Search Results for author: Hui Chen

Found 112 papers, 43 papers with code

How Can Cross-lingual Knowledge Contribute Better to Fine-Grained Entity Typing?

no code implementations Findings (ACL) 2022 Hailong Jin, Tiansi Dong, Lei Hou, Juanzi Li, Hui Chen, Zelin Dai, Qu Yincen

Cross-lingual Entity Typing (CLET) aims at improving the quality of entity type prediction by transferring semantic knowledge learned from rich-resourced languages to low-resourced languages.

Entity Typing Transfer Learning +1

PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation

no code implementations14 Mar 2024 Yizhe Xiong, Hui Chen, Tianxiang Hao, Zijia Lin, Jungong Han, Yuesong Zhang, Guoxin Wang, Yongjun Bao, Guiguang Ding

Consequently, a simple combination of them cannot guarantee accomplishing both training efficiency and inference efficiency with minimal costs.

Model Compression

ELAA Near-Field Localization and Sensing with Partial Blockage Detection

no code implementations24 Feb 2024 Hui Chen, Pinjun Zheng, Yu Ge, Ahmed Elzanaty, Jiguang He, Tareq Y. Al-Naffouri, Henk Wymeersch

Considering the array size could be much larger than an obstacle, the effect of partial blockage (i. e., a portion of antennas are blocked) is investigated, and a blockage detection algorithm is proposed.

INSTRAUG: Automatic Instruction Augmentation for Multimodal Instruction Fine-tuning

1 code implementation22 Feb 2024 Wei Han, Hui Chen, Soujanya Poria

Fine-tuning large language models (LLMs) on multi-task instruction-following data has been proven to be a powerful learning paradigm for improving their zero-shot capabilities on new tasks.

Instruction Following

Bring Your Own Character: A Holistic Solution for Automatic Facial Animation Generation of Customized Characters

1 code implementation21 Feb 2024 Zechen Bai, Peng Chen, Xiaolan Peng, Lu Liu, Hui Chen, Mike Zheng Shou, Feng Tian

In our solution, a deep learning model was first trained to retarget the facial expression from input face images to virtual human faces by estimating the blendshape coefficients.


Weakly Augmented Variational Autoencoder in Time Series Anomaly Detection

no code implementations7 Jan 2024 Zhangkai Wu, Longbing Cao, Qi Zhang, Junxian Zhou, Hui Chen

Due to their unsupervised training and uncertainty estimation, deep Variational Autoencoders (VAEs) have become powerful tools for reconstruction-based Time Series Anomaly Detection (TSAD).

Anomaly Detection Self-Supervised Learning +2

One-Dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applications

no code implementations26 Dec 2023 Mengyao Lyu, Yuhong Yang, Haiwen Hong, Hui Chen, Xuan Jin, Yuan He, Hui Xue, Jungong Han, Guiguang Ding

The prevalent use of commercial and open-source diffusion models (DMs) for text-to-image generation prompts risk mitigation to prevent undesired behaviors.

Text-to-Image Generation

On Smart Morphing Wing Aircraft Robust Adaptive Beamforming

no code implementations22 Dec 2023 Yizhen Jia, Hui Chen, Wen-Qin Wang, Jie Cheng

To overcome this problem and ensure robust beamforming for FCA, deviations in array control parameters (ACPs) and array perturbations, the effect of mutual coupling in addition to looking-direction errors should be considered.

RepViT-SAM: Towards Real-Time Segmenting Anything

2 code implementations10 Dec 2023 Ao Wang, Hui Chen, Zijia Lin, Jungong Han, Guiguang Ding

Here, to achieve real-time segmenting anything on mobile devices, following MobileSAM, we replace the heavyweight image encoder in SAM with RepViT model, ending up with the RepViT-SAM model.

DiffusionTalker: Personalization and Acceleration for Speech-Driven 3D Face Diffuser

no code implementations28 Nov 2023 Peng Chen, Xiaobao Wei, Ming Lu, Yitong Zhu, Naiming Yao, Xingyu Xiao, Hui Chen

To address the above limitations, we propose DiffusionTalker, a diffusion-based method that utilizes contrastive learning to personalize 3D facial animation and knowledge distillation to accelerate 3D animation generation.

3D Face Animation Contrastive Learning +1

RIS Position and Orientation Estimation via Multi-Carrier Transmissions and Multiple Receivers

no code implementations15 Nov 2023 Reza Ghazalian, Hui Chen, George C. Alexandropoulos, Gonzalo Seco-Granados, Henk Wymeersch, Riku Jäntti

In this paper, we consider a static user equipped with an RIS and study the RIS localization problem (i. e., joint three-dimensional position and orientation estimation), when operating in a system comprising a single-antenna transmitter and multiple synchronized single-antenna receivers with known locations.


InstructCoder: Instruction Tuning Large Language Models for Code Editing

1 code implementation31 Oct 2023 Kaixin Li, Qisheng Hu, Xu Zhao, Hui Chen, Yuxi Xie, Tiedong Liu, Qizhe Xie, Junxian He

In this work, we explore the use of Large Language Models (LLMs) to edit code based on user instructions.

Missing-modality Enabled Multi-modal Fusion Architecture for Medical Data

no code implementations27 Sep 2023 Muyu Wang, Shiyu Fan, Yichen Li, Hui Chen

This study aimed to develop an efficient multi-modal fusion architecture for medical data that was robust to missing modalities and further improved the performance on disease diagnosis. X-ray chest radiographs for the image modality, radiology reports for the text modality, and structured value data for the tabular data modality were fused in this study.


Bayesian Personalized Federated Learning with Shared and Personalized Uncertainty Representations

no code implementations27 Sep 2023 Hui Chen, Hengyu Liu, Longbing Cao, Tiancheng Zhang

BPFL aims to quantify the uncertainty and heterogeneity within and across clients towards uncertainty representations by addressing the statistical heterogeneity of client data.

Personalized Federated Learning

Confidence-based Visual Dispersal for Few-shot Unsupervised Domain Adaptation

1 code implementation ICCV 2023 Yizhe Xiong, Hui Chen, Zijia Lin, Sicheng Zhao, Guiguang Ding

To address this issue, recent works consider the Few-shot Unsupervised Domain Adaptation (FUDA) where only a few source samples are labeled, and conduct knowledge transfer via self-supervised learning methods.

Self-Supervised Learning Transfer Learning +1

6G Positioning and Sensing Through the Lens of Sustainability, Inclusiveness, and Trustworthiness

no code implementations24 Sep 2023 Henk Wymeersch, Hui Chen, Hao Guo, Musa Furkan Keskin, Bahare M. Khorsandi, Mohammad H. Moghaddam, Alejandro Ramirez, Kim Schindhelm, Athanasios Stavridis, Tommy Svensson, Vijaya Yajnanarayana

6G promises a paradigm shift in which positioning and sensing are inherently integrated, enhancing not only the communication performance but also enabling location- and context-aware services.

RepViT: Revisiting Mobile CNN From ViT Perspective

7 code implementations18 Jul 2023 Ao Wang, Hui Chen, Zijia Lin, Jungong Han, Guiguang Ding

Recently, lightweight Vision Transformers (ViTs) demonstrate superior performance and lower latency, compared with lightweight Convolutional Neural Networks (CNNs), on resource-constrained mobile devices.

CodeInstruct: Empowering Language Models to Edit Code

1 code implementation Github 2023 Qisheng Hu*, Kaixin Li*, Xu Zhao, Yuxi Xie, Tiedong Liu, Hui Chen, Qizhe Xie, Junxian He

In this work, we explore the use of large language models (LLMs) to edit code based on user instructions, covering a broad range of implicit tasks such as comment insertion, code optimization, and code refactoring.

Domain-Expanded ASTE: Rethinking Generalization in Aspect Sentiment Triplet Extraction

no code implementations23 May 2023 Yew Ken Chia, Hui Chen, Wei Han, Guizhen Chen, Sharifah Mahani Aljunied, Soujanya Poria, Lidong Bing

Aspect Sentiment Triplet Extraction (ASTE) is a subtask of Aspect-Based Sentiment Analysis (ABSA) that considers each opinion term, their expressed sentiment, and the corresponding aspect targets.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2

Zero Access Points 3D Cooperative Positioning via RIS and Sidelink Communications

no code implementations15 May 2023 Mustafa Ammous, Hui Chen, Henk Wymeersch, Shahrokh Valaee

Reconfigurable intelligent surfaces (RISs) are expected to be a main component of future 6G networks, due to their capability to create a controllable wireless environment, and achieve extended coverage and improved localization accuracy.

Consolidator: Mergeable Adapter with Grouped Connections for Visual Adaptation

1 code implementation30 Apr 2023 Tianxiang Hao, Hui Chen, Yuchen Guo, Guiguang Ding

To further enhance the model's capacity to transfer knowledge under a constrained storage budget and keep inference efficient, we consolidate the parameters in two stages: 1. between adaptation and storage, and 2. between loading and inference.

Bayesian Federated Learning: A Survey

no code implementations26 Apr 2023 Longbing Cao, Hui Chen, Xuhui Fan, Joao Gama, Yew-Soon Ong, Vipin Kumar

This survey presents a critical overview of BFL, including its basic concepts, its relations to Bayesian learning in the context of FL, and a taxonomy of BFL from both Bayesian and federated perspectives.

Federated Learning Privacy Preserving

JrCUP: Joint RIS Calibration and User Positioning for 6G Wireless Systems

no code implementations2 Apr 2023 Pinjun Zheng, Hui Chen, Tarig Ballal, Mikko Valkama, Henk Wymeersch, Tareq Y. Al-Naffouri

In the second stage, a two-dimensional search algorithm is proposed to estimate the three-dimensional user and RIS positions, one-dimensional RIS orientation, and clock bias from the estimated channel parameters.

Box-Level Active Detection

1 code implementation CVPR 2023 Mengyao Lyu, Jundong Zhou, Hui Chen, YiJie Huang, Dongdong Yu, Yaqian Li, Yandong Guo, Yuchen Guo, Liuyu Xiang, Guiguang Ding

Active learning selects informative samples for annotation within budget, which has proven efficient recently on object detection.

Active Learning object-detection +1

Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete Labels

1 code implementation CVPR 2023 Zixuan Ding, Ao Wang, Hui Chen, Qiang Zhang, Pengzhang Liu, Yongjun Bao, Weipeng Yan, Jungong Han

In this paper, we advocate remedying the deficiency of label supervision for the MLR with incomplete labels by deriving a structured semantic prior about the label-to-label correspondence via a semantic prior prompter.

Language Modelling Self-Supervised Learning +1

Experimental Validation of Single BS 5G mmWave Positioning and Mapping for Intelligent Transport

no code implementations21 Mar 2023 Yu Ge, Hedieh Khosravi, Fan Jiang, Hui Chen, Simon Lindberg, Peter Hammarberg, Hyowon Kim, Oliver Brunnegård, Olof Eriksson, Bengt-Erik Olsson, Fredrik Tufvesson, Lennart Svensson, Henk Wymeersch

Positioning with 5G signals generally requires connection to several base stations (BSs), which makes positioning more demanding in terms of infrastructure than communications.


Multi-RIS-Enabled 3D Sidelink Positioning

no code implementations24 Feb 2023 Hui Chen, Pinjun Zheng, Musa Furkan Keskin, Tareq Al-Naffouri, Henk Wymeersch

Positioning is expected to be a core function in intelligent transportation systems (ITSs) to support communication and location-based services, such as autonomous driving, traffic control, etc.

Autonomous Driving

MVKT-ECG: Efficient Single-lead ECG Classification on Multi-Label Arrhythmia by Multi-View Knowledge Transferring

no code implementations28 Jan 2023 Yuzhen Qin, Li Sun, Hui Chen, Wei-Qiang Zhang, Wenming Yang, Jintao Fei, Guijin Wang

However, it is challenging to develop a single-lead-based ECG interpretation model for multiple diseases diagnosis due to the lack of some key disease information.

ECG Classification Knowledge Distillation

RISs and Sidelink Communications in Smart Cities: The Key to Seamless Localization and Sensing

no code implementations9 Jan 2023 Hui Chen, Hyowon Kim, Mustafa Ammous, Gonzalo Seco-Granados, George C. Alexandropoulos, Shahrokh Valaee, Henk Wymeersch

A smart city involves, among other elements, intelligent transportation, crowd monitoring, and digital twins, each of which requires information exchange via wireless communication links and localization of connected devices and passive objects (including people).

Modeling and Analysis of OFDM-based 5G/6G Localization under Hardware Impairments

no code implementations3 Jan 2023 Hui Chen, Musa Furkan Keskin, Sina Rezaei Aghdam, Hyowon Kim, Simon Lindberg, Andreas Wolfgang, Traian E. Abrudan, Thomas Eriksson, Henk Wymeersch

Our extensive simulation results demonstrate that each type of HWI leads to a different level of degradation in angle and delay estimation performance, and the prominent impairment factors on delay estimation will have a dominant negative effect on SER.

RIS-Enabled and Access-Point-Free Simultaneous Radio Localization and Mapping

no code implementations14 Dec 2022 Hyowon Kim, Hui Chen, Musa Furkan Keskin, Yu Ge, Kamran Keykhosravi, George C. Alexandropoulos, Sunwoo Kim, Henk Wymeersch

In the upcoming sixth generation (6G) of wireless communication systems, reconfigurable intelligent surfaces~(RISs) are regarded as one of the promising technological enablers, which can provide programmable signal propagation.

RIS-Aided Monostatic Sensing and Object Detection with Single and Double Bounce Multipath

no code implementations14 Dec 2022 Hyowon Kim, Alessio Fascista, Hui Chen, Yu Ge, George C. Alexandropoulos, Gonzalo Seco-Granados, Henk Wymeersch

We propose a framework for monostatic sensing by a user equipment (UE), aided by a reconfigurable intelligent surface (RIS) in environments with single- and double-bounce signal propagation.

object-detection Object Detection

Joint RIS Calibration and Multi-User Positioning

no code implementations8 Dec 2022 Yi Lu, Hui Chen, Jukka Talvitie, Henk Wymeersch, Mikko Valkama

Reconfigurable intelligent surfaces (RISs) are expected to be a key component enabling the mobile network evolution towards a flexible and intelligent 6G wireless platform.

Misspecified Cramér-Rao Bound of RIS-aided Localization under Geometry Mismatch

no code implementations13 Nov 2022 Pinjun Zheng, Hui Chen, Tarig Ballal, Henk Wymeersch, Tareq Y. Al-Naffouri

In 5G/6G wireless systems, reconfigurable intelligent surfaces (RIS) can play a role as a passive anchor to enable and enhance localization in various scenarios.

Ground Plane Matters: Picking Up Ground Plane Prior in Monocular 3D Object Detection

no code implementations3 Nov 2022 Fan Yang, Xinhao Xu, Hui Chen, Yuchen Guo, Jungong Han, Kai Ni, Guiguang Ding

To pick up the ground plane prior for M3OD, we propose a Ground Plane Enhanced Network (GPENet) which resolves both issues at one go.

Monocular 3D Object Detection object-detection

Generative Knowledge Graph Construction: A Review

1 code implementation23 Oct 2022 Hongbin Ye, Ningyu Zhang, Hui Chen, Huajun Chen

Our contributions are threefold: (1) We present a detailed, complete taxonomy for the generative KGC methods; (2) We provide a theoretical and empirical analysis of the generative KGC methods; (3) We propose several research directions that can be developed in the future.

graph construction Knowledge Graphs

MM-Align: Learning Optimal Transport-based Alignment Dynamics for Fast and Accurate Inference on Missing Modality Sequences

1 code implementation23 Oct 2022 Wei Han, Hui Chen, Min-Yen Kan, Soujanya Poria

Existing multimodal tasks mostly target at the complete input modality setting, i. e., each modality is either complete or completely missing in both training and test sets.

Denoising Imputation

SAT: Improving Semi-Supervised Text Classification with Simple Instance-Adaptive Self-Training

1 code implementation23 Oct 2022 Hui Chen, Wei Han, Soujanya Poria

Self-training methods have been explored in recent years and have exhibited great performance in improving semi-supervised learning.

Pseudo Label Semi-Supervised Text Classification

Joint User Localization and Location Calibration of A Hybrid Reconfigurable Intelligent Surface

no code implementations18 Oct 2022 Reza Ghazalian, Hui Chen, George C. Alexandropoulos, Gonzalo Seco-Granados, Henk Wymeersch, Riku Jäntti

The recent research in the emerging technology of reconfigurable intelligent surfaces (RISs) has identified its high potential for localization and sensing.


Neural-Symbolic Entangled Framework for Complex Query Answering

no code implementations19 Sep 2022 Zezhong Xu, Wen Zhang, Peng Ye, Hui Chen, Huajun Chen

In this work, we propose a Neural and Symbolic Entangled framework (ENeSy) for complex query answering, which enables the neural and symbolic reasoning to enhance each other to alleviate the cascading error and KG incompleteness.

Complex Query Answering Link Prediction +1

Localization Coverage Analysis of THz Communication Systems with a 3D Array

no code implementations19 Sep 2022 Pinjun Zheng, Tarig Ballal, Hui Chen, Henk Wymeersch, Tareq Y. Al-Naffouri

This paper considers the problem of estimating the position and orientation of a user equipped with a three-dimensional (3D) array receiving downlink far-field THz signals from multiple base stations with known positions and orientations.


DoubleMix: Simple Interpolation-Based Data Augmentation for Text Classification

1 code implementation COLING 2022 Hui Chen, Wei Han, Diyi Yang, Soujanya Poria

This paper proposes a simple yet effective interpolation-based data augmentation approach termed DoubleMix, to improve the robustness of models in text classification.

Sentence Text Augmentation +2

Detecting Network-based Internet Censorship via Latent Feature Representation Learning

1 code implementation12 Sep 2022 Shawn P. Duncan, Hui Chen

To estimate the probability of censorship events from the inferred latent features, we rely on a densely connected multi-layer neural network model.

Representation Learning

SANCL: Multimodal Review Helpfulness Prediction with Selective Attention and Natural Contrastive Learning

1 code implementation COLING 2022 Wei Han, Hui Chen, Zhen Hai, Soujanya Poria, Lidong Bing

With the boom of e-commerce, Multimodal Review Helpfulness Prediction (MRHP), which aims to sort product reviews according to the predicted helpfulness scores has become a research hotspot.

