhang, Tong Xu, Xiangyu Zhao, Xian Wu, Yefeng Zheng, Enhong Chen

Information extraction (IE) aims to extract structural knowledge (such as entities, relations, and events) from plain natural language texts.

MolSets: Molecular Graph Deep Sets Learning for Mixture Property Modeling

1 code implementation27 Dec 2023 Hengrui Zhang, Jie Chen, James M. Rondinelli, Wei Chen

This complexity is particularly evident in molecular mixtures, a frequently explored space for materials such as battery electrolytes.

mixture property prediction molecular representation

Identification of Causal Structure with Latent Variables Based on Higher Order Cumulants

no code implementations19 Dec 2023 Wei Chen, Zhiyi Huang, Ruichu Cai, Zhifeng Hao, Kun Zhang

Despite the emergence of numerous methods aimed at addressing this challenge, they are not fully identified to the structure that two observed variables are influenced by one latent variable and there might be a directed edge in between.

Causal Discovery

Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-Off

no code implementations16 Dec 2023 Yu-An Liu, Ruqing Zhang, Mingkun Zhang, Wei Chen, Maarten de Rijke, Jiafeng Guo, Xueqi Cheng

We decompose the robust ranking error into two components, i. e., a natural ranking error for effectiveness evaluation and a boundary ranking error for assessing adversarial robustness.

Adversarial Robustness Information Retrieval

K-ESConv: Knowledge Injection for Emotional Support Dialogue Systems via Prompt Learning

no code implementations16 Dec 2023 Wei Chen, Gang Zhao, Xiaojin Zhang, Xiang Bai, Xuanjing Huang, Zhongyu Wei

Automatic psychological counseling requires mass of professional knowledge that can be found in online counseling forums.

Response Generation

Enlighten-Your-Voice: When Multimodal Meets Zero-shot Low-light Image Enhancement

1 code implementation15 Dec 2023 Xiaofeng Zhang, Zishan Xu, Hao Tang, Chaochen Gu, Wei Chen, Shanying Zhu, Xinping Guan

Low-light image enhancement is a crucial visual task, and many unsupervised methods tend to overlook the degradation of visible information in low-light scenes, which adversely affects the fusion of complementary information and hinders the generation of satisfactory results.

Low-Light Image Enhancement

Local-Global History-aware Contrastive Learning for Temporal Knowledge Graph Reasoning

no code implementations4 Dec 2023 Wei Chen, Huaiyu Wan, Yuting Wu, Shuyuan Zhao, Jiayaqi Cheng, Yuxin Li, Youfang Lin

Temporal knowledge graphs (TKGs) have been identified as a promising approach to represent the dynamics of facts along the timeline.

Contrastive Learning Knowledge Graphs

A Cyclic Small Phase Theorem

no code implementations1 Dec 2023 Chao Chen, Wei Chen, Di Zhao, Jianqi Chen, Li Qiu

This paper introduces a brand-new phase definition called the segmental phase for multi-input multi-output linear time-invariant systems.

Phase Preservation of N-Port Networks under General Connections

no code implementations28 Nov 2023 Jianqi Chen, Wei Chen, Chao Chen, Li Qiu

In addition, the inverse operations of the considered connections, that is, network subtractions with correspondences are examined.

Statistical Parameterized Physics-Based Machine Learning Digital Twin Models for Laser Powder Bed Fusion Process

no code implementations14 Nov 2023 Yangfan Li, Satyajit Mojumder, Ye Lu, Abdullah Al Amin, Jiachen Guo, Xiaoyu Xie, Wei Chen, Gregory J. Wagner, Jian Cao, Wing Kam Liu

In the context of laser powder bed fusion (LPBF) additive manufacturing, a digital twin of the manufacturing process can offer predictions for the produced parts, diagnostics for manufacturing defects, as well as control capabilities.

CAME: Competitively Learning a Mixture-of-Experts Model for First-stage Retrieval

no code implementations6 Nov 2023 Yinqiong Cai, Yixing Fan, Keping Bi, Jiafeng Guo, Wei Chen, Ruqing Zhang, Xueqi Cheng

The first-stage retrieval aims to retrieve a subset of candidate documents from a huge collection both effectively and efficiently.

Retrieval

Closing the Gap Between the Upper Bound and the Lower Bound of Adam's Iteration Complexity

no code implementations27 Oct 2023 Bohan Wang, Jingwen Fu, Huishuai Zhang, Nanning Zheng, Wei Chen

Recently, Arjevani et al. [1] established a lower bound of iteration complexity for the first-order optimization under an $L$-smooth condition and a bounded noise variance assumption.

LEMMA valid

Mixed-Variable Global Sensitivity Analysis For Knowledge Discovery And Efficient Combinatorial Materials Design

no code implementations23 Oct 2023 Yigitcan Comlek, LiWei Wang, Wei Chen

So far, global sensitivity studies have often been limited to design spaces with only quantitative (numerical) design variables.

Navigate

When Urban Region Profiling Meets Large Language Models

no code implementations22 Oct 2023 Yibo Yan, Haomin Wen, Siru Zhong, Wei Chen, Haodong Chen, Qingsong Wen, Roger Zimmermann, Yuxuan Liang

To answer the questions, we leverage the power of Large Language Models (LLMs) and introduce the first-ever LLM-enhanced framework that integrates the knowledge of textual modality into urban imagery profiling, named LLM-enhanced Urban Region Profiling with Contrastive Language-Image Pretraining (UrbanCLIP).

Language Modelling Representation Learning

HEProto: A Hierarchical Enhancing ProtoNet based on Multi-Task Learning for Few-shot Named Entity Recognition

1 code implementation CIKM 2023 Wei Chen, Lili Zhao, Pengfei Luo, Tong Xu, Yi Zheng, Enhong Chen

Great efforts have been made on this task with competitive performance, however, they usually treat the two subtasks, namely span detection and type classification, as mutually independent, and the integrity and correlation between subtasks have been largely ignored.

Contrastive Learning Few-shot NER +4

Towards Enhancing Relational Rules for Knowledge Graph Link Prediction

1 code implementation20 Oct 2023 Shuhan Wu, Huaiyu Wan, Wei Chen, Yuting Wu, Junfeng Shen, Youfang Lin

To address these issues, we propose a novel knowledge graph reasoning approach, the Relational rUle eNhanced Graph Neural Network (RUN-GNN).

Inductive Link Prediction Relation

Over-the-Air Federated Learning and Optimization

no code implementations16 Oct 2023 Jingyang Zhu, Yuanming Shi, Yong Zhou, Chunxiao Jiang, Wei Chen, Khaled B. Letaief

We first provide a comprehensive study on the convergence of AirComp-based FedAvg (AirFedAvg) algorithms under both strongly convex and non-convex settings with constant and diminishing learning rates in the presence of data heterogeneity.

Federated Learning

Rate Compatible LDPC Neural Decoding Network: A Multi-Task Learning Approach

no code implementations10 Oct 2023 Yukun Cheng, Wei Chen, Lun Li, Bo Ai

Deep learning based decoding networks have shown significant improvement in decoding LDPC codes, but the neural decoders are limited by rate-matching operations such as puncturing or extending, thus needing to train multiple decoders with different code rates for a variety of channel conditions.

Multi-Task Learning

A Latent Variable Approach for Non-Hierarchical Multi-Fidelity Adaptive Sampling

no code implementations5 Oct 2023 Yi-Ping Chen, LiWei Wang, Yigitcan Comlek, Wei Chen

However, most existing MF methods rely on the hierarchical assumption of fidelity levels or fail to capture the intercorrelation between multiple fidelity levels and utilize it to quantify the value of the future samples and navigate the adaptive sampling.

Bayesian Optimization Navigate

Gated Cross-Attention Network for Depth Completion

no code implementations28 Sep 2023 Xiaogang Jia, Songlei Jian, Yusong Tan, Yonggang Che, Wei Chen, Zhengfa Liang

With a simple yet efficient gating mechanism, our proposed method achieves fast and accurate depth completion without the need for additional branches or post-processing steps.

Autonomous Driving Depth Completion +1

A Comprehensive Study of PAPR Reduction Techniques for Deep Joint Source Channel Coding in OFDM Systems

no code implementations21 Sep 2023 Maolin Liu, Wei Chen, Jialong Xu, Bo Ai

Recently, deep joint source channel coding (DJSCC) techniques have been extensively studied and have shown significant performance with limited bandwidth and low signal to noise ratio.

DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services

2 code implementations20 Sep 2023 Shengbin Yue, Wei Chen, Siyuan Wang, Bingxuan Li, Chenchen Shen, Shujun Liu, Yuxuan Zhou, Yao Xiao, Song Yun, Xuanjing Huang, Zhongyu Wei

We propose DISC-LawLLM, an intelligent legal system utilizing large language models (LLMs) to provide a wide range of legal services.

Legal Reasoning Retrieval

Signal Processing and Learning for Next Generation Multiple Access in 6G

no code implementations1 Sep 2023 Wei Chen, Yuanwei Liu, Hamid Jafarkhani, Yonina C. Eldar, Peiying Zhu, Khaled B Letaief

Wireless communication systems to date primarily rely on the orthogonality of resources to facilitate the design and implementation, from user access to data transmission.

Continual Learning for Generative Retrieval over Dynamic Corpora

no code implementations29 Aug 2023 Jiangui Chen, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Wei Chen, Yixing Fan, Xueqi Cheng

We put forward a novel Continual-LEarner for generatiVE Retrieval (CLEVER) model and make two major contributions to continual learning for GR: (i) To encode new documents into docids with low computational cost, we present Incremental Product Quantization, which updates a partial quantization codebook according to two adaptive thresholds; and (ii) To memorize new documents for querying without forgetting previous knowledge, we propose a memory-augmented learning mechanism, to form meaningful connections between old and new documents.

Continual Learning Quantization +1

DISC-MedLLM: Bridging General Large Language Models and Real-World Medical Consultation

1 code implementation28 Aug 2023 Zhijie Bao, Wei Chen, Shengze Xiao, Kuang Ren, Jiaao Wu, Cheng Zhong, Jiajie Peng, Xuanjing Huang, Zhongyu Wei

We propose DISC-MedLLM, a comprehensive solution that leverages Large Language Models (LLMs) to provide accurate and truthful medical response in end-to-end conversational healthcare services.

Knowledge Graphs

Inducing Causal Structure for Abstractive Text Summarization

1 code implementation24 Aug 2023 Lu Chen, Ruqing Zhang, Wei Huang, Wei Chen, Jiafeng Guo, Xueqi Cheng

The key idea is to reformulate the Variational Auto-encoder (VAE) to fit the joint distribution of the document and summary variables from the training corpus.

Abstractive Text Summarization

L^2R: Lifelong Learning for First-stage Retrieval with Backward-Compatible Representations

1 code implementation22 Aug 2023 Yinqiong Cai, Keping Bi, Yixing Fan, Jiafeng Guo, Wei Chen, Xueqi Cheng

First-stage retrieval is a critical task that aims to retrieve relevant document candidates from a large-scale collection.

Retrieval

Soft Decomposed Policy-Critic: Bridging the Gap for Effective Continuous Control with Discrete RL

no code implementations20 Aug 2023 Yechen Zhang, Jian Sun, Gang Wang, Zhuo Li, Wei Chen

Discrete reinforcement learning (RL) algorithms have demonstrated exceptional performance in solving sequential decision tasks with discrete action spaces, such as Atari games.

Atari Games Continuous Control +1

Black-box Adversarial Attacks against Dense Retrieval Models: A Multi-view Contrastive Learning Method

no code implementations19 Aug 2023 Yu-An Liu, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Wei Chen, Yixing Fan, Xueqi Cheng

The AREA task is meant to trick DR models into retrieving a target document that is outside the initial set of candidate documents retrieved by the DR model in response to a query.

Adversarial Attack Attribute +2

Federated Reinforcement Learning for Electric Vehicles Charging Control on Distribution Networks

no code implementations17 Aug 2023 Junkai Qian, Yuning Jiang, Xin Liu, Qing Wang, Ting Wang, Yuanming Shi, Wei Chen

To effectively learn the optimal EV charging control strategy, a federated deep reinforcement learning algorithm named FedSAC is further proposed.

reinforcement-learning

SciRE-Solver: Accelerating Diffusion Models Sampling by Score-integrand Solver with Recursive Difference

1 code implementation15 Aug 2023 Shigui Li, Wei Chen, Delu Zeng

Based on the RD method and the truncated Taylor expansion of score-integrand, we propose SciRE-Solver with the convergence order guarantee for accelerating sampling of DMs.

Beyond Semantics: Learning a Behavior Augmented Relevance Model with Self-supervised Learning

1 code implementation10 Aug 2023 Zeyuan Chen, Wei Chen, Jia Xu, Zhongyi Liu, Wei zhang

Drawing inspiration from this, we devise a novel Behavior Augmented Relevance Learning model for Alipay Search (BARL-ASe) that leverages neighbor queries of target item and neighbor items of target query to complement target query-item semantic matching.

