Search Results for author: Wei Yuan

Found 35 papers, 9 papers with code

PTF-FSR: A Parameter Transmission-Free Federated Sequential Recommender System

no code implementations8 Jun 2024 Wei Yuan, Chaoqun Yang, Liang Qu, Quoc Viet Hung Nguyen, Guanhua Ye, Hongzhi Yin

Recently, due to increasing concerns about user data privacy, some researchers have implemented federated learning for sequential recommendation, a. k. a., Federated Sequential Recommender Systems (FedSeqRecs), in which a public sequential recommender model is shared and frequently transmitted between a central server and clients to achieve collaborative learning.

Federated Learning Language Modelling +2

Markov chain Monte Carlo without evaluating the target: an auxiliary variable approach

1 code implementation7 Jun 2024 Wei Yuan, Guanyang Wang

In sampling tasks, it is common for target distributions to be known up to a normalising constant.

Poisoning Attacks and Defenses in Recommender Systems: A Survey

1 code implementation3 Jun 2024 Zongwei Wang, Junliang Yu, Min Gao, Wei Yuan, Guanhua Ye, Shazia Sadiq, Hongzhi Yin

Modern recommender systems (RS) have profoundly enhanced user experience across digital platforms, yet they face significant threats from poisoning attacks.

Recommendation Systems

Vector-Symbolic Architecture for Event-Based Optical Flow

no code implementations14 May 2024 Hongzhi You, Yijun Cao, Wei Yuan, Fanjun Wang, Ning Qiao, YongJie Li

Based on this HD feature descriptor, we propose a novel feature matching framework for event-based optical flow, encompassing both model-based (VSA-Flow) and self-supervised learning (VSA-SM) methods.

Event-based Optical Flow Optical Flow Estimation +1

Automated Similarity Metric Generation for Recommendation

no code implementations18 Apr 2024 Liang Qu, Yun Lin, Wei Yuan, Xiaojun Wan, Yuhui Shi, Hongzhi Yin

Given the critical role of similarity metrics in recommender systems, existing methods mainly employ handcrafted similarity metrics to capture the complex characteristics of user-item interactions.

Recommendation Systems

Robust Federated Contrastive Recommender System against Model Poisoning Attack

no code implementations29 Mar 2024 Wei Yuan, Chaoqun Yang, Liang Qu, Guanhua Ye, Quoc Viet Hung Nguyen, Hongzhi Yin

In this paper, we introduce a novel contrastive learning framework designed to fully leverage the client's sparse data through embedding augmentation, referred to as CL4FedRec.

Contrastive Learning Model Poisoning +2

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 Graph Neural Network +1

On-Device Recommender Systems: A Comprehensive Survey

no code implementations21 Jan 2024 Hongzhi Yin, Liang Qu, Tong Chen, Wei Yuan, Ruiqi Zheng, Jing Long, Xin Xia, Yuhui Shi, Chengqi Zhang

Recently, driven by the advances in storage, communication, and computation capabilities of edge devices, there has been a shift of focus from CloudRSs to on-device recommender systems (DeviceRSs), which leverage the capabilities of edge devices to minimize centralized data storage requirements, reduce the response latency caused by communication overheads, and enhance user privacy and security by localizing data processing and model training.

Recommendation Systems

ROIC-DM: Robust Text Inference and Classification via Diffusion Model

no code implementations7 Jan 2024 Shilong Yuan, Wei Yuan, Hongzhi Yin, Tieke He

While language models have made many milestones in text inference and classification tasks, they remain susceptible to adversarial attacks that can lead to unforeseen outcomes.

Denoising

Adversarial Item Promotion on Visually-Aware Recommender Systems by Guided Diffusion

no code implementations25 Dec 2023 Lijian Chen, Wei Yuan, Tong Chen, Guanhua Ye, Quoc Viet Hung Nguyen, Hongzhi Yin

Visually-aware recommender systems have found widespread application in domains where visual elements significantly contribute to the inference of users' potential preferences.

Recommendation Systems

Hide Your Model: A Parameter Transmission-free Federated Recommender System

1 code implementation25 Nov 2023 Wei Yuan, Chaoqun Yang, Liang Qu, Quoc Viet Hung Nguyen, JianXin Li, Hongzhi Yin

Existing FedRecs generally adhere to a learning protocol in which a central server shares a global recommendation model with clients, and participants achieve collaborative learning by frequently communicating the model's public parameters.

Privacy Preserving Recommendation Systems

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

Hybrid Feature Embedding For Automatic Building Outline Extraction

no code implementations20 Jul 2023 Weihang Ran, Wei Yuan, Xiaodan Shi, Zipei Fan, Ryosuke Shibasaki

Building outline extracted from high-resolution aerial images can be used in various application fields such as change detection and disaster assessment.

Change Detection Decoder

Manipulating Visually-aware Federated Recommender Systems and Its Countermeasures

no code implementations14 May 2023 Wei Yuan, Shilong Yuan, Chaoqun Yang, Quoc Viet Hung Nguyen, Hongzhi Yin

Therefore, when incorporating visual information in FedRecs, all existing model poisoning attacks' effectiveness becomes questionable.

Collaborative Filtering Model Poisoning +2

KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment

1 code implementation11 May 2023 Lingzhi Wang, Tong Chen, Wei Yuan, Xingshan Zeng, Kam-Fai Wong, Hongzhi Yin

Recent legislation of the "right to be forgotten" has led to the interest in machine unlearning, where the learned models are endowed with the function to forget information about specific training instances as if they have never existed in the training set.

