Search Results for author: Lizhen Cui

Found 44 papers, 14 papers with code

Towards Personalized Privacy: User-Governed Data Contribution for Federated Recommendation

no code implementations31 Jan 2024 Liang Qu, Wei Yuan, Ruiqi Zheng, Lizhen Cui, Yuhui Shi, Hongzhi Yin

To bridge this gap, this paper explores a user-governed data contribution federated recommendation architecture where users are free to take control of whether they share data and the proportion of data they share to the server.

Contrastive Learning Recommendation Systems

Decentralized Collaborative Learning with Adaptive Reference Data for On-Device POI Recommendation

no code implementations24 Jan 2024 Ruiqi Zheng, Liang Qu, Tong Chen, Lizhen Cui, Yuhui Shi, Hongzhi Yin

Collaborative Learning (CL) emerges to promote model sharing among users, where reference data is an intermediary that allows users to exchange their soft decisions without directly sharing their private data or parameters, ensuring privacy and benefiting from collaboration.

Anchoring Path for Inductive Relation Prediction in Knowledge Graphs

1 code implementation21 Dec 2023 Zhixiang Su, Di Wang, Chunyan Miao, Lizhen Cui

To address this challenge, we propose Anchoring Path Sentence Transformer (APST) by introducing Anchoring Paths (APs) to alleviate the reliance of CPs.

Inductive Relation Prediction Knowledge Graphs +4

FedSSA: Semantic Similarity-based Aggregation for Efficient Model-Heterogeneous Personalized Federated Learning

no code implementations14 Dec 2023 Liping Yi, Han Yu, Zhuan Shi, Gang Wang, Xiaoguang Liu, Lizhen Cui, Xiaoxiao Li

To address these limitations, we propose the Federated Semantic Similarity Aggregation (FedSSA) approach, which splits each client's model into a heterogeneous (structure-different) feature extractor and a homogeneous (structure-same) classification header.

Computational Efficiency Personalized Federated Learning +4

A Critical Look at Classic Test-Time Adaptation Methods in Semantic Segmentation

no code implementations9 Oct 2023 Chang'an Yi, Haotian Chen, Yifan Zhang, Yonghui Xu, Lizhen Cui

This pronounced emphasis on classification might lead numerous newcomers and engineers to mistakenly assume that classic TTA methods designed for classification can be directly applied to segmentation.

Classification Segmentation +2

Unsupervised Representation Learning for Time Series: A Review

1 code implementation3 Aug 2023 Qianwen Meng, Hangwei Qian, Yong liu, Yonghui Xu, Zhiqi Shen, Lizhen Cui

However, there is a lack of systematic analysis of unsupervised representation learning approaches for time series.

Contrastive Learning Representation Learning +1

HeteFedRec: Federated Recommender Systems with Model Heterogeneity

no code implementations24 Jul 2023 Wei Yuan, Liang Qu, Lizhen Cui, Yongxin Tong, Xiaofang Zhou, Hongzhi Yin

Owing to the nature of privacy protection, federated recommender systems (FedRecs) have garnered increasing interest in the realm of on-device recommender systems.

Knowledge Distillation Recommendation Systems

Explicit Knowledge Graph Reasoning for Conversational Recommendation

no code implementations1 May 2023 Xuhui Ren, Tong Chen, Quoc Viet Hung Nguyen, Lizhen Cui, Zi Huang, Hongzhi Yin

Recent conversational recommender systems (CRSs) tackle those limitations by enabling recommender systems to interact with the user to obtain her/his current preference through a sequence of clarifying questions.

Attribute Recommendation Systems

Continuous Input Embedding Size Search For Recommender Systems

no code implementations7 Apr 2023 Yunke Qu, Tong Chen, Xiangyu Zhao, Lizhen Cui, Kai Zheng, Hongzhi Yin

Latent factor models are the most popular backbones for today's recommender systems owing to their prominent performance.

Recommendation Systems Reinforcement Learning (RL)

FedMAE: Federated Self-Supervised Learning with One-Block Masked Auto-Encoder

no code implementations20 Mar 2023 Nan Yang, Xuanyu Chen, Charles Z. Liu, Dong Yuan, Wei Bao, Lizhen Cui

Latest federated learning (FL) methods started to focus on how to use unlabeled data in clients for training due to users' privacy concerns, high labeling costs, or lack of expertise.