Self-Supervised Learning Semantic Similarity +1

Deep Plug-and-Play Prior for Multitask Channel Reconstruction in Massive MIMO Systems

1 code implementation9 Aug 2023 Weixiao Wan, Wei Chen, Shiyue Wang, Geoffrey Ye Li, Bo Ai

The proposed method corresponding to these three channel reconstruction tasks employs a common DL model, which greatly reduces the overhead of model training and storage.

Multi-Task Learning

Causal-learn: Causal Discovery in Python

1 code implementation31 Jul 2023 Yujia Zheng, Biwei Huang, Wei Chen, Joseph Ramsey, Mingming Gong, Ruichu Cai, Shohei Shimizu, Peter Spirtes, Kun Zhang

Causal discovery aims at revealing causal relations from observational data, which is a fundamental task in science and engineering.

Causal Discovery

Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-trained Vision-Language Models

no code implementations ICCV 2023 Kecheng Zheng, Wei Wu, Ruili Feng, Kai Zhu, Jiawei Liu, Deli Zhao, Zheng-Jun Zha, Wei Chen, Yujun Shen

To bring the useful knowledge back into light, we first identify a set of parameters that are important to a given downstream task, then attach a binary mask to each parameter, and finally optimize these masks on the downstream data with the parameters frozen.

PromptMagician: Interactive Prompt Engineering for Text-to-Image Creation

1 code implementation18 Jul 2023 Yingchaojie Feng, Xingbo Wang, Kam Kwai Wong, Sijia Wang, Yuhong Lu, Minfeng Zhu, Baicheng Wang, Wei Chen

Generative text-to-image models have gained great popularity among the public for their powerful capability to generate high-quality images based on natural language prompts.

Prompt Engineering

Dynamic Prediction using Time-Dependent Cox Survival Neural Network

no code implementations12 Jul 2023 Lang Zeng, Jipeng Zhang, Wei Chen, Ying Ding

Motivated by establishing a dynamic prediction model for the progressive eye disease, age-related macular degeneration (AMD), we proposed a time-dependent Cox model-based survival neural network (tdCoxSNN) to predict its progression on a continuous time scale using longitudinal fundus images.

Data-Driven Design for Metamaterials and Multiscale Systems: A Review

no code implementations1 Jul 2023 Doksoo Lee, Wei Wayne Chen, LiWei Wang, Yu-Chin Chan, Wei Chen

Metamaterials are artificial materials designed to exhibit effective material parameters that go beyond those found in nature.

TNPAR: Topological Neural Poisson Auto-Regressive Model for Learning Granger Causal Structure from Event Sequences

no code implementations25 Jun 2023 Ruichu Cai, Yuequn Liu, Wei Chen, Jie Qiao, Yuguang Yan, Zijian Li, Keli Zhang, Zhifeng Hao

This observation prompts us to tackle two ensuing challenges: 1) how to model the event sequences while incorporating both the prior topological network and the latent Granger causal structure, and 2) how to learn the Granger causal structure.

Causal Discovery

On the Robustness of Generative Retrieval Models: An Out-of-Distribution Perspective

no code implementations22 Jun 2023 Yu-An Liu, Ruqing Zhang, Jiafeng Guo, Wei Chen, Xueqi Cheng

Recently, we have witnessed generative retrieval increasingly gaining attention in the information retrieval (IR) field, which retrieves documents by directly generating their identifiers.

Information Retrieval Retrieval

Taming the Exponential Action Set: Sublinear Regret and Fast Convergence to Nash Equilibrium in Online Congestion Games

no code implementations19 Jun 2023 Jing Dong, Jingyu Wu, Siwei Wang, Baoxiang Wang, Wei Chen

The congestion game is a powerful model that encompasses a range of engineering systems such as traffic networks and resource allocation.

Do as I can, not as I get

no code implementations17 Jun 2023 Shangfei Zheng, Hongzhi Yin, Tong Chen, Quoc Viet Hung Nguyen, Wei Chen, Lei Zhao

This paper proposes a model called TMR to mine valuable information from simulated data environments.

Knowledge Graphs Multi-modal Knowledge Graph +1

Power-law Dynamic arising from machine learning

no code implementations16 Jun 2023 Wei Chen, Weitao Du, Zhi-Ming Ma, Qi Meng

We study a kind of new SDE that was arisen from the research on optimization in machine learning, we call it power-law dynamic because its stationary distribution cannot have sub-Gaussian tail and obeys power-law.

ScrollTimes: Tracing the Provenance of Paintings as a Window into History

no code implementations15 Jun 2023 Wei zhang, Wong Kam-Kwai, Yitian Chen, Ailing Jia, Luwei Wang, Jian-Wei Zhang, Lechao Cheng, Huamin Qu, Wei Chen

The study of cultural artifact provenance, tracing ownership and preservation, holds significant importance in archaeology and art history.

When and Why Momentum Accelerates SGD:An Empirical Study

no code implementations15 Jun 2023 Jingwen Fu, Bohan Wang, Huishuai Zhang, Zhizheng Zhang, Wei Chen, Nanning Zheng

In the comparison of SGDM and SGD with the same effective learning rate and the same batch size, we observe a consistent pattern: when $\eta_{ef}$ is small, SGDM and SGD experience almost the same empirical training losses; when $\eta_{ef}$ surpasses a certain threshold, SGDM begins to perform better than SGD.

NFTVis: Visual Analysis of NFT Performance

no code implementations5 Jun 2023 Fan Yan, Xumeng Wang, Ketian Mao, Wei zhang, Wei Chen

A non-fungible token (NFT) is a data unit stored on the blockchain.

Time Series

USD: Unknown Sensitive Detector Empowered by Decoupled Objectness and Segment Anything Model

no code implementations4 Jun 2023 Yulin He, Wei Chen, Yusong Tan, Siqi Wang

Open World Object Detection (OWOD) is a novel and challenging computer vision task that enables object detection with the ability to detect unknown objects.

Object object-detection +1

Causal Discovery with Latent Confounders Based on Higher-Order Cumulants

no code implementations31 May 2023 Ruichu Cai, Zhiyi Huang, Wei Chen, Zhifeng Hao, Kun Zhang

In light of the power of the closed-form solution to OICA corresponding to the One-Latent-Component structure, we formulate a way to estimate the mixing matrix using the higher-order cumulants, and further propose the testable One-Latent-Component condition to identify the latent variables and determine causal orders.

Causal Discovery

Convergence of AdaGrad for Non-convex Objectives: Simple Proofs and Relaxed Assumptions

no code implementations29 May 2023 Bohan Wang, Huishuai Zhang, Zhi-Ming Ma, Wei Chen

We provide a simple convergence proof for AdaGrad optimizing non-convex objectives under only affine noise variance and bounded smoothness assumptions.

KNSE: A Knowledge-aware Natural Language Inference Framework for Dialogue Symptom Status Recognition

no code implementations26 May 2023 Wei Chen, Shiqi Wei, Zhongyu Wei, Xuanjing Huang

Symptom diagnosis in medical conversations aims to correctly extract both symptom entities and their status from the doctor-patient dialogue.

Natural Language Inference

Combinatorial Bandits for Maximum Value Reward Function under Max Value-Index Feedback

1 code implementation25 May 2023 Yiliu Wang, Wei Chen, Milan Vojnović

We propose an algorithm and provide a regret bound for problem instances with stochastic arm outcomes according to arbitrary distributions with finite supports.

Deep-Learning-Aided Alternating Least Squares for Tensor CP Decomposition and Its Application to Massive MIMO Channel Estimation

no code implementations23 May 2023 Xiao Gong, Wei Chen, Bo Ai, Geert Leus

To achieve accurate and low-latency channel estimation, good and fast CP decomposition algorithms are desired.

Bandit Multi-linear DR-Submodular Maximization and Its Applications on Adversarial Submodular Bandits

no code implementations21 May 2023 Zongqi Wan, Jialin Zhang, Wei Chen, Xiaoming Sun, Zhijie Zhang

Then we reduce submodular bandit with partition matroid constraint and bandit sequential monotone maximization to the online bandit learning of the monotone multi-linear DR-submodular functions, attaining $O(T^{2/3}\log T)$ of $(1-1/e)$-regret in both problems, which improve the existing results.

Constructing a personalized AI assistant for shear wall layout using Stable Diffusion

no code implementations18 May 2023 Lufeng Wang, Jiepeng Liu, Guozhong Cheng, En Liu, Wei Chen

Shear wall structures are widely used in high-rise residential buildings, and the layout of shear walls requires many years of design experience and iterative trial and error.

Deep Learning for Asynchronous Massive Access with Data Frame Length Diversity

no code implementations12 May 2023 Yanna Bai, Wei Chen, Bo Ai, Petar Popovski

Grant-free non-orthogonal multiple access has been regarded as a viable approach to accommodate access for a massive number of machine-type devices with small data packets.

Action Detection Activity Detection

Topic-oriented Adversarial Attacks against Black-box Neural Ranking Models

1 code implementation28 Apr 2023 Yu-An Liu, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Wei Chen, Yixing Fan, Xueqi Cheng

In this paper, we focus on a more general type of perturbation and introduce the topic-oriented adversarial ranking attack task against NRMs, which aims to find an imperceptible perturbation that can promote a target document in ranking for a group of queries with the same topic.

Information Retrieval Retrieval

CoSDA: Continual Source-Free Domain Adaptation

1 code implementation13 Apr 2023 Haozhe Feng, Zhaorui Yang, Hesun Chen, Tianyu Pang, Chao Du, Minfeng Zhu, Wei Chen, Shuicheng Yan

Recently, SFDA has gained popularity due to the need to protect the data privacy of the source domain, but it suffers from catastrophic forgetting on the source domain due to the lack of data.

Source-Free Domain Adaptation

Weight Try-Once-Discard Protocol-Based L_2 L_infinity State Estimation for Markovian Jumping Neural Networks with Partially Known Transition Probabilities

no code implementations10 Apr 2023 Cong Zou, Wei Chen

It was the L_2 L_infinity performance index that for the first time is initiated into the discussion on state estimation of delayed MJNNs with with partially known transition probabilities, which provides a more general promotion for the estimation error. The WTOD protocol is adopted to dispatch the sensor nodes so as to effectively alleviate the updating frequency of output signals.

DREAM: Adaptive Reinforcement Learning based on Attention Mechanism for Temporal Knowledge Graph Reasoning

no code implementations8 Apr 2023 Shangfei Zheng, Hongzhi Yin, Tong Chen, Quoc Viet Hung Nguyen, Wei Chen, Lei Zhao

Although existing TKG reasoning methods have the ability to predict missing future events, they fail to generate explicit reasoning paths and lack explainability.

Knowledge Graphs Missing Elements +3

4D Agnostic Real-Time Facial Animation Pipeline for Desktop Scenarios

no code implementations6 Apr 2023 Wei Chen, Hongwei Xu, Jelo Wang

The pipeline differs from professional head-mounted facial capture solutions in that it only requires the use of a consumer-grade 3D camera on the desk to achieve high-precision real-time facial capture.

Blockwise Compression of Transformer-based Models without Retraining

no code implementations4 Apr 2023 Gaochen Dong, Wei Chen

This method mitigates data distribution deviation caused by quantization, eliminating the requirement for retraining.

Quantization

VISHIEN-MAAT: Scrollytelling visualization design for explaining Siamese Neural Network concept to non-technical users

no code implementations4 Apr 2023 Noptanit Chotisarn, Sarun Gulyanon, Tianye Zhang, Wei Chen

Hence, this work proposes a novel visualization design for creating a scrollytelling that can effectively explain an AI concept to non-technical users.

Contextual Combinatorial Bandits with Probabilistically Triggered Arms

no code implementations30 Mar 2023 Xutong Liu, Jinhang Zuo, Siwei Wang, John C. S. Lui, Mohammad Hajiesmaili, Adam Wierman, Wei Chen

We study contextual combinatorial bandits with probabilistically triggered arms (C$^2$MAB-T) under a variety of smoothness conditions that capture a wide range of applications, such as contextual cascading bandits and contextual influence maximization bandits.

XVoxel-Based Parametric Design Optimization of Feature Models

no code implementations17 Mar 2023 Ming Li, Chengfeng Lin, Wei Chen, Yusheng Liu, Shuming Gao, Qiang Zou

As such, it can establish a direct mapping between design models and analysis models, which in turn enables automatic updates on simulation results for design modifications, and vice versa -- effectively a closed loop between CAD and CAE.

Computational Efficiency

Block-wise Bit-Compression of Transformer-based Models

no code implementations16 Mar 2023 Gaochen Dong, Wei Chen

With the popularity of the recent Transformer-based models represented by BERT, GPT-3 and ChatGPT, there has been state-of-the-art performance in a range of natural language processing tasks.

CrossFormer++: A Versatile Vision Transformer Hinging on Cross-scale Attention

1 code implementation13 Mar 2023 Wenxiao Wang, Wei Chen, Qibo Qiu, Long Chen, Boxi Wu, Binbin Lin, Xiaofei He, Wei Liu

On the one hand, CEL blends each token with multiple patches of different scales, providing the self-attention module itself with cross-scale features.

Image Classification Instance Segmentation +3

Pseudo-label Correction and Learning For Semi-Supervised Object Detection

no code implementations6 Mar 2023 Yulin He, Wei Chen, Ke Liang, Yusong Tan, Zhengfa Liang, Yulan Guo

Our proposed method, Pseudo-label Correction and Learning (PCL), is extensively evaluated on the MS COCO and PASCAL VOC benchmarks.

object-detection Object Detection +2

Deep Learning for Video-Text Retrieval: a Review

no code implementations24 Feb 2023 Cunjuan Zhu, Qi Jia, Wei Chen, Yanming Guo, Yu Liu

Video-Text Retrieval (VTR) aims to search for the most relevant video related to the semantics in a given sentence, and vice versa.

Retrieval Sentence +2

Rapid Design of Top-Performing Metal-Organic Frameworks with Qualitative Representations of Building Blocks

1 code implementation17 Feb 2023 Yigitcan Comlek, Thang Duc Pham, Randall Snurr, Wei Chen

Our approach provides three main advantages: (i) no specific physical descriptors are required and only building blocks that construct the MOFs are used in global optimization through qualitative representations, (ii) the method is application and property independent, and (iii) the latent variable approach provides an interpretable model of qualitative building blocks with physical justification.

Bayesian Optimization

Lero: A Learning-to-Rank Query Optimizer

1 code implementation14 Feb 2023 Rong Zhu, Wei Chen, Bolin Ding, Xingguang Chen, Andreas Pfadler, Ziniu Wu, Jingren Zhou

In this paper, we introduce a learning-to-rank query optimizer, called Lero, which builds on top of a native query optimizer and continuously learns to improve the optimization performance.

Binary Classification Learning-To-Rank

Trajectory-User Linking via Hierarchical Spatio-Temporal Attention Networks

1 code implementation11 Feb 2023 Wei Chen, Chao Huang, Yanwei Yu, Yongguo Jiang, Junyu Dong

Trajectory-User Linking (TUL) is crucial for human mobility modeling by linking diferent trajectories to users with the exploration of complex mobility patterns.

Combinatorial Causal Bandits without Graph Skeleton

1 code implementation31 Jan 2023 Shi Feng, Nuoya Xiong, Wei Chen

This paper studies the CCB problem without the graph structure on binary general causal models and BGLMs.

Does Federated Learning Really Need Backpropagation?

1 code implementation28 Jan 2023 Haozhe Feng, Tianyu Pang, Chao Du, Wei Chen, Shuicheng Yan, Min Lin

BAFFLE is 1) memory-efficient and easily fits uploading bandwidth; 2) compatible with inference-only hardware optimization and model quantization or pruning; and 3) well-suited to trusted execution environments, because the clients in BAFFLE only execute forward propagation and return a set of scalars to the server.

Federated Learning Quantization

XNLI: Explaining and Diagnosing NLI-based Visual Data Analysis

no code implementations25 Jan 2023 Yingchaojie Feng, Xingbo Wang, Bo Pan, Kam Kwai Wong, Yi Ren, Shi Liu, Zihan Yan, Yuxin Ma, Huamin Qu, Wei Chen

Our research explores how to provide explanations for NLIs to help users locate the problems and further revise the queries.

Data Visualization

Elevation Estimation-Driven Building 3D Reconstruction from Single-View Remote Sensing Imagery

no code implementations11 Jan 2023 Yongqiang Mao, Kaiqiang Chen, Liangjin Zhao, Wei Chen, Deke Tang, Wenjie Liu, Zhirui Wang, Wenhui Diao, Xian Sun, Kun fu

Our Building3D is rooted in the SFFDE network for building elevation prediction, synchronized with a building extraction network for building masks, and then sequentially performs point cloud reconstruction, surface reconstruction (or CityGML model reconstruction).

Point cloud reconstruction Surface Reconstruction

Decoding Structure-Spectrum Relationships with Physically Organized Latent Spaces

no code implementations11 Jan 2023 Zhu Liang, Matthew R. Carbone, Wei Chen, Fanchen Meng, Eli Stavitski, Deyu Lu, Mark S. Hybertsen, Xiaohui Qu

A new semi-supervised machine learning method for the discovery of structure-spectrum relationships is developed and demonstrated using the specific example of interpreting X-ray absorption near-edge structure (XANES) spectra.

MAUD: An Expert-Annotated Legal NLP Dataset for Merger Agreement Understanding

2 code implementations2 Jan 2023 Steven H. Wang, Antoine Scardigli, Leonard Tang, Wei Chen, Dimitry Levkin, Anya Chen, Spencer Ball, Thomas Woodside, Oliver Zhang, Dan Hendrycks

Reading comprehension of legal text can be a particularly challenging task due to the length and complexity of legal clauses and a shortage of expert-annotated datasets.

Reading Comprehension

Towards Efficient Visual Simplification of Computational Graphs in Deep Neural Networks

no code implementations21 Dec 2022 Rusheng Pan, Zhiyong Wang, Yating Wei, Han Gao, Gongchang Ou, Caleb Chen Cao, Jingli Xu, Tong Xu, Wei Chen

A computational graph in a deep neural network (DNN) denotes a specific data flow diagram (DFD) composed of many tensors and operators.

Category-Level 6D Object Pose Estimation with Flexible Vector-Based Rotation Representation

no code implementations9 Dec 2022 Wei Chen, Xi Jia, Zhongqun Zhang, Hyung Jin Chang, Linlin Shen, Jinming Duan, Ales Leonardis

The proposed rotation representation has two major advantages: 1) decoupled characteristic that makes the rotation estimation easier; 2) flexible length and rotated angle of the vectors allow us to find a more suitable vector representation for specific pose estimation task.

6D Pose Estimation using RGB Data Augmentation

Fourier-Net: Fast Image Registration with Band-limited Deformation

1 code implementation29 Nov 2022 Xi Jia, Joseph Bartlett, Wei Chen, Siyang Song, Tianyang Zhang, Xinxing Cheng, Wenqi Lu, Zhaowen Qiu, Jinming Duan

Specifically, instead of our Fourier-Net learning to output a full-resolution displacement field in the spatial domain, we learn its low-dimensional representation in a band-limited Fourier domain.

Image Registration

CSI-PPPNet: A One-Sided One-for-All Deep Learning Framework for Massive MIMO CSI Feedback

no code implementations29 Nov 2022 Wei Chen, Weixiao Wan, Shiyue Wang, Peng Sun, Geoffrey Ye Li, Bo Ai

The CSI is compressed via linear projections at the UE, and is recovered at the BS using deep learning (DL) with plug-and-play priors (PPP).

Denoising

A Knowledge-based Learning Framework for Self-supervised Pre-training Towards Enhanced Recognition of Biomedical Microscopy Images

1 code implementation27 Nov 2022 Wei Chen, Chen Li, Dan Chen, Xin Luo

Self-supervised pre-training has become the priory choice to establish reliable neural networks for automated recognition of massive biomedical microscopy images, which are routinely annotation-free, without semantics, and without guarantee of quality.

Contrastive Learning Image Restoration +2

EHSNet: End-to-End Holistic Learning Network for Large-Size Remote Sensing Image Semantic Segmentation

no code implementations21 Nov 2022 Wei Chen, Yansheng Li, Bo Dang, Yongjun Zhang

This paper presents EHSNet, a new end-to-end segmentation network designed for the holistic learning of large-size remote sensing image semantic segmentation (LRISS).

Semantic Segmentation

ET-AL: Entropy-Targeted Active Learning for Bias Mitigation in Materials Data

1 code implementation15 Nov 2022 Hengrui Zhang, Wei Wayne Chen, James M. Rondinelli, Wei Chen

To mitigate the bias, we develop an entropy-targeted active learning (ET-AL) framework, which guides the acquisition of new data to improve the diversity of underrepresented crystal systems.

Active Learning Materials Screening

Synchronization of Diverse Agents via Phase Analysis

no code implementations8 Nov 2022 Dan Wang, Wei Chen, Li Qiu

They can also model the controllers of the agents which may be different for each agent or uniform for all the agents.

Fully Bayesian inference for latent variable Gaussian process models

1 code implementation4 Nov 2022 Suraj Yerramilli, Akshay Iyer, Wei Chen, Daniel W. Apley

However, this plug-in approach will not account for uncertainty in estimation of the LVs, which can be significant especially with limited training data.

Bayesian Inference Gaussian Processes +1

Global-to-local Expression-aware Embeddings for Facial Action Unit Detection

no code implementations27 Oct 2022 Rudong An, Wei zhang, Hao Zeng, Wei Chen, Zhigang Deng, Yu Ding

Then, AU feature maps and their corresponding AU masks are multiplied to generate AU masked features focusing on local facial region.

Action Unit Detection Facial Action Unit Detection

Facial Action Units Detection Aided by Global-Local Expression Embedding

no code implementations25 Oct 2022 Zhipeng Hu, Wei zhang, Lincheng Li, Yu Ding, Wei Chen, Zhigang Deng, Xin Yu

We find that AUs and facial expressions are highly associated, and existing facial expression datasets often contain a large number of identities.

3D Face Reconstruction

Feature-Proxy Transformer for Few-Shot Segmentation

2 code implementations13 Oct 2022 Jian-Wei Zhang, Yifan Sun, Yi Yang, Wei Chen

With a rethink of recent advances, we find that the current FSS framework has deviated far from the supervised segmentation framework: Given the deep features, FSS methods typically use an intricate decoder to perform sophisticated pixel-wise matching, while the supervised segmentation methods use a simple linear classification head.

Few-Shot Semantic Segmentation Segmentation +1

Federated Reinforcement Learning for Real-Time Electric Vehicle Charging and Discharging Control

no code implementations4 Oct 2022 Zixuan Zhang, Yuning Jiang, Yuanming Shi, Ye Shi, Wei Chen

This paper develops an optimal EV charging/discharging control strategy for different EV users under dynamic environments to maximize EV users' benefits.

reinforcement-learning Reinforcement Learning (RL)

Certified Robustness to Word Substitution Ranking Attack for Neural Ranking Models

1 code implementation14 Sep 2022 Chen Wu, Ruqing Zhang, Jiafeng Guo, Wei Chen, Yixing Fan, Maarten de Rijke, Xueqi Cheng

A ranking model is said to be Certified Top-$K$ Robust on a ranked list when it is guaranteed to keep documents that are out of the top $K$ away from the top $K$ under any attack.

Information Retrieval Retrieval

Disconnected Emerging Knowledge Graph Oriented Inductive Link Prediction

1 code implementation3 Sep 2022 Yufeng Zhang, Weiqing Wang, Hongzhi Yin, Pengpeng Zhao, Wei Chen, Lei Zhao

A more challenging scenario is that emerging KGs consist of only unseen entities, called as disconnected emerging KGs (DEKGs).

Contrastive Learning Inductive Link Prediction +2

MMKGR: Multi-hop Multi-modal Knowledge Graph Reasoning

no code implementations3 Sep 2022 Shangfei Zheng, Weiqing Wang, Jianfeng Qu, Hongzhi Yin, Wei Chen, Lei Zhao

Multi-modal knowledge graphs (MKGs) include not only the relation triplets, but also related multi-modal auxiliary data (i. e., texts and images), which enhance the diversity of knowledge.

Knowledge Graphs Missing Elements +1

Batch-Size Independent Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms or Independent Arms

no code implementations31 Aug 2022 Xutong Liu, Jinhang Zuo, Siwei Wang, Carlee Joe-Wong, John C. S. Lui, Wei Chen

Under this new condition, we propose a BCUCB-T algorithm with variance-aware confidence intervals and conduct regret analysis which reduces the $O(K)$ factor to $O(\log K)$ or $O(\log^2 K)$ in the regret bound, significantly improving the regret bounds for the above applications.

A Hierarchical Interactive Network for Joint Span-based Aspect-Sentiment Analysis

1 code implementation COLING 2022 Wei Chen, Jinglong Du, Zhao Zhang, Fuzhen Zhuang, Zhongshi He

Recently, some span-based methods have achieved encouraging performances for joint aspect-sentiment analysis, which first extract aspects (aspect extraction) by detecting aspect boundaries and then classify the span-level sentiments (sentiment classification).

Aspect Extraction Sentiment Analysis +1

Provable Adaptivity in Adam

no code implementations21 Aug 2022 Bohan Wang, Yushun Zhang, Huishuai Zhang, Qi Meng, Zhi-Ming Ma, Tie-Yan Liu, Wei Chen

In particular, the existing analysis of Adam cannot clearly demonstrate the advantage of Adam over SGD.

Attribute

Global Consistent Point Cloud Registration Based on Lie-algebraic Cohomology

no code implementations15 Aug 2022 Yuxue Ren, Baowei Jiang, Wei Chen, Na lei, Xianfeng David Gu

We present a novel, effective method for global point cloud registration problems by geometric topology.

Point Cloud Registration

D2-TPred: Discontinuous Dependency for Trajectory Prediction under Traffic Lights

1 code implementation21 Jul 2022 Yuzhen Zhang, Wentong Wang, Weizhi Guo, Pei Lv, Mingliang Xu, Wei Chen, Dinesh Manocha

We present a trajectory prediction approach with respect to traffic lights, D2-TPred, which uses a spatial dynamic interaction graph (SDG) and a behavior dependency graph (BDG) to handle the problem of discontinuous dependency in the spatial-temporal space.

Trajectory Prediction

Uncertainty-Aware Mixed-Variable Machine Learning for Materials Design

no code implementations11 Jul 2022 Hengrui Zhang, Wei Wayne Chen, Akshay Iyer, Daniel W. Apley, Wei Chen

Data-driven design shows the promise of accelerating materials discovery but is challenging due to the prohibitive cost of searching the vast design space of chemistry, structure, and synthesis methods.

Bayesian Optimization BIG-bench Machine Learning +1

Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimization

no code implementations27 Jun 2022 Xiaodong Yang, Huishuai Zhang, Wei Chen, Tie-Yan Liu

By ensuring differential privacy in the learning algorithms, one can rigorously mitigate the risk of large models memorizing sensitive training data.

Combinatorial Pure Exploration of Causal Bandits

no code implementations16 Jun 2022 Nuoya Xiong, Wei Chen

The combinatorial pure exploration of causal bandits is the following online learning task: given a causal graph with unknown causal inference distributions, in each round we choose a subset of variables to intervene or do no intervention, and observe the random outcomes of all random variables, with the goal that using as few rounds as possible, we can output an intervention that gives the best (or almost best) expected outcome on the reward variable $Y$ with probability at least $1-\delta$, where $\delta$ is a given confidence level.

Causal Inference Multi-Armed Bandits

Combinatorial Causal Bandits

1 code implementation4 Jun 2022 Shi Feng, Wei Chen

For the special case of linear models with hidden variables, we apply causal inference techniques such as the do-calculus to convert the original model into a Markovian model, and then show that our BGLM-OFU algorithm and another algorithm based on the linear regression both solve such linear models with hidden variables.

Causal Inference

Tiered Reinforcement Learning: Pessimism in the Face of Uncertainty and Constant Regret

1 code implementation25 May 2022 Jiawei Huang, Li Zhao, Tao Qin, Wei Chen, Nan Jiang, Tie-Yan Liu

We propose a new learning framework that captures the tiered structure of many real-world user-interaction applications, where the users can be divided into two groups based on their different tolerance on exploration risks and should be treated separately.

reinforcement-learning Reinforcement Learning (RL)

Mutual Distillation Learning Network for Trajectory-User Linking

1 code implementation8 May 2022 Wei Chen, Shuzhe Li, Chao Huang, Yanwei Yu, Yongguo Jiang, Junyu Dong

In this paper, we propose a novel Mutual distillation learning network to solve the TUL problem for sparse check-in mobility data, named MainTUL.

DxFormer: A Decoupled Automatic Diagnostic System Based on Decoder-Encoder Transformer with Dense Symptom Representations

1 code implementation8 May 2022 Wei Chen, Cheng Zhong, Jiajie Peng, Zhongyu Wei

Diagnosis-oriented dialogue system queries the patient's health condition and makes predictions about possible diseases through continuous interaction with the patient.

Reinforcement Learning (RL) Text Generation

Time-Series Domain Adaptation via Sparse Associative Structure Alignment: Learning Invariance and Variance

no code implementations7 May 2022 Zijian Li, Ruichu Cai, Jiawei Chen, Yuguan Yan, Wei Chen, Keli Zhang, Junjian Ye

Based on this inspiration, we investigate the domain-invariant unweighted sparse associative structures and the domain-variant strengths of the structures.

Time Series Time Series Analysis +2

A Benchmark for Automatic Medical Consultation System: Frameworks, Tasks and Datasets

1 code implementation19 Apr 2022 Wei Chen, Zhiwei Li, Hongyi Fang, Qianyuan Yao, Cheng Zhong, Jianye Hao, Qi Zhang, Xuanjing Huang, Jiajie Peng, Zhongyu Wei

In recent years, interest has arisen in using machine learning to improve the efficiency of automatic medical consultation and enhance patient experience.

Dialogue Act Classification Dialogue Understanding +4

Neural Operator with Regularity Structure for Modeling Dynamics Driven by SPDEs

1 code implementation13 Apr 2022 Peiyan Hu, Qi Meng, Bingguang Chen, Shiqi Gong, Yue Wang, Wei Chen, Rongchan Zhu, Zhi-Ming Ma, Tie-Yan Liu

Stochastic partial differential equations (SPDEs) are significant tools for modeling dynamics in many areas including atmospheric sciences and physics.

Automated Sleep Staging via Parallel Frequency-Cut Attention

no code implementations7 Apr 2022 Zheng Chen, Ziwei Yang, Lingwei Zhu, Wei Chen, Toshiyo Tamura, Naoaki Ono, MD Altaf-Ul-Amin, Shigehiko Kanaya, Ming Huang

This paper proposes a novel framework for automatically capturing the time-frequency nature of electroencephalogram (EEG) signals of human sleep based on the authoritative sleep medicine guidance.

Decision Making EEG +3

TO-FLOW: Efficient Continuous Normalizing Flows with Temporal Optimization adjoint with Moving Speed

1 code implementation CVPR 2022 Shian Du, Yihong Luo, Wei Chen, Jian Xu, Delu Zeng

In this paper, a temporal optimization is proposed by optimizing the evolutionary time for forward propagation of the neural ODE training.

GAN-DUF: Hierarchical Deep Generative Models for Design Under Free-Form Geometric Uncertainty

1 code implementation21 Feb 2022 Wei Wayne Chen, Doksoo Lee, Oluwaseyi Balogun, Wei Chen

To address this issue, we propose a Generative Adversarial Network-based Design under Uncertainty Framework (GAN-DUF), which contains a deep generative model that simultaneously learns a compact representation of nominal (ideal) designs and the conditional distribution of fabricated designs given any nominal design.

