Shuai Wang

University of Electronic Science and Technology of China

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Tony Q. S. Quek

Singapore University of Technology and Design

Yiwei Li

Xiamen University of Technology

Chong‐Yung Chi

National Tsing Hua University

Tsung‐Hui Chