Search Results for author: Liang Chen

Found 130 papers, 56 papers with code

OID: Outlier Identifying and Discarding in Blind Image Deblurring

no code implementations ECCV 2020 Liang Chen, Faming Fang, Jiawei Zhang, Jun Liu, Guixu Zhang

Even a small amount of outliers can dramatically degrade the quality of the estimated blur kernel, because the outliers are not conforming to the linear formation of the blurring process.

Blind Image Deblurring Image Deblurring

Enhanced Sparse Model for Blind Deblurring

no code implementations ECCV 2020 Liang Chen, Faming Fang, Shen Lei, Fang Li, Guixu Zhang

Specifically, we use a weighted combination of a dense function (i. e. l2) and a newly designed enhanced sparse model termed as le, which is developed from two sparse models (i. e. l1 and l0), to fulfill the task.


The Devil is in the Data: Learning Fair Graph Neural Networks via Partial Knowledge Distillation

1 code implementation29 Nov 2023 Yuchang Zhu, Jintang Li, Liang Chen, Zibin Zheng

Experiments on several benchmark datasets demonstrate that FairGKD, which does not require access to demographic information, significantly improves the fairness of GNNs by a large margin while maintaining their utility.

Fairness Knowledge Distillation

A Survey of the Evolution of Language Model-Based Dialogue Systems

no code implementations28 Nov 2023 Hongru Wang, Lingzhi Wang, Yiming Du, Liang Chen, Jingyan Zhou, YuFei Wang, Kam-Fai Wong

This survey delves into the historical trajectory of dialogue systems, elucidating their intricate relationship with advancements in language models by categorizing this evolution into four distinct stages, each marked by pivotal LM breakthroughs: 1) Early_Stage: characterized by statistical LMs, resulting in rule-based or machine-learning-driven dialogue_systems; 2) Independent development of TOD and ODD based on neural_language_models (NLM; e. g., LSTM and GRU), since NLMs lack intrinsic knowledge in their parameters; 3) fusion between different types of dialogue systems with the advert of pre-trained_language_models (PLMs), starting from the fusion between four_sub-tasks_within_TOD, and then TOD_with_ODD; and 4) current LLM-based_dialogue_system, wherein LLMs can be used to conduct TOD and ODD seamlessly.

Language Modelling

LasTGL: An Industrial Framework for Large-Scale Temporal Graph Learning

no code implementations28 Nov 2023 Jintang Li, Jiawang Dan, Ruofan Wu, Jing Zhou, Sheng Tian, Yunfei Liu, Baokun Wang, Changhua Meng, Weiqiang Wang, Yuchang Zhu, Liang Chen, Zibin Zheng

Over the past few years, graph neural networks (GNNs) have become powerful and practical tools for learning on (static) graph-structure data.

Graph Learning

Hetero$^2$Net: Heterophily-aware Representation Learning on Heterogenerous Graphs

no code implementations18 Oct 2023 Jintang Li, Zheng Wei, Jiawang Dan, Jing Zhou, Yuchang Zhu, Ruofan Wu, Baokun Wang, Zhang Zhen, Changhua Meng, Hong Jin, Zibin Zheng, Liang Chen

Through in-depth investigations on several real-world heterogeneous graphs exhibiting varying levels of heterophily, we have observed that heterogeneous graph neural networks (HGNNs), which inherit many mechanisms from GNNs designed for homogeneous graphs, fail to generalize to heterogeneous graphs with heterophily or low level of homophily.

Node Classification Representation Learning

Language Agents for Detecting Implicit Stereotypes in Text-to-image Models at Scale

no code implementations18 Oct 2023 Qichao Wang, Tian Bian, Yian Yin, Tingyang Xu, Hong Cheng, Helen M. Meng, Zibin Zheng, Liang Chen, Bingzhe Wu

The recent surge in the research of diffusion models has accelerated the adoption of text-to-image models in various Artificial Intelligence Generated Content (AIGC) commercial products.

Guiding AMR Parsing with Reverse Graph Linearization

1 code implementation13 Oct 2023 Bofei Gao, Liang Chen, Peiyi Wang, Zhifang Sui, Baobao Chang

Abstract Meaning Representation (AMR) parsing aims to extract an abstract semantic graph from a given sentence.

AMR Parsing

Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators

1 code implementation11 Oct 2023 Liang Chen, Yang Deng, Yatao Bian, Zeyu Qin, Bingzhe Wu, Tat-Seng Chua, Kam-Fai Wong

Large language models (LLMs) outperform information retrieval techniques for downstream knowledge-intensive tasks when being prompted to generate world knowledge.

Information Retrieval Informativeness +4

Synaptic delay induced macroscopic dynamics of the large-scale network of Izhikevich neurons

no code implementations6 Oct 2023 Liang Chen, Sue Ann Campbell

We investigate the impact of the heterogeneity of the quenched input current, the SFA mechanism and the synaptic delay on macroscopic dynamics.

Existence of a Competitive Equilibrium with Substitutes, with Applications to Matching and Discrete Choice Models

no code implementations20 Sep 2023 Liang Chen, Eugene Choo, Alfred Galichon, Simon Weber

We propose new results for the existence and uniqueness of a general nonparametric and nonseparable competitive equilibrium with substitutes.

MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning

2 code implementations14 Sep 2023 Haozhe Zhao, Zefan Cai, Shuzheng Si, Xiaojian Ma, Kaikai An, Liang Chen, Zixuan Liu, Sheng Wang, Wenjuan Han, Baobao Chang

In this paper, we address the limitation above by 1) introducing MMICL, a new approach to allow the VLM to deal with multi-modal inputs efficiently; 2) proposing a novel context scheme to augment the in-context learning ability of the VLM; 3) constructing the Multi-modal In-Context Learning (MIC) dataset, designed to enhance the VLM's ability to understand complex multi-modal prompts.

Language Modelling

Making Large Language Models Better Reasoners with Alignment

no code implementations5 Sep 2023 Peiyi Wang, Lei LI, Liang Chen, Feifan Song, Binghuai Lin, Yunbo Cao, Tianyu Liu, Zhifang Sui

To address this problem, we introduce an \textit{Alignment Fine-Tuning (AFT)} paradigm, which involves three steps: 1) fine-tuning LLMs with COT training data; 2) generating multiple COT responses for each question, and categorizing them into positive and negative ones based on whether they achieve the correct answer; 3) calibrating the scores of positive and negative responses given by LLMs with a novel constraint alignment loss.

Domain Generalization via Rationale Invariance

1 code implementation ICCV 2023 Liang Chen, Yong Zhang, Yibing Song, Anton Van Den Hengel, Lingqiao Liu

Specifically, we propose treating the element-wise contributions to the final results as the rationale for making a decision and representing the rationale for each sample as a matrix.

Decision Making Domain Generalization

SAILOR: Structural Augmentation Based Tail Node Representation Learning

1 code implementation13 Aug 2023 Jie Liao, Jintang Li, Liang Chen, Bingzhe Wu, Yatao Bian, Zibin Zheng

In the pursuit of promoting the expressiveness of GNNs for tail nodes, we explore how the deficiency of structural information deteriorates the performance of tail nodes and propose a general Structural Augmentation based taIL nOde Representation learning framework, dubbed as SAILOR, which can jointly learn to augment the graph structure and extract more informative representations for tail nodes.

Representation Learning

A Self-supervised SAR Image Despeckling Strategy Based on Parameter-sharing Convolutional Neural Networks

no code implementations11 Aug 2023 Liang Chen, Yifei Yin, Hao Shi, Qingqing Sheng, Wei Li

The training image pairs are generated by the sub-sampler from real-word SAR image to estimate the noise distribution.

Sar Image Despeckling

M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning

no code implementations7 Jun 2023 Lei LI, Yuwei Yin, Shicheng Li, Liang Chen, Peiyi Wang, Shuhuai Ren, Mukai Li, Yazheng Yang, Jingjing Xu, Xu sun, Lingpeng Kong, Qi Liu

To tackle this challenge and promote research in the vision-language field, we introduce the Multi-Modal, Multilingual Instruction Tuning (M$^3$IT) dataset, designed to optimize VLM alignment with human instructions.

World Knowledge

Scaling Up, Scaling Deep: Blockwise Graph Contrastive Learning

1 code implementation3 Jun 2023 Jintang Li, Wangbin Sun, Ruofan Wu, Yuchang Zhu, Liang Chen, Zibin Zheng

Oversmoothing is a common phenomenon in graph neural networks (GNNs), in which an increase in the network depth leads to a deterioration in their performance.

Contrastive Learning

A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks

1 code implementation30 May 2023 Jintang Li, Huizhe Zhang, Ruofan Wu, Zulun Zhu, Liang Chen, Zibin Zheng, Baokun Wang, Changhua Meng

While contrastive self-supervised learning has become the de-facto learning paradigm for graph neural networks, the pursuit of high task accuracy requires a large hidden dimensionality to learn informative and discriminative full-precision representations, raising concerns about computation, memory footprint, and energy consumption burden (largely overlooked) for real-world applications.

Contrastive Learning Self-Supervised Learning

Large Language Models are not Fair Evaluators

2 code implementations29 May 2023 Peiyi Wang, Lei LI, Liang Chen, Zefan Cai, Dawei Zhu, Binghuai Lin, Yunbo Cao, Qi Liu, Tianyu Liu, Zhifang Sui

In this paper, we uncover a systematic bias in the evaluation paradigm of adopting large language models~(LLMs), e. g., GPT-4, as a referee to score and compare the quality of responses generated by candidate models.

Language Modelling Large Language Model

Attention Paper: How Generative AI Reshapes Digital Shadow Industry?

no code implementations26 May 2023 Qichao Wang, Huan Ma, WenTao Wei, Hangyu Li, Liang Chen, Peilin Zhao, Binwen Zhao, Bo Hu, Shu Zhang, Zibin Zheng, Bingzhe Wu

The rapid development of digital economy has led to the emergence of various black and shadow internet industries, which pose potential risks that can be identified and managed through digital risk management (DRM) that uses different techniques such as machine learning and deep learning.


TransWorldNG: Traffic Simulation via Foundation Model

1 code implementation25 May 2023 Ding Wang, Xuhong Wang, Liang Chen, Shengyue Yao, Ming Jing, Honghai Li, Li Li, Shiqiang Bao, Fei-Yue Wang, Yilun Lin

To the best of our knowledge, this is the first traffic simulator that can automatically learn traffic patterns from real-world data and efficiently generate accurate and realistic traffic environments.

Decision Making Management

Building Transportation Foundation Model via Generative Graph Transformer

no code implementations24 May 2023 Xuhong Wang, Ding Wang, Liang Chen, Yilun Lin

This data-driven and model-free simulation method addresses the challenges faced by traditional systems in terms of structural complexity and model accuracy and provides a foundation for solving complex transportation problems with real data.

Graph Generation Management +1

Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration

1 code implementation23 May 2023 Yang Deng, Lizi Liao, Liang Chen, Hongru Wang, Wenqiang Lei, Tat-Seng Chua

Conversational systems based on Large Language Models (LLMs), such as ChatGPT, show exceptional proficiency in context understanding and response generation.

Descriptive Response Generation

On the robust learning mixtures of linear regressions

no code implementations23 May 2023 Ying Huang, Liang Chen

In this note, we consider the problem of robust learning mixtures of linear regressions.

Less Can Be More: Unsupervised Graph Pruning for Large-scale Dynamic Graphs

1 code implementation18 May 2023 Jintang Li, Sheng Tian, Ruofan Wu, Liang Zhu, Welong Zhao, Changhua Meng, Liang Chen, Zibin Zheng, Hongzhi Yin

We approach the problem by our proposed STEP, a self-supervised temporal pruning framework that learns to remove potentially redundant edges from input dynamic graphs.

Node Classification

Estimation of Characteristics-based Quantile Factor Models

no code implementations26 Apr 2023 Liang Chen, Juan Jose Dolado, Jesus Gonzalo, Haozi Pan

This paper studies the estimation of characteristic-based quantile factor models where the factor loadings are unknown functions of observed individual characteristics while the idiosyncratic error terms are subject to conditional quantile restrictions.

Common Correlated Effects Estimation of Nonlinear Panel Data Models

no code implementations25 Apr 2023 Liang Chen, Minyuan Zhang

This paper focuses on estimating the coefficients and average partial effects of observed regressors in nonlinear panel data models with interactive fixed effects, using the common correlated effects (CCE) framework.

Time Series

Curriculum Modeling the Dependence among Targets with Multi-task Learning for Financial Marketing

no code implementations25 Apr 2023 Yunpeng Weng, Xing Tang, Liang Chen, Xiuqiang He

For example, in online marketing, the cascade behavior pattern of $impression \rightarrow click \rightarrow conversion$ is usually modeled as multiple tasks in a multi-task manner, where the sequential dependence between tasks is simply connected with an explicitly defined function or implicitly transferred information in current works.

Marketing Multi-Task Learning

Efficient Halftoning via Deep Reinforcement Learning

no code implementations24 Apr 2023 Haitian Jiang, Dongliang Xiong, Xiaowen Jiang, Li Ding, Liang Chen, Kai Huang

In this paper, we propose a fast and structure-aware halftoning method via a data-driven approach.

reinforcement-learning SSIM

Cross-View Hierarchy Network for Stereo Image Super-Resolution

1 code implementation13 Apr 2023 Wenbin Zou, Hongxia Gao, Liang Chen, Yunchen Zhang, Mingchao Jiang, Zhongxin Yu, Ming Tan

Stereo image super-resolution aims to improve the quality of high-resolution stereo image pairs by exploiting complementary information across views.

Stereo Image Super-Resolution

Improved Test-Time Adaptation for Domain Generalization

1 code implementation CVPR 2023 Liang Chen, Yong Zhang, Yibing Song, Ying Shan, Lingqiao Liu

Generally, a TTT strategy hinges its performance on two main factors: selecting an appropriate auxiliary TTT task for updating and identifying reliable parameters to update during the test phase.

Domain Generalization Test

Manipulating Federated Recommender Systems: Poisoning with Synthetic Users and Its Countermeasures

no code implementations6 Apr 2023 Wei Yuan, Quoc Viet Hung Nguyen, Tieke He, Liang Chen, Hongzhi Yin

To reveal the real vulnerability of FedRecs, in this paper, we present a new poisoning attack method to manipulate target items' ranks and exposure rates effectively in the top-$K$ recommendation without relying on any prior knowledge.

Privacy Preserving Recommendation Systems

Self-Sampling Training and Evaluation for the Accuracy-Bias Tradeoff in Recommendation

1 code implementation7 Feb 2023 Dugang Liu, Yang Qiao, Xing Tang, Liang Chen, Xiuqiang He, Weike Pan, Zhong Ming

Specifically, SSTE uses a self-sampling module to generate some subsets with different degrees of bias from the original training and validation data.


Optimizing Feature Set for Click-Through Rate Prediction

1 code implementation26 Jan 2023 Fuyuan Lyu, Xing Tang, Dugang Liu, Liang Chen, Xiuqiang He, Xue Liu

Because of the large-scale search space, we develop a learning-by-continuation training scheme to learn such gates.

Click-Through Rate Prediction

CARD: Semantic Segmentation with Efficient Class-Aware Regularized Decoder

1 code implementation11 Jan 2023 Ye Huang, Di Kang, Liang Chen, Wenjing Jia, Xiangjian He, Lixin Duan, Xuefei Zhe, Linchao Bao

Extensive experiments and ablation studies conducted on multiple benchmark datasets demonstrate that the proposed CAR can boost the accuracy of all baseline models by up to 2. 23% mIOU with superior generalization ability.

Representation Learning Semantic Segmentation +1

MR Elastography with Optimization-Based Phase Unwrapping and Traveling Wave Expansion-based Neural Network (TWENN)

no code implementations6 Jan 2023 Shengyuan Ma, Runke Wang, Suhao Qiu, Ruokun Li, Qi Yue, Qingfang Sun, Liang Chen, Fuhua Yan, Guang-Zhong Yang, Yuan Feng

Here we propose a pipeline for processing MRE images using optimization-based displacement extraction and Traveling Wave Expansion-based Neural Network (TWENN) modulus estimation.

Spectral Adversarial Training for Robust Graph Neural Network

1 code implementation20 Nov 2022 Jintang Li, Jiaying Peng, Liang Chen, Zibin Zheng, TingTing Liang, Qing Ling

In this work, we seek to address these challenges and propose Spectral Adversarial Training (SAT), a simple yet effective adversarial training approach for GNNs.

Are All Edges Necessary? A Unified Framework for Graph Purification

no code implementations9 Nov 2022 Zishan Gu, Jintang Li, Liang Chen

Graph Neural Networks (GNNs) as deep learning models working on graph-structure data have achieved advanced performance in many works.

Large-batch Optimization for Dense Visual Predictions

1 code implementation20 Oct 2022 Zeyue Xue, Jianming Liang, Guanglu Song, Zhuofan Zong, Liang Chen, Yu Liu, Ping Luo

To address this challenge, we propose a simple yet effective algorithm, named Adaptive Gradient Variance Modulator (AGVM), which can train dense visual predictors with very large batch size, enabling several benefits more appealing than prior arts.

Instance Segmentation object-detection +3

A Two-Stage Method for Chinese AMR Parsing

1 code implementation29 Sep 2022 Liang Chen, Bofei Gao, Baobao Chang

In this paper, we provide a detailed description of our system at CAMRP-2022 evaluation.

AMR Parsing Test +1

Uncertainty-Induced Transferability Representation for Source-Free Unsupervised Domain Adaptation

1 code implementation30 Aug 2022 Jiangbo Pei, Zhuqing Jiang, Aidong Men, Liang Chen, Yang Liu, Qingchao Chen

Secondly, based on the UTR, we propose a novel Calibrated Adaption Framework (CAF) for SFUDA, including i)the source knowledge calibration module that guides the target model to learn the transferable source knowledge and discard the non-transferable one, and ii)the target semantics calibration module that calibrates the unreliable semantics.

Unsupervised Domain Adaptation

Scaling Up Dynamic Graph Representation Learning via Spiking Neural Networks

1 code implementation15 Aug 2022 Jintang Li, Zhouxin Yu, Zulun Zhu, Liang Chen, Qi Yu, Zibin Zheng, Sheng Tian, Ruofan Wu, Changhua Meng

We explore a new direction in that we can capture the evolving dynamics of temporal graphs with spiking neural networks (SNNs) instead of RNNs.

Graph Representation Learning Node Classification

Spiking Graph Convolutional Networks

1 code implementation5 May 2022 Zulun Zhu, Jiaying Peng, Jintang Li, Liang Chen, Qi Yu, Siqiang Luo

Graph Convolutional Networks (GCNs) achieve an impressive performance due to the remarkable representation ability in learning the graph information.

Graph Classification Recommendation Systems

A Survey of Deep Learning Models for Structural Code Understanding

1 code implementation3 May 2022 Ruoting Wu, Yuxin Zhang, Qibiao Peng, Liang Chen, Zibin Zheng

In recent years, the rise of deep learning and automation requirements in the software industry has elevated Intelligent Software Engineering to new heights.

FastGCL: Fast Self-Supervised Learning on Graphs via Contrastive Neighborhood Aggregation

no code implementations2 May 2022 Yuansheng Wang, Wangbin Sun, Kun Xu, Zulun Zhu, Liang Chen, Zibin Zheng

Graph contrastive learning (GCL), as a popular approach to graph self-supervised learning, has recently achieved a non-negligible effect.

Contrastive Learning Data Augmentation +3

GUARD: Graph Universal Adversarial Defense

1 code implementation20 Apr 2022 Jintang Li, Jie Liao, Ruofan Wu, Liang Chen, Zibin Zheng, Jiawang Dan, Changhua Meng, Weiqiang Wang

To mitigate such a threat, considerable research efforts have been devoted to increasing the robustness of GCNs against adversarial attacks.

Adversarial Defense

Self-Calibrated Efficient Transformer for Lightweight Super-Resolution

1 code implementation19 Apr 2022 Wenbin Zou, Tian Ye, Weixin Zheng, Yunchen Zhang, Liang Chen, Yi Wu

Recently, deep learning has been successfully applied to the single-image super-resolution (SISR) with remarkable performance.

Image Super-Resolution

ATP: AMRize Then Parse! Enhancing AMR Parsing with PseudoAMRs

2 code implementations Findings (NAACL) 2022 Liang Chen, Peiyi Wang, Runxin Xu, Tianyu Liu, Zhifang Sui, Baobao Chang

As Abstract Meaning Representation (AMR) implicitly involves compound semantic annotations, we hypothesize auxiliary tasks which are semantically or formally related can better enhance AMR parsing.

Ranked #7 on AMR Parsing on LDC2020T02 (using extra training data)

AMR Parsing Dependency Parsing +1

Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection

1 code implementation CVPR 2022 Liang Chen, Yong Zhang, Yibing Song, Lingqiao Liu, Jue Wang

Following this principle, we propose to enrich the "diversity" of forgeries by synthesizing augmented forgeries with a pool of forgery configurations and strengthen the "sensitivity" to the forgeries by enforcing the model to predict the forgery configurations.

DeepFake Detection Face Swapping +1

Exact mean-field models for spiking neural networks with adaptation

no code implementations16 Mar 2022 Liang Chen, Sue Ann Campbell

Networks of spiking neurons with adaption have been shown to be able to reproduce a wide range of neural activities, including the emergent population bursting and spike synchrony that underpin brain disorders and normal function.

CAR: Class-aware Regularizations for Semantic Segmentation

1 code implementation arXiv:2203.07160 2022 Ye Huang, Di Kang, Liang Chen, Xuefei Zhe, Wenjing Jia, Xiangjian He, Linchao Bao

Recent segmentation methods, such as OCR and CPNet, utilizing "class level" information in addition to pixel features, have achieved notable success for boosting the accuracy of existing network modules.

Representation Learning Semantic Segmentation

Focus on the Target's Vocabulary: Masked Label Smoothing for Machine Translation

2 code implementations6 Mar 2022 Liang Chen, Runxin Xu, Baobao Chang

Label smoothing and vocabulary sharing are two widely used techniques in neural machine translation models.