Generative Adversarial Network Robust Design +1

t-METASET: Tailoring Property Bias of Large-Scale Metamaterial Datasets through Active Learning

no code implementations21 Feb 2022 Doksoo Lee, Yu-Chin Chan, Wei Wayne Chen, LiWei Wang, Anton van Beek, Wei Chen

Distinctly, we seek a solution to a commonplace yet frequently overlooked scenario at early stages of data-driven design of metamaterials: when a massive (~O(10^4 )) shape-only library has been prepared with no properties evaluated.

Active Learning

Branching Reinforcement Learning

no code implementations16 Feb 2022 Yihan Du, Wei Chen

In this paper, we propose a novel Branching Reinforcement Learning (Branching RL) model, and investigate both Regret Minimization (RM) and Reward-Free Exploration (RFE) metrics for this model.

LEMMA Recommendation Systems +2

When Small Gain Meets Small Phase

no code implementations16 Jan 2022 Di Zhao, Wei Chen, Li Qiu

In this paper, we investigate the feedback stability of multiple-input multiple-output linear time-invariant systems with combined gain and phase information.

LEMMA

REST: Debiased Social Recommendation via Reconstructing Exposure Strategies

1 code implementation13 Jan 2022 Ruichu Cai, Fengzhu Wu, Zijian Li, Jie Qiao, Wei Chen, Yuexing Hao, Hao Gu

By explicitly Reconstructing Exposure STrategies (REST in short), we formalize the recommendation problem as the counterfactual reasoning and propose the debiased social recommendation method.

counterfactual Counterfactual Reasoning +1

Baihe: SysML Framework for AI-driven Databases

no code implementations29 Dec 2021 Andreas Pfadler, Rong Zhu, Wei Chen, Botong Huang, Tianjing Zeng, Bolin Ding, Jingren Zhou

Based on the high level architecture, we then describe a concrete implementation of Baihe for PostgreSQL and present example use cases for learned query optimizers.

Deep Generative Models for Geometric Design Under Uncertainty

1 code implementation15 Dec 2021 Wei Wayne Chen, Doksoo Lee, Wei Chen

Deep generative models have demonstrated effectiveness in learning compact and expressive design representations that significantly improve geometric design optimization.

Generative Adversarial Network

Glue: Adaptively Merging Single Table Cardinality to Estimate Join Query Size

no code implementations7 Dec 2021 Rong Zhu, Tianjing Zeng, Andreas Pfadler, Wei Chen, Bolin Ding, Jingren Zhou

Cardinality estimation (CardEst), a central component of the query optimizer, plays a significant role in generating high-quality query plans in DBMS.

Recovering Latent Causal Factor for Generalization to Distributional Shifts

1 code implementation NeurIPS 2021 Xinwei Sun, Botong Wu, Xiangyu Zheng, Chang Liu, Wei Chen, Tao Qin, Tie-Yan Liu

To avoid such a spurious correlation, we propose \textbf{La}tent \textbf{C}ausal \textbf{I}nvariance \textbf{M}odels (LaCIM) that specifies the underlying causal structure of the data and the source of distributional shifts, guiding us to pursue only causal factor for prediction.

Remixing Functionally Graded Structures: Data-Driven Topology Optimization with Multiclass Shape Blending

1 code implementation1 Dec 2021 Yu-Chin Chan, Daicong Da, LiWei Wang, Wei Chen

We propose to inherit the advantages of both through a data-driven framework for multiclass functionally graded structures that mixes several families, i. e., classes, of microstructure topologies to create spatially-varying designs with guaranteed feasibility.

CCSL: A Causal Structure Learning Method from Multiple Unknown Environments

1 code implementation18 Nov 2021 Wei Chen, Yunjin Wu, Ruichu Cai, Yueguo Chen, Zhifeng Hao

This method simultaneously integrates the following two tasks: 1) clustering samples of the subjects with the same causal mechanism into different groups; 2) learning causal structures from the samples within the group.

Causal Discovery Clustering +1

The Hardness Analysis of Thompson Sampling for Combinatorial Semi-bandits with Greedy Oracle

no code implementations NeurIPS 2021 Fang Kong, Yueran Yang, Wei Chen, Shuai Li

These are the first theoretical results for TS to solve CMAB with a common approximation oracle and break the misconception that TS cannot work with approximation oracles.

Combinatorial Optimization Open-Ended Question Answering +1

Availability Attacks Create Shortcuts

1 code implementation1 Nov 2021 Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu

We are the first to unveil an important population property of the perturbations of these attacks: they are almost \textbf{linearly separable} when assigned with the target labels of the corresponding samples, which hence can work as \emph{shortcuts} for the learning objective.

Data Poisoning

Collaborative Pure Exploration in Kernel Bandit

no code implementations29 Oct 2021 Yihan Du, Wei Chen, Yuko Kuroki, Longbo Huang

In this paper, we formulate a Collaborative Pure Exploration in Kernel Bandit problem (CoPE-KB), which provides a novel model for multi-agent multi-task decision making under limited communication and general reward functions, and is applicable to many online learning tasks, e. g., recommendation systems and network scheduling.

Decision Making Recommendation Systems +1

Optimizing Information-theoretical Generalization Bounds via Anisotropic Noise in SGLD

no code implementations NeurIPS 2021 Bohan Wang, Huishuai Zhang, Jieyu Zhang, Qi Meng, Wei Chen, Tie-Yan Liu

We prove that with constraint to guarantee low empirical risk, the optimal noise covariance is the square root of the expected gradient covariance if both the prior and the posterior are jointly optimized.

Generalization Bounds

SE(3) Equivariant Graph Neural Networks with Complete Local Frames

1 code implementation26 Oct 2021 Weitao Du, He Zhang, Yuanqi Du, Qi Meng, Wei Chen, Bin Shao, Tie-Yan Liu

In this paper, we propose a framework to construct SE(3) equivariant graph neural networks that can approximate the geometric quantities efficiently.

Computational Efficiency

TESSERACT: Gradient Flip Score to Secure Federated Learning Against Model Poisoning Attacks

no code implementations19 Oct 2021 Atul Sharma, Wei Chen, Joshua Zhao, Qiang Qiu, Somali Chaterji, Saurabh Bagchi

The attack uses the intuition that simply by changing the sign of the gradient updates that the optimizer is computing, for a set of malicious clients, a model can be diverted from the optima to increase the test error rate.

Federated Learning Model Poisoning

Does Momentum Change the Implicit Regularization on Separable Data?

no code implementations8 Oct 2021 Bohan Wang, Qi Meng, Huishuai Zhang, Ruoyu Sun, Wei Chen, Zhi-Ming Ma, Tie-Yan Liu

The momentum acceleration technique is widely adopted in many optimization algorithms.