Machine Unlearning Response Generation

Privacy-preserving Adversarial Facial Features

no code implementations CVPR 2023 Zhibo Wang, He Wang, Shuaifan Jin, Wenwen Zhang, Jiahui Hu, Yan Wang, Peng Sun, Wei Yuan, Kaixin Liu, Kui Ren

In this paper, we propose an adversarial features-based face privacy protection (AdvFace) approach to generate privacy-preserving adversarial features, which can disrupt the mapping from adversarial features to facial images to defend against reconstruction attacks.

Face Recognition Privacy Preserving

Joint Semantic and Structural Representation Learning for Enhancing User Preference Modelling

no code implementations24 Apr 2023 Xuhui Ren, Wei Yuan, Tong Chen, Chaoqun Yang, Quoc Viet Hung Nguyen, Hongzhi Yin

Knowledge graphs (KGs) have become important auxiliary information for helping recommender systems obtain a good understanding of user preferences.

Knowledge Graphs Language Modelling +2

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

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

Federated Unlearning for On-Device Recommendation

no code implementations20 Oct 2022 Wei Yuan, Hongzhi Yin, Fangzhao Wu, Shijie Zhang, Tieke He, Hao Wang

It removes a user's contribution by rolling back and calibrating the historical parameter updates and then uses these updates to speed up federated recommender reconstruction.

Recommendation Systems

Hardware Acceleration of Sampling Algorithms in Sample and Aggregate Graph Neural Networks

no code implementations7 Sep 2022 Yuchen Gui, Boyi Wei, Wei Yuan, Xi Jin

Sampling is an important process in many GNN structures in order to train larger datasets with a smaller computational complexity.

Online Trajectory Prediction for Metropolitan Scale Mobility Digital Twin

no code implementations21 Jun 2022 Zipei Fan, Xiaojie Yang, Wei Yuan, Renhe Jiang, Quanjun Chen, Xuan Song, Ryosuke Shibasaki

In the first stage, to encode the daily variation of human mobility at a metropolitan level, we automatically extract citywide mobility trends as crowd contexts and predict long-term and long-distance movements at a coarse level.

Retrieval Trajectory Prediction

Comprehensive Privacy Analysis on Federated Recommender System against Attribute Inference Attacks

no code implementations24 May 2022 Shijie Zhang, Wei Yuan, Hongzhi Yin

In this paper, we first design a novel attribute inference attacker to perform a comprehensive privacy analysis of the state-of-the-art federated recommender models.

Attribute Inference Attack +2

CSCNet: Contextual Semantic Consistency Network for Trajectory Prediction in Crowded Spaces

no code implementations17 Feb 2022 Beihao Xia, Conghao Wong, Qinmu Peng, Wei Yuan, Xinge You

The current methods are dedicated to studying the agents' future trajectories under the social interaction and the sceneries' physical constraints.

Autonomous Driving Trajectory Prediction

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

MSN: Multi-Style Network for Trajectory Prediction

1 code implementation2 Jul 2021 Conghao Wong, Beihao Xia, Qinmu Peng, Wei Yuan, Xinge You

Then, we assume that the target agents may plan their future behaviors according to each of these categorized styles, thus utilizing different style channels to make predictions with significant style differences in parallel.

Robot Navigation Self-Driving Cars +1

CAT: Cross Attention in Vision Transformer

1 code implementation10 Jun 2021 Hezheng Lin, Xing Cheng, Xiangyu Wu, Fan Yang, Dong Shen, Zhongyuan Wang, Qing Song, Wei Yuan

In this paper, we propose a new attention mechanism in Transformer termed Cross Attention, which alternates attention inner the image patch instead of the whole image to capture local information and apply attention between image patches which are divided from single-channel feature maps capture global information.

Deformations of Q-curvature II

no code implementations11 Feb 2021 Yueh-Ju Lin, Wei Yuan

This is the second article of a sequence of research on deformations of Q-curvature.

Differential Geometry

EAdam Optimizer: How $ε$ Impact Adam

2 code implementations4 Nov 2020 Wei Yuan, Kai-Xin Gao

Recently, many variants of Adam, such as Adabound, RAdam and Adabelief, have been proposed and show better performance than Adam.

Kernelized Similarity Learning and Embedding for Dynamic Texture Synthesis

1 code implementation11 Nov 2019 Shiming Chen, Peng Zhang, Guo-Sen Xie, Qinmu Peng, Zehong Cao, Wei Yuan, Xinge You

Dynamic texture (DT) exhibits statistical stationarity in the spatial domain and stochastic repetitiveness in the temporal dimension, indicating that different frames of DT possess a high similarity correlation that is critical prior knowledge.

Texture Synthesis

Semantic Segmentation for Urban Planning Maps based on U-Net

no code implementations28 Sep 2018 Zhiling Guo, Hiroaki Shengoku, Guangming Wu, Qi Chen, Wei Yuan, Xiaodan Shi, Xiaowei Shao, Yongwei Xu, Ryosuke Shibasaki

The results indicate the proposed method can serve as a viable tool for urban planning map semantic segmentation task with high accuracy and efficiency.

Segmentation Semantic Segmentation

Multi-view Common Component Discriminant Analysis for Cross-view Classification

no code implementations14 May 2018 Xinge You, Jiamiao Xu, Wei Yuan, Xiao-Yuan Jing, DaCheng Tao, Taiping Zhang

Cross-view classification that means to classify samples from heterogeneous views is a significant yet challenging problem in computer vision.

General Classification

Sparse multi-view matrix factorisation: a multivariate approach to multiple tissue comparisons

no code implementations4 Mar 2015 Zi Wang, Wei Yuan, Giovanni Montana

The proposed methodology can be interpreted as an extension of principal component analysis in that it provides the means to decompose the total sample variance in each tissue into the sum of two components: one capturing the variance that is shared across tissues, and one isolating the tissue-specific variances.

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