Machine Translation Translation

Faithful learning with sure data for lung nodule diagnosis

no code implementations25 Feb 2022 Hanxiao Zhang, Liang Chen, Xiao Gu, Minghui Zhang, Yulei Qin, Feng Yao, Zhexin Wang, Yun Gu, Guang-Zhong Yang

In this study, we construct a sure dataset with pathologically-confirmed labels and propose a collaborative learning framework to facilitate sure nodule classification by integrating unsure data knowledge through nodule segmentation and malignancy score regression.

Classification Lung Nodule Classification +1

Enhanced DeepONet for Modeling Partial Differential Operators Considering Multiple Input Functions

no code implementations17 Feb 2022 Lesley Tan, Liang Chen

We propose new Enhanced DeepONet or EDeepONet high-level neural network structure, in which two input functions are represented by two branch DNN sub-networks, which are then connected with output truck network via inner product to generate the output of the whole neural network.

Recent Advances in Reliable Deep Graph Learning: Inherent Noise, Distribution Shift, and Adversarial Attack

no code implementations15 Feb 2022 Jintang Li, Bingzhe Wu, Chengbin Hou, Guoji Fu, Yatao Bian, Liang Chen, Junzhou Huang, Zibin Zheng

Despite the progress, applying DGL to real-world applications faces a series of reliability threats including inherent noise, distribution shift, and adversarial attacks.

Adversarial Attack Graph Learning

Robust Dynamic State Estimator of Integrated Energy Systems based on Natural Gas Partial Differential Equations

no code implementations4 Feb 2022 Liang Chen, Yang Li, Manyun Huang, Xinxin Hui, Songlin Gu

A novel robust dynamic state estimation methodology for integrated natural gas and electric power systems is proposed based on Kalman filter.

Neighboring Backdoor Attacks on Graph Convolutional Network

no code implementations17 Jan 2022 Liang Chen, Qibiao Peng, Jintang Li, Yang Liu, Jiawei Chen, Yong Li, Zibin Zheng

To address such a challenge, we set the trigger as a single node, and the backdoor is activated when the trigger node is connected to the target node.

Backdoor Attack

Geometric Anchor Correspondence Mining With Uncertainty Modeling for Universal Domain Adaptation

no code implementations CVPR 2022 Liang Chen, Yihang Lou, Jianzhong He, Tao Bai, Minghua Deng

Therefore, in this paper, we propose a Geometric anchor-guided Adversarial and conTrastive learning framework with uncErtainty modeling called GATE to alleviate these issues.

Contrastive Learning Universal Domain Adaptation

Carrier Phase Ranging for Indoor Positioning with 5G NR Signals

no code implementations22 Dec 2021 Liang Chen, Xin Zhou, Feifei Chen, Lie-Liang Yang, Ruizhi Chen

Indoor positioning is one of the core technologies of Internet of Things (IoT) and artificial intelligence (AI), and is expected to play a significant role in the upcoming era of AI.

Perceiving and Modeling Density is All You Need for Image Dehazing

1 code implementation18 Nov 2021 Tian Ye, Mingchao Jiang, Yunchen Zhang, Liang Chen, ErKang Chen, Pen Chen, Zhiyong Lu

However, due to the paradox caused by the variation of real captured haze and the fixed degradation parameters of the current networks, the generalization ability of recent dehazing methods on real-world hazy images is not ideal. To address the problem of modeling real-world haze degradation, we propose to solve this problem by perceiving and modeling density for uneven haze distribution.

Image Dehazing Single Image Dehazing

Hierarchical Curriculum Learning for AMR Parsing

1 code implementation ACL 2022 Peiyi Wang, Liang Chen, Tianyu Liu, Damai Dai, Yunbo Cao, Baobao Chang, Zhifang Sui

Abstract Meaning Representation (AMR) parsing aims to translate sentences to semantic representation with a hierarchical structure, and is recently empowered by pretrained sequence-to-sequence models.

AMR Parsing Representation Learning

Incorporating Surprisingly Popular Algorithm and Euclidean Distance-based Adaptive Topology into PSO

no code implementations25 Aug 2021 Xuan Wu, Jizong Han, Di Wang, Pengyue Gao, Quanlong Cui, Liang Chen, Yanchun Liang, Han Huang, Heow Pueh Lee, Chunyan Miao, You Zhou, Chunguo Wu

While many Particle Swarm Optimization (PSO) algorithms only use fitness to assess the performance of particles, in this work, we adopt Surprisingly Popular Algorithm (SPA) as a complementary metric in addition to fitness.

DGCN: Diversified Recommendation with Graph Convolutional Networks

2 code implementations16 Aug 2021 Yu Zheng, Chen Gao, Liang Chen, Depeng Jin, Yong Li

These years much effort has been devoted to improving the accuracy or relevance of the recommendation system.

Collaborative Filtering

Understanding Structural Vulnerability in Graph Convolutional Networks

1 code implementation13 Aug 2021 Liang Chen, Jintang Li, Qibiao Peng, Yang Liu, Zibin Zheng, Carl Yang

In this work, we theoretically and empirically demonstrate that structural adversarial examples can be attributed to the non-robust aggregation scheme (i. e., the weighted mean) of GCNs.

Neighborhood Consensus Contrastive Learning for Backward-Compatible Representation

no code implementations7 Aug 2021 Shengsen Wu, Liang Chen, Yihang Lou, Yan Bai, Tao Bai, Minghua Deng, Lingyu Duan

Therefore, backward-compatible representation is proposed to enable "new" features to be compared with "old" features directly, which means that the database is active when there are both "new" and "old" features in it.