Federated Learning Image Reconstruction +1

Dual Graph Multitask Framework for Imbalanced Delivery Time Estimation

no code implementations15 Feb 2023 Lei Zhang, Mingliang Wang, Xin Zhou, Xingyu Wu, Yiming Cao, Yonghui Xu, Lizhen Cui, Zhiqi Shen

To address the issue, we propose a novel Dual Graph Multitask framework for imbalanced Delivery Time Estimation (DGM-DTE).

History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue System

no code implementations2 Feb 2023 Tong Zhang, Yong liu, Boyang Li, Zhiwei Zeng, Pengwei Wang, Yuan You, Chunyan Miao, Lizhen Cui

HAHT maintains a long-term memory of history conversations and utilizes history information to understand current conversation context and generate well-informed and context-relevant responses.

Interaction-level Membership Inference Attack Against Federated Recommender Systems

no code implementations26 Jan 2023 Wei Yuan, Chaoqun Yang, Quoc Viet Hung Nguyen, Lizhen Cui, Tieke He, Hongzhi Yin

An interaction-level membership inference attacker is first designed, and then the classical privacy protection mechanism, Local Differential Privacy (LDP), is adopted to defend against the membership inference attack.

Attribute Federated Learning +3

Multi-Aspect Explainable Inductive Relation Prediction by Sentence Transformer

1 code implementation4 Jan 2023 Zhixiang Su, Di Wang, Chunyan Miao, Lizhen Cui

Recent studies on knowledge graphs (KGs) show that path-based methods empowered by pre-trained language models perform well in the provision of inductive and explainable relation predictions.

Inductive Relation Prediction Knowledge Graphs +3

Towards AI-Empowered Crowdsourcing

no code implementations28 Dec 2022 Shipeng Wang, Qingzhong Li, Lizhen Cui, Zhongmin Yan, Yonghui Xu, Zhuan Shi, Xinping Min, Zhiqi Shen, Han Yu

Crowdsourcing, in which human intelligence and productivity is dynamically mobilized to tackle tasks too complex for automation alone to handle, has grown to be an important research topic and inspired new businesses (e. g., Uber, Airbnb).

Management

MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time Series

1 code implementation2 Dec 2022 Qianwen Meng, Hangwei Qian, Yong liu, Lizhen Cui, Yonghui Xu, Zhiqi Shen

Learning semantic-rich representations from raw unlabeled time series data is critical for downstream tasks such as classification and forecasting.

Clustering Contrastive Learning +3

XSimGCL: Towards Extremely Simple Graph Contrastive Learning for Recommendation

1 code implementation6 Sep 2022 Junliang Yu, Xin Xia, Tong Chen, Lizhen Cui, Nguyen Quoc Viet Hung, Hongzhi Yin

Contrastive learning (CL) has recently been demonstrated critical in improving recommendation performance.

Contrastive Learning

Enhancing Sequential Recommendation with Graph Contrastive Learning

no code implementations30 May 2022 Yixin Zhang, Yong liu, Yonghui Xu, Hao Xiong, Chenyi Lei, wei he, Lizhen Cui, Chunyan Miao

Specifically, GCL4SR employs a Weighted Item Transition Graph (WITG), built based on interaction sequences of all users, to provide global context information for each interaction and weaken the noise information in the sequence data.

Auxiliary Learning Contrastive Learning +1

Unified Question Generation with Continual Lifelong Learning

no code implementations24 Jan 2022 Wei Yuan, Hongzhi Yin, Tieke He, Tong Chen, Qiufeng Wang, Lizhen Cui

To solve the problems, we propose a model named Unified-QG based on lifelong learning techniques, which can continually learn QG tasks across different datasets and formats.

Question Answering Question Generation +1

Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendation

1 code implementation16 Dec 2021 Junliang Yu, Hongzhi Yin, Xin Xia, Tong Chen, Lizhen Cui, Quoc Viet Hung Nguyen

Contrastive learning (CL) recently has spurred a fruitful line of research in the field of recommendation, since its ability to extract self-supervised signals from the raw data is well-aligned with recommender systems' needs for tackling the data sparsity issue.