Contrastive Learning

You Only Search Once: On Lightweight Differentiable Architecture Search for Resource-Constrained Embedded Platforms

1 code implementation30 Aug 2022 Xiangzhong Luo, Di Liu, Hao Kong, Shuo Huai, Hui Chen, Weichen Liu

Benefiting from the search efficiency, differentiable neural architecture search (NAS) has evolved as the most dominant alternative to automatically design competitive deep neural networks (DNNs).

Neural Architecture Search

Doppler Exploitation in Bistatic mmWave Radio SLAM

no code implementations22 Aug 2022 Yu Ge, Ossi Kaltiokallio, Hui Chen, Fan Jiang, Jukka Talvitie, Mikko Valkama, Lennart Svensson, Henk Wymeersch

Networks in 5G and beyond utilize millimeter wave (mmWave) radio signals, large bandwidths, and large antenna arrays, which bring opportunities in jointly localizing the user equipment and mapping the propagation environment, termed as simultaneous localization and mapping (SLAM).

Simultaneous Localization and Mapping

Bi-Static Sensing for Near-Field RIS Localization

no code implementations28 Jun 2022 Reza Ghazalian, Kamran Keykhosravi, Hui Chen, Henk Wymeersch, Riku Jäntti

Due to the deployment of RISs with a large dimension, near-field (NF) scenarios are likely to occur, especially for indoor applications, and are the focus of this work.


Channel Model Mismatch Analysis for XL-MIMO Systems from a Localization Perspective

1 code implementation30 May 2022 Hui Chen, Ahmed Elzanaty, Reza Ghazalian, Musa Furkan Keskin, Riku Jäntti, Henk Wymeersch

Radio localization is applied in high-frequency (e. g., mmWave and THz) systems to support communication and to provide location-based services without extra infrastructure.

Doppler-Enabled Single-Antenna Localization and Mapping Without Synchronization

no code implementations30 May 2022 Hui Chen, Fan Jiang, Yu Ge, Hyowon Kim, Henk Wymeersch

With the help of multipath components (MPCs), localization and mapping tasks can be done with a single base station (BS) and single unsynchronized user equipment (UE) if both of them are equipped with an antenna array.

Commonsense Knowledge Salience Evaluation with a Benchmark Dataset in E-commerce

1 code implementation22 May 2022 Yincen Qu, Ningyu Zhang, Hui Chen, Zelin Dai, Zezhong Xu, Chengming Wang, Xiaoyu Wang, Qiang Chen, Huajun Chen

In addition to formulating the new task, we also release a new Benchmark dataset of Salience Evaluation in E-commerce (BSEE) and hope to promote related research on commonsense knowledge salience evaluation.

Antenna Selection in Switch-Based MIMO Arrays via DOA threshold region Approximation

1 code implementation22 May 2022 Hui Chen, Tarig Ballal, Mohammed E. Eltayeb, Tareq Y. Al-Naffouri

We first perform a subarray layout alignment process to remove subarrays with identical beampatterns and create a unique subarray set.

Bridging the Gap between Reality and Ideality of Entity Matching: A Revisiting and Benchmark Re-Construction

no code implementations12 May 2022 Tianshu Wang, Hongyu Lin, Cheng Fu, Xianpei Han, Le Sun, Feiyu Xiong, Hui Chen, Minlong Lu, Xiuwen Zhu

Experimental results demonstrate that the assumptions made in the previous benchmark construction process are not coincidental with the open environment, which conceal the main challenges of the task and therefore significantly overestimate the current progress of entity matching.

Entity Resolution

MCRB-based Performance Analysis of 6G Localization under Hardware Impairments

no code implementations27 Apr 2022 Hui Chen, Sina Rezaei Aghdam, Musa Furkan Keskin, Yibo Wu, Simon Lindberg, Andreas Wolfgang, Ulf Gustavsson, Thomas Eriksson, Henk Wymeersch

Location information is expected to be the key to meeting the needs of communication and context-aware services in 6G systems.

Quantity over Quality: Training an AV Motion Planner with Large Scale Commodity Vision Data

no code implementations3 Mar 2022 Lukas Platinsky, Tayyab Naseer, Hui Chen, Ben Haines, Haoyue Zhu, Hugo Grimmett, Luca Del Pero

This motivates the use of commodity sensors like cameras for data collection, which are an order of magnitude cheaper than HD sensor suites, but offer lower fidelity.

Motion Planning

Ontology-enhanced Prompt-tuning for Few-shot Learning

no code implementations27 Jan 2022 Hongbin Ye, Ningyu Zhang, Shumin Deng, Xiang Chen, Hui Chen, Feiyu Xiong, Xi Chen, Huajun Chen

Specifically, we develop the ontology transformation based on the external knowledge graph to address the knowledge missing issue, which fulfills and converts structure knowledge to text.