Contrastive Learning

Physics-Enforced Modeling for Insertion Loss of Transmission Lines by Deep Neural Networks

no code implementations27 Jul 2021 Liang Chen, Lesley Tan

In the second method, a third-order polynomial expression is defined first, which ensures positiveness, to approximate the insertion loss, then DeepONet neural network structure, which was proposed recently for function and system modeling, was employed to model the coefficients of polynomials.

Dynamic State Estimation for Integrated Natural Gas and Electric Power Systems

no code implementations13 Jul 2021 Liang Chen, Xinxin Hui, Songlin Gu, Manyun Huang, Yang Li

Boundary conditions of pipeline networks are used as supplementary constraints in the system model.

Learning a Non-Blind Deblurring Network for Night Blurry Images

no code implementations CVPR 2021 Liang Chen, Jiawei Zhang, Jinshan Pan, Songnan Lin, Faming Fang, Jimmy S. Ren

Deblurring night blurry images is difficult, because the common-used blur model based on the linear convolution operation does not hold in this situation due to the influence of saturated pixels.

Deblurring Image Restoration

Blind Deblurring for Saturated Images

no code implementations CVPR 2021 Liang Chen, Jiawei Zhang, Songnan Lin, Faming Fang, Jimmy S. Ren

To address this problem, we introduce a new blur model to fit both saturated and unsaturated pixels, and all informative pixels can be considered during deblurring process.


DNA-GCN: Graph convolutional networks for predicting DNA-protein binding

1 code implementation2 Jun 2021 Yuhang Guo, Xiao Luo, Liang Chen, Minghua Deng

Predicting DNA-protein binding is an important and classic problem in bioinformatics.


Signal Acquisition of Luojia-1A Low Earth Orbit Navigation Augmentation System with Software Defined Receiver

no code implementations31 May 2021 Liang Chen, Xiangchen Lu, Nan Shen, Lei Wang, Yuan Zhuang, Ye Su, Deren Li, Ruizhi Chen

The performance of those integration algorithms on expanding the successful acquisition time range is verified by the real data collected from the Luojia-1A satellite.

AutoDebias: Learning to Debias for Recommendation

1 code implementation10 May 2021 Jiawei Chen, Hande Dong, Yang Qiu, Xiangnan He, Xin Xin, Liang Chen, Guli Lin, Keping Yang

This provides a valuable opportunity to develop a universal solution for debiasing, e. g., by learning the debiasing parameters from data.

Imputation Meta-Learning +1

Personalized Bundle Recommendation in Online Games

no code implementations12 Apr 2021 Qilin Deng, Kai Wang, Minghao Zhao, Zhene Zou, Runze Wu, Jianrong Tao, Changjie Fan, Liang Chen

In business domains, \textit{bundling} is one of the most important marketing strategies to conduct product promotions, which is commonly used in online e-commerce and offline retailers.

Link Prediction Marketing +1

Reinforcement Learning with a Disentangled Universal Value Function for Item Recommendation

no code implementations7 Apr 2021 Kai Wang, Zhene Zou, Qilin Deng, Runze Wu, Jianrong Tao, Changjie Fan, Liang Chen, Peng Cui

As a part of the value function, free from the sparse and high-variance reward signals, a high-capacity reward-independent world model is trained to simulate complex environmental dynamics under a certain goal.

Model-based Reinforcement Learning Recommendation Systems +2

Neural Architecture Search based on Cartesian Genetic Programming Coding Method

no code implementations12 Mar 2021 Xuan Wu, Linhan Jia, Xiuyi Zhang, Liang Chen, Yanchun Liang, You Zhou, Chunguo Wu

To evolve the architectures under the framework of CGP, the operations such as convolution are identified as the types of function nodes of CGP, and the evolutionary operations are designed based on Evolutionary Strategy.

BIG-bench Machine Learning Neural Architecture Search +1

Robust Kalman filter-based dynamic state estimation of natural gas pipeline networks

no code implementations26 Feb 2021 Liang Chen, Peng Jin, Jing Yang, Yang Li, Yi Song

To obtain the accurate transient states of the big scale natural gas pipeline networks under the bad data and non-zero mean noises conditions, a robust Kalman filter-based dynamic state estimation method is proposed using the linearized gas pipeline transient flow equations in this paper.

A High-dimensional Sparse Fourier Transform in the Continuous Setting

no code implementations22 Feb 2021 Liang Chen

In this paper, we theoretically propose a new hashing scheme to establish the sparse Fourier transform in high-dimensional space.

Data Structures and Algorithms Information Theory Numerical Analysis Information Theory Numerical Analysis 41A63 G.1.2; F.2.1

GraphGallery: A Platform for Fast Benchmarking and Easy Development of Graph Neural Networks Based Intelligent Software

1 code implementation16 Feb 2021 Jintang Li, Kun Xu, Liang Chen, Zibin Zheng, Xiao Liu

Graph Neural Networks (GNNs) have recently shown to be powerful tools for representing and analyzing graph data.


Material absorption-based carrier generation model for modeling optoelectronic devices

no code implementations12 Feb 2021 Liang Chen, Hakan Bagci

The generation rate of photocarriers in optoelectronic materials is commonly calculated using the Poynting vector in the frequency domain.

Optics Computational Engineering, Finance, and Science Computational Physics

A possible blazar spectral irregularity case caused by photon--axionlike-particle oscillations

no code implementations11 Feb 2021 Jianeng Zhou, Zhongxiang Wang, Feng Huang, Liang Chen

We investigate this possibility by fitting the spectrum with the photon-ALP oscillation model, and find that the parameter space of ALP mass $m_a\leq 10^{-8}$\, eV and the coupling constant (between photons and ALPs) $g_{a\gamma}$=1. 16--1. 48$\times 10^{-10}$\, GeV$^{-1}$ can provide a fit to the line-like feature, while the magnetic field at the emission site of $\gamma$-rays is fixed at 0. 7\, G.