Contrastive Learning Recommendation Systems

Open-Set Crowdsourcing using Multiple-Source Transfer Learning

no code implementations7 Nov 2021 Guangyang Han, Guoxian Yu, Lei Liu, Lizhen Cui, Carlotta Domeniconi, Xiangliang Zhang

First, OSCrowd integrates crowd theme related datasets into a large source domain to facilitate partial transfer learning to approximate the label space inference of these tasks.

Transfer Learning

Crowdsourcing with Meta-Workers: A New Way to Save the Budget

no code implementations7 Nov 2021 Guangyang Han, Guoxian Yu, Lizhen Cui, Carlotta Domeniconi, Xiangliang Zhang

Due to the unreliability of Internet workers, it's difficult to complete a crowdsourcing project satisfactorily, especially when the tasks are multiple and the budget is limited.

Few-Shot Learning Image Classification

Cross-modal Zero-shot Hashing by Label Attributes Embedding

no code implementations7 Nov 2021 Runmin Wang, Guoxian Yu, Lei Liu, Lizhen Cui, Carlotta Domeniconi, Xiangliang Zhang

Cross-modal hashing (CMH) is one of the most promising methods in cross-modal approximate nearest neighbor search.

Attribute

Major Depressive Disorder Recognition and Cognitive Analysis Based on Multi-layer Brain Functional Connectivity Networks

no code implementations2 Nov 2021 Xiaofang Sun, Xiangwei Zheng, Yonghui Xu, Lizhen Cui, Bin Hu

On the increase of major depressive disorders (MDD), many researchers paid attention to their recognition and treatment.

PipAttack: Poisoning Federated Recommender Systems forManipulating Item Promotion

no code implementations21 Oct 2021 Shijie Zhang, Hongzhi Yin, Tong Chen, Zi Huang, Quoc Viet Hung Nguyen, Lizhen Cui

Evaluations on two real-world datasets show that 1) our attack model significantly boosts the exposure rate of the target item in a stealthy way, without harming the accuracy of the poisoned recommender; and 2) existing defenses are not effective enough, highlighting the need for new defenses against our local model poisoning attacks to federated recommender systems.

Federated Learning Model Poisoning +1

GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated Learning

1 code implementation5 Sep 2021 Zelei Liu, YuanYuan Chen, Han Yu, Yang Liu, Lizhen Cui

In addition, we design a guided Monte Carlo sampling approach combined with within-round and between-round truncation to further reduce the number of model reconstructions and evaluations required, through extensive experiments under diverse realistic data distribution settings.

Computational Efficiency Federated Learning

Self-Supervised Graph Co-Training for Session-based Recommendation

2 code implementations24 Aug 2021 Xin Xia, Hongzhi Yin, Junliang Yu, Yingxia Shao, Lizhen Cui

In this paper, for informative session-based data augmentation, we combine self-supervised learning with co-training, and then develop a framework to enhance session-based recommendation.

Contrastive Learning Data Augmentation +2

Noise-Resistant Deep Metric Learning with Probabilistic Instance Filtering

no code implementations3 Aug 2021 Chang Liu, Han Yu, Boyang Li, Zhiqi Shen, Zhanning Gao, Peiran Ren, Xuansong Xie, Lizhen Cui, Chunyan Miao

Noisy labels are commonly found in real-world data, which cause performance degradation of deep neural networks.

Metric Learning

Few-Shot Partial-Label Learning

no code implementations2 Jun 2021 Yunfeng Zhao, Guoxian Yu, Lei Liu, Zhongmin Yan, Lizhen Cui, Carlotta Domeniconi

Partial-label learning (PLL) generally focuses on inducing a noise-tolerant multi-class classifier by training on overly-annotated samples, each of which is annotated with a set of labels, but only one is the valid label.

Few-Shot Learning Metric Learning +2

NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labels

1 code implementation31 May 2021 Jingfeng Zhang, Xilie Xu, Bo Han, Tongliang Liu, Gang Niu, Lizhen Cui, Masashi Sugiyama

First, we thoroughly investigate noisy labels (NLs) injection into AT's inner maximization and outer minimization, respectively and obtain the observations on when NL injection benefits AT.