Event Extraction Few-Shot Learning +1

Constrained Wrapped Least Squares: A Tool for High Accuracy GNSS Attitude Determination

no code implementations29 Dec 2021 Xing Liu, Tarig Ballal, Hui Chen, Tareq Y. Al-Naffouri

Attitude determination is a popular application of Global Navigation Satellite Systems (GNSS).

Ghost Imaging Based on Recurrent Neural Network

no code implementations1 Dec 2021 Yuchen He, Sihong Duan, Jianxing Li, Hui Chen, Huaibin Zheng, Jianbin Liu, Yu Zhou, Zhuo Xu

The testing results show that the proposed method can achieve image reconstruction at a very low sampling rate (0. 38$\%$).

Image Reconstruction

A Tutorial on Terahertz-Band Localization for 6G Communication Systems

1 code implementation16 Oct 2021 Hui Chen, Hadi Sarieddeen, Tarig Ballal, Henk Wymeersch, Mohamed-Slim Alouini, Tareq Y. Al-Naffouri

Terahertz (THz) communications are celebrated as key enablers for converged localization and sensing in future sixth-generation (6G) wireless communication systems and beyond.

Multi-trends Enhanced Dynamic Micro-video Recommendation

no code implementations8 Oct 2021 Yujie Lu, Yingxuan Huang, Shengyu Zhang, Wei Han, Hui Chen, Zhou Zhao, Fei Wu

In this paper, we propose the DMR framework to explicitly model dynamic multi-trends of users' current preference and make predictions based on both the history and future potential trends.

Recommendation Systems

Learning to Ask for Data-Efficient Event Argument Extraction

no code implementations1 Oct 2021 Hongbin Ye, Ningyu Zhang, Zhen Bi, Shumin Deng, Chuanqi Tan, Hui Chen, Fei Huang, Huajun Chen

Event argument extraction (EAE) is an important task for information extraction to discover specific argument roles.

Event Argument Extraction

Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis

2 code implementations EMNLP 2021 Wei Han, Hui Chen, Soujanya Poria

In this work, we propose a framework named MultiModal InfoMax (MMIM), which hierarchically maximizes the Mutual Information (MI) in unimodal input pairs (inter-modality) and between multimodal fusion result and unimodal input in order to maintain task-related information through multimodal fusion.

Multimodal Sentiment Analysis

Bi-Bimodal Modality Fusion for Correlation-Controlled Multimodal Sentiment Analysis

2 code implementations28 Jul 2021 Wei Han, Hui Chen, Alexander Gelbukh, Amir Zadeh, Louis-Philippe Morency, Soujanya Poria

Multimodal sentiment analysis aims to extract and integrate semantic information collected from multiple modalities to recognize the expressed emotions and sentiment in multimodal data.

Multimodal Deep Learning Multimodal Sentiment Analysis

A Game-Theoretic Approach to Multi-Agent Trust Region Optimization

1 code implementation12 Jun 2021 Ying Wen, Hui Chen, Yaodong Yang, Zheng Tian, Minne Li, Xu Chen, Jun Wang

Trust region methods are widely applied in single-agent reinforcement learning problems due to their monotonic performance-improvement guarantee at every iteration.

Atari Games Multi-agent Reinforcement Learning +2

Improving Conversational Recommendation System by Pretraining on Billions Scale of Knowledge Graph

no code implementations30 Apr 2021 Chi-Man Wong, Fan Feng, Wen Zhang, Chi-Man Vong, Hui Chen, Yichi Zhang, Peng He, Huan Chen, Kun Zhao, Huajun Chen

We first construct a billion-scale conversation knowledge graph (CKG) from information about users, items and conversations, and then pretrain CKG by introducing knowledge graph embedding method and graph convolution network to encode semantic and structural information respectively. To make the CTR prediction model sensible of current state of users and the relationship between dialogues and items, we introduce user-state and dialogue-interaction representations based on pre-trained CKG and propose K-DCN. In K-DCN, we fuse the user-state representation, dialogue-interaction representation and other normal feature representations via deep cross network, which will give the rank of candidate items to be recommended. We experimentally prove that our proposal significantly outperforms baselines and show it's real application in Alime.

Click-Through Rate Prediction Knowledge Graph Embedding +1

Speckles-Training-Based Denoising Convolutional Neural Network Ghost Imaging

no code implementations7 Apr 2021 Yuchen He, Sihong Duan, Jianxing Li, Hui Chen, Huaibin Zheng, Jianbin Liu, Shitao Zhu, Zhuo Xu

Ghost imaging (GI) has been paid attention gradually because of its lens-less imaging capability, turbulence-free imaging and high detection sensitivity.


Text-guided Legal Knowledge Graph Reasoning

1 code implementation6 Apr 2021 Luoqiu Li, Zhen Bi, Hongbin Ye, Shumin Deng, Hui Chen, Huaixiao Tou

In this paper, we propose a novel legal application of legal provision prediction (LPP), which aims to predict the related legal provisions of affairs.

Knowledge Graph Completion

Generative-Adversarial-Networks-based Ghost Recognition

no code implementations25 Mar 2021 Yuchen He, Yibing Chen, Sheng Luo, Hui Chen, Jianxing Li, Zhuo Xu

The proposed method can improve the problems caused by conventional recognition methods that based on target image information, and provide a certain turbulence-free ability.

Image Reconstruction

Deep Structural Estimation: With an Application to Option Pricing

1 code implementation18 Feb 2021 Hui Chen, Antoine Didisheim, Simon Scheidegger

We propose a novel structural estimation framework in which we train a surrogate of an economic model with deep neural networks.

DOA Estimation with Non-Uniform Linear Arrays: A Phase-Difference Projection Approach

1 code implementation6 Feb 2021 Hui Chen, Tarig Ballal, Tareq Y. Al-Naffouri

The concept of \emph{wrapped phased-difference pattern} (WPDP) is introduced, which allows the proposed algorithm to compute most of the parameters required for DOA estimation in an offline manner, hence resulting in a superior computational speed in realtime.

Contrastive Coding for Active Learning Under Class Distribution Mismatch

no code implementations ICCV 2021 Pan Du, Suyun Zhao, Hui Chen, Shuwen Chai, Hong Chen, Cuiping Li

However, its performance deteriorates under class distribution mismatch, wherein the unlabeled data contain many samples out of the class distribution of labeled data.

Active Learning Contrastive Learning

Multi-Agent Trust Region Learning

1 code implementation1 Jan 2021 Ying Wen, Hui Chen, Yaodong Yang, Zheng Tian, Minne Li, Xu Chen, Jun Wang

We derive the lower bound of agents' payoff improvements for MATRL methods, and also prove the convergence of our method on the meta-game fixed points.

Atari Games Multi-agent Reinforcement Learning +3

Physical rendering of synthetic spaces for topological sound transport

no code implementations22 Dec 2020 Hui Chen, Hongkuan Zhang, Qian Wu, Yu Huang, Huy Nguyen, Emil Prodan, Xiaoming Zhou, Guoliang Huang

Synthetic dimensions can be rendered in the physical space and this has been achieved with photonics and cold atomic gases, however, little to no work has been succeeded in acoustics because acoustic wave-guides cannot be weakly coupled in a continuous fashion.

Mesoscale and Nanoscale Physics Classical Physics

Persuasive Dialogue Understanding: the Baselines and Negative Results

no code implementations19 Nov 2020 Hui Chen, Deepanway Ghosal, Navonil Majumder, Amir Hussain, Soujanya Poria

Persuasion aims at forming one's opinion and action via a series of persuasive messages containing persuader's strategies.

Attribute Dialogue Understanding +7

Learning to Infer Unseen Attribute-Object Compositions

no code implementations27 Oct 2020 Hui Chen, Zhixiong Nan, Jingjing Jiang, Nanning Zheng

The composition recognition of unseen attribute-object is critical to make machines learn to decompose and compose complex concepts like people.

Attribute Object

Decision-Aware Conditional GANs for Time Series Data

no code implementations26 Sep 2020 He Sun, Zhun Deng, Hui Chen, David C. Parkes

We introduce the decision-aware time-series conditional generative adversarial network (DAT-CGAN) as a method for time-series generation.

Generative Adversarial Network Time Series +2

DualDE: Dually Distilling Knowledge Graph Embedding for Faster and Cheaper Reasoning

no code implementations13 Sep 2020 Yushan Zhu, Wen Zhang, Mingyang Chen, Hui Chen, Xu Cheng, Wei zhang, Huajun Chen

In DualDE, we propose a soft label evaluation mechanism to adaptively assign different soft label and hard label weights to different triples, and a two-stage distillation approach to improve the student's acceptance of the teacher.

Knowledge Distillation Knowledge Graph Embedding +2

Dialogue Relation Extraction with Document-level Heterogeneous Graph Attention Networks

1 code implementation10 Sep 2020 Hui Chen, Pengfei Hong, Wei Han, Navonil Majumder, Soujanya Poria

This graph is fed to a graph attention network for context propagation among relevant nodes, which effectively captures the dialogue context.

Ranked #7 on Dialog Relation Extraction on DialogRE (F1c (v1) metric)

Dialog Relation Extraction Graph Attention +2

FLFE: A Communication-Efficient and Privacy-Preserving Federated Feature Engineering Framework

no code implementations5 Sep 2020 Pei Fang, Zhendong Cai, Hui Chen, QingJiang Shi

Feature engineering is the process of using domain knowledge to extract features from raw data via data mining techniques and is a key step to improve the performance of machine learning algorithms.

Feature Engineering Privacy Preserving

A Derivation of Identifiable Condition for Non-Uniform Linear Array DOA Estimation

no code implementations31 Aug 2020 Hui Chen, Tarig Ballal, Tareq Y. Al-Naffouri

Phase ambiguity happens in uniform linear arrays (ULAs) when the sensor distance is greater than $\lambda/2$.

A Natural Language Processing Pipeline of Chinese Free-text Radiology Reports for Liver Cancer Diagnosis

no code implementations10 Apr 2020 Honglei Liu, Yan Xu, Zhiqiang Zhang, Ni Wang, Yanqun Huang, Yanjun Hu, Zhenghan Yang, Rui Jiang, Hui Chen

Despite the rapid development of natural language processing (NLP) implementation in electronic medical records (EMRs), Chinese EMRs processing remains challenging due to the limited corpus and specific grammatical characteristics, especially for radiology reports.

Computed Tomography (CT) Coreference Resolution +3


no code implementations ICLR 2020 Hui Chen, Zhixiong Nan, Nanning Zheng

This paper handles a challenging problem, unseen attribute-object pair recognition, which asks a model to simultaneously recognize the attribute type and the object type of a given image while this attribute-object pair is not included in the training set.

Attribute Object

Enhanced Meta-Learning for Cross-lingual Named Entity Recognition with Minimal Resources

1 code implementation14 Nov 2019 Qianhui Wu, Zijia Lin, Guoxin Wang, Hui Chen, Börje F. Karlsson, Biqing Huang, Chin-Yew Lin

For languages with no annotated resources, transferring knowledge from rich-resource languages is an effective solution for named entity recognition (NER).

Cross-Lingual NER Meta-Learning +4

UER: An Open-Source Toolkit for Pre-training Models

1 code implementation IJCNLP 2019 Zhe Zhao, Hui Chen, Jinbin Zhang, Xin Zhao, Tao Liu, Wei Lu, Xi Chen, Haotang Deng, Qi Ju, Xiaoyong Du

Existing works, including ELMO and BERT, have revealed the importance of pre-training for NLP tasks.

PDANet: Polarity-consistent Deep Attention Network for Fine-grained Visual Emotion Regression

1 code implementation11 Sep 2019 Sicheng Zhao, Zizhou Jia, Hui Chen, Leida Li, Guiguang Ding, Kurt Keutzer

By optimizing the PCR loss, PDANet can generate a polarity preserved attention map and thus improve the emotion regression performance.

Deep Attention Emotion Classification +2

A new Majorana platform in an Fe-As bilayer superconductor

no code implementations1 Jul 2019 Wenyao Liu, Lu Cao, Shiyu Zhu, Lingyuan Kong, Guangwei Wang, Michal Papaj, Peng Zhang, Yabin Liu, Hui Chen, Geng Li, Fazhi Yang, Takeshi Kondo, Shixuan Du, Guanghan Cao, Shik Shin, Liang Fu, Zhiping Yin, Hong-Jun Gao, Hong Ding

On the other hand, some iron-pnictide (Fe-As) superconductors, such as LiFeAs, have been demonstrated to have a similar topological band structure, yet no MZM has been observed in its vortex cores, raising a question of universality of MZM presence in iron-based superconductors.

Superconductivity Strongly Correlated Electrons

A Variational Approach for Learning from Positive and Unlabeled Data

1 code implementation NeurIPS 2020 Hui Chen, Fangqing Liu, Yin Wang, Liyue Zhao, Hao Wu

Learning binary classifiers only from positive and unlabeled (PU) data is an important and challenging task in many real-world applications, including web text classification, disease gene identification and fraud detection, where negative samples are difficult to verify experimentally.

Fraud Detection text-classification +1

Geometry-Contrastive GAN for Facial Expression Transfer

1 code implementation6 Feb 2018 Fengchun Qiao, Naiming Yao, Zirui Jiao, Zhihao LI, Hui Chen, Hongan Wang

Geometry information is introduced into cGANs as continuous conditions to guide the generation of facial expressions.

Contrastive Learning Generative Adversarial Network

3D Model-Based Continuous Emotion Recognition

no code implementations CVPR 2015 Hui Chen, Jiangdong Li, Fengjun Zhang, Yang Li, Hongan Wang

We propose a real-time 3D model-based method that continuously recognizes dimensional emotions from facial expressions in natural communications.

Emotion Recognition

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