High Energy Astrophysical Phenomena

Lower Bound on the Optimal Access Bandwidth of ($K+2,K,2$)-MDS Array Code with Degraded Read Friendly

no code implementations4 Feb 2021 Ting-Yi Wu, Yunghsiang S. Han, Zhengrui Li, Bo Bai, Gong Zhang, Liang Chen, Xiang Wu

Accessing the data in the failed disk (degraded read) with low latency is crucial for an erasure-coded storage system.

Information Theory Information Theory

Matching Function Equilibria with Partial Assignment: Existence, Uniqueness and Estimation

no code implementations3 Feb 2021 Liang Chen, Eugene Choo, Alfred Galichon, Simon Weber

We argue that models coming from a variety of fields, such as matching models and discrete choice models among others, share a common structure that we call matching function equilibria with partial assignment.


Deep Reinforcement Learning with Spatio-temporal Traffic Forecasting for Data-Driven Base Station Sleep Control

no code implementations21 Jan 2021 Qiong Wu, Xu Chen, Zhi Zhou, Liang Chen, Junshan Zhang

To meet the ever increasing mobile traffic demand in 5G era, base stations (BSs) have been densely deployed in radio access networks (RANs) to increase the network coverage and capacity.

Decoding PPP Corrections from BDS B2b Signals Using a Software-defined Receiver: an Initial Performance Evaluation

no code implementations27 Nov 2020 Xiangchen Lu, Liang Chen, Nan Shen, Lei Wang, Zhenhang Jiao, Ruizhi Chen

With the rapid development of China's BeiDou Navigation Satellite System(BDS), the application of real-time precise point positioning (RTPPP) based on BDS has become an active research area in the field of Global Navigation Satellite System (GNSS).

Learning to Sample the Most Useful Training Patches from Images

no code implementations24 Nov 2020 Shuyang Sun, Liang Chen, Gregory Slabaugh, Philip Torr

Some image restoration tasks like demosaicing require difficult training samples to learn effective models.


Ensemble Knowledge Distillation for CTR Prediction

no code implementations8 Nov 2020 Jieming Zhu, Jinyang Liu, Weiqi Li, Jincai Lai, Xiuqiang He, Liang Chen, Zibin Zheng

Recently, deep learning-based models have been widely studied for click-through rate (CTR) prediction and lead to improved prediction accuracy in many industrial applications.

Click-Through Rate Prediction Knowledge Distillation

GAIN: Graph Attention & Interaction Network for Inductive Semi-Supervised Learning over Large-scale Graphs

no code implementations3 Nov 2020 Yunpeng Weng, Xu Chen, Liang Chen, Wei Liu

Most existing GNN models exploit a single type of aggregator (e. g., mean-pooling) to aggregate neighboring nodes information, and then add or concatenate the output of aggregator to the current representation vector of the center node.

Graph Attention Link Prediction +1

Self-supervised Graph Learning for Recommendation

2 code implementations21 Oct 2020 Jiancan Wu, Xiang Wang, Fuli Feng, Xiangnan He, Liang Chen, Jianxun Lian, Xing Xie

In this work, we explore self-supervised learning on user-item graph, so as to improve the accuracy and robustness of GCNs for recommendation.

Graph Learning Representation Learning +1

Stochastic Time-Periodic Tonelli Lagrangian on Compact Manifold

no code implementations21 Sep 2020 Liang Chen

In this paper, we study a class of time-periodic stochastic Tonelli Lagrangians on compact manifolds.

Dynamical Systems

Adversarial Attack on Large Scale Graph

1 code implementation8 Sep 2020 Jintang Li, Tao Xie, Liang Chen, Fenfang Xie, Xiangnan He, Zibin Zheng

Currently, most works on attacking GNNs are mainly using gradient information to guide the attack and achieve outstanding performance.

Adversarial Attack

Variance-reduced Language Pretraining via a Mask Proposal Network

no code implementations12 Aug 2020 Liang Chen

In particular, we first propose a principled gradient variance decomposition theorem, which shows that the variance of the stochastic gradient of the language pretraining can be naturally decomposed into two terms: the variance that arises from the sample of data in a batch, and the variance that arises from the sampling of the mask.

Self-Supervised Learning

Interactive Path Reasoning on Graph for Conversational Recommendation

no code implementations1 Jul 2020 Wenqiang Lei, Gangyi Zhang, Xiangnan He, Yisong Miao, Xiang Wang, Liang Chen, Tat-Seng Chua

Traditional recommendation systems estimate user preference on items from past interaction history, thus suffering from the limitations of obtaining fine-grained and dynamic user preference.

Recommendation Systems

Realistic Adversarial Data Augmentation for MR Image Segmentation

1 code implementation23 Jun 2020 Chen Chen, Chen Qin, Huaqi Qiu, Cheng Ouyang, Shuo Wang, Liang Chen, Giacomo Tarroni, Wenjia Bai, Daniel Rueckert

In this work, we propose an adversarial data augmentation method for training neural networks for medical image segmentation.

Data Augmentation Image Segmentation +3

Crossed-Time Delay Neural Network for Speaker Recognition

2 code implementations31 May 2020 Liang Chen, Yanchun Liang, Xiaohu Shi, You Zhou, Chunguo Wu

Time Delay Neural Network (TDNN) is a well-performing structure for DNN-based speaker recognition systems.