Adversarial Robustness

Towards Personalized Federated Learning

no code implementations1 Mar 2021 Alysa Ziying Tan, Han Yu, Lizhen Cui, Qiang Yang

In parallel with the rapid adoption of Artificial Intelligence (AI) empowered by advances in AI research, there have been growing awareness and concerns of data privacy.

Benchmarking Personalized Federated Learning +1

Graph Embedding for Recommendation against Attribute Inference Attacks

no code implementations29 Jan 2021 Shijie Zhang, Hongzhi Yin, Tong Chen, Zi Huang, Lizhen Cui, Xiangliang Zhang

Specifically, in GERAI, we bind the information perturbation mechanism in differential privacy with the recommendation capability of graph convolutional networks.

Attribute Graph Embedding +2

FENet: A Frequency Extraction Network for Obstructive Sleep Apnea Detection

no code implementations8 Jan 2021 Guanhua Ye, Hongzhi Yin, Tong Chen, Hongxu Chen, Lizhen Cui, Xiangliang Zhang

Obstructive Sleep Apnea (OSA) is a highly prevalent but inconspicuous disease that seriously jeopardizes the health of human beings.

Sleep apnea detection

Self-Supervised Hypergraph Convolutional Networks for Session-based Recommendation

2 code implementations12 Dec 2020 Xin Xia, Hongzhi Yin, Junliang Yu, Qinyong Wang, Lizhen Cui, Xiangliang Zhang

Moreover, to enhance hypergraph modeling, we devise another graph convolutional network which is based on the line graph of the hypergraph and then integrate self-supervised learning into the training of the networks by maximizing mutual information between the session representations learned via the two networks, serving as an auxiliary task to improve the recommendation task.

Self-Supervised Learning Session-Based Recommendations

Commonsense knowledge adversarial dataset that challenges ELECTRA

no code implementations25 Oct 2020 Gongqi Lin, Yuan Miao, Xiaoyong Yang, Wenwu Ou, Lizhen Cui, Wei Guo, Chunyan Miao

To investigate machine comprehension models' ability in handling the commonsense knowledge, we created a Question and Answer Dataset with common knowledge of Synonyms (QADS).

Reading Comprehension Word Sense Disambiguation

GCN-Based User Representation Learning for Unifying Robust Recommendation and Fraudster Detection

1 code implementation20 May 2020 Shijie Zhang, Hongzhi Yin, Tong Chen, Quoc Viet Nguyen Hung, Zi Huang, Lizhen Cui

Therefore, it is of great practical significance to construct a robust recommender system that is able to generate stable recommendations even in the presence of shilling attacks.

Recommendation Systems Representation Learning

Enhancing Social Recommendation with Adversarial Graph Convolutional Networks

no code implementations5 Apr 2020 Junliang Yu, Hongzhi Yin, Jundong Li, Min Gao, Zi Huang, Lizhen Cui

Social recommender systems are expected to improve recommendation quality by incorporating social information when there is little user-item interaction data.

Recommendation Systems

Attacks Which Do Not Kill Training Make Adversarial Learning Stronger

1 code implementation ICML 2020 Jingfeng Zhang, Xilie Xu, Bo Han, Gang Niu, Lizhen Cui, Masashi Sugiyama, Mohan Kankanhalli

Adversarial training based on the minimax formulation is necessary for obtaining adversarial robustness of trained models.

Adversarial Robustness

Diversity-Promoting Deep Reinforcement Learning for Interactive Recommendation

no code implementations19 Mar 2019 Yong Liu, Yinan Zhang, Qiong Wu, Chunyan Miao, Lizhen Cui, Binqiang Zhao, Yin Zhao, Lu Guan

Interactive recommendation that models the explicit interactions between users and the recommender system has attracted a lot of research attentions in recent years.

Recommendation Systems reinforcement-learning +1

Ethically Aligned Opportunistic Scheduling for Productive Laziness

no code implementations2 Jan 2019 Han Yu, Chunyan Miao, Yongqing Zheng, Lizhen Cui, Simon Fauvel, Cyril Leung

In order to enable workforce management systems to follow the IEEE Ethically Aligned Design guidelines to prioritize worker wellbeing, we propose a distributed Computational Productive Laziness (CPL) approach in this paper.

Management Scheduling

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