Speaker Recognition Speaker Verification

Secure Deep Graph Generation with Link Differential Privacy

1 code implementation1 May 2020 Carl Yang, Haonan Wang, Ke Zhang, Liang Chen, Lichao Sun

Many data mining and analytical tasks rely on the abstraction of networks (graphs) to summarize relational structures among individuals (nodes).

Graph Generation Link Prediction

Modelling High-Order Social Relations for Item Recommendation

no code implementations23 Mar 2020 Yang Liu, Liang Chen, Xiangnan He, Jiaying Peng, Zibin Zheng, Jie Tang

The prevalence of online social network makes it compulsory to study how social relations affect user choice.

Vocal Bursts Intensity Prediction

A Survey of Adversarial Learning on Graphs

2 code implementations10 Mar 2020 Liang Chen, Jintang Li, Jiaying Peng, Tao Xie, Zengxu Cao, Kun Xu, Xiangnan He, Zibin Zheng, Bingzhe Wu

To bridge this gap, we investigate and summarize the existing works on graph adversarial learning tasks systemically.

Clustering Graph Clustering +2

DeepCP: Deep Learning Driven Cascade Prediction Based Autonomous Content Placement in Closed Social Network

no code implementations9 Mar 2020 Qiong Wu, Muhong Wu, Xu Chen, Zhi Zhou, Kaiwen He, Liang Chen

Accordingly, we further propose a novel autonomous content placement mechanism CP-GAN which adopts the generative adversarial network (GAN) for agile placement decision making to reduce the content access latency and enhance users' QoE.

Decision Making

Data Poisoning Attacks on Neighborhood-based Recommender Systems

no code implementations1 Dec 2019 Liang Chen, Yangjun Xu, Fenfang Xie, Min Huang, Zibin Zheng

2) the fake users can be transferred to attack the state-of-the-art collaborative filtering recommender systems such as Neural Collaborative Filtering and Bayesian Personalized Ranking Matrix Factorization.

Collaborative Filtering Data Poisoning +1

The Intrinsic Properties of Brain Based on the Network Structure

no code implementations2 Nov 2019 Xiang Zou, Lie Yao, Donghua Zhao, Liang Chen, Ying Mao

The dynamic of the equation set can be described by some basic equations, which is based on the mathematical derivation.

Decision Making

Selecting Reliable Blockchain Peers via Hybrid Blockchain Reliability Prediction

1 code implementation31 Oct 2019 PeiLin Zheng, Zibin Zheng, Liang Chen

Blockchain and blockchain-based decentralized applications are attracting increasing attentions recently.

Software Engineering Distributed, Parallel, and Cluster Computing

Intelligent image synthesis to attack a segmentation CNN using adversarial learning

no code implementations24 Sep 2019 Liang Chen, Paul Bentley, Kensaku MORI, Kazunari Misawa, Michitaka Fujiwara, Daniel Rueckert

Our approach has three key features: 1) The generated adversarial examples exhibit anatomical variations (in form of deformations) as well as appearance perturbations; 2) The adversarial examples attack segmentation models so that the Dice scores decrease by a pre-specified amount; 3) The attack is not required to be specified beforehand.

Image Generation Image Segmentation +3

A New CGAN Technique for Constrained Topology Design Optimization

no code implementations22 Jan 2019 M. -H. Herman Shen, Liang Chen

This paper presents a new conditional GAN (named convex relaxing CGAN or crCGAN) to replicate the conventional constrained topology optimization algorithms in an extremely effective and efficient process.

Learning Semantic Representations for Unsupervised Domain Adaptation

1 code implementation ICML 2018 Shaoan Xie, Zibin Zheng, Liang Chen, Chuan Chen

Prior domain adaptation methods address this problem through aligning the global distribution statistics between source domain and target domain, but a drawback of prior methods is that they ignore the semantic information contained in samples, e. g., features of backpacks in target domain might be mapped near features of cars in source domain.

Learning Semantic Representations Unsupervised Domain Adaptation

Attention-Gated Networks for Improving Ultrasound Scan Plane Detection

6 code implementations15 Apr 2018 Jo Schlemper, Ozan Oktay, Liang Chen, Jacqueline Matthew, Caroline Knight, Bernhard Kainz, Ben Glocker, Daniel Rueckert

We show that, when the base network has a high capacity, the incorporated attention mechanism can provide efficient object localisation while improving the overall performance.

Object Recognition Based on Amounts of Unlabeled Data

no code implementations25 Mar 2016 Fuqiang Liu, Fukun Bi, Liang Chen

Using 2% labeled data and 98% unlabeled data, the accuracies of the proposed method on the two data sets are 78. 39% and 50. 77% respectively.

Object Recognition

Boost Picking: A Universal Method on Converting Supervised Classification to Semi-supervised Classification

no code implementations18 Feb 2016 Fuqiang Liu, Fukun Bi, Yiding Yang, Liang Chen

It is theoretically proved that Boost Picking could train a supervised model mainly by un-labeled data as effectively as the same model trained by 100% labeled data, only if recalls of the two weak classifiers are all greater than zero and the sum of precisions is greater than one.

Classification General Classification +1

Feature-Area Optimization: A Novel SAR Image Registration Method

no code implementations18 Feb 2016 Fuqiang Liu, Fukun Bi, Liang Chen, Hao Shi, Wei Liu

This letter proposes a synthetic aperture radar (SAR) image registration method named Feature-Area Optimization (FAO).

Image Registration

Dual Linear Regression Based Classification for Face Cluster Recognition

no code implementations CVPR 2014 Liang Chen

Considering that the image vectors of each subject, either in gallery or in probe, span a subspace; an algorithm, Dual Linear Regression Classification (DLRC), for the face cluster recognition problem is developed where the distance between two subspaces is defined as the similarity value between a gallery subject and a probe subject.

Classification General Classification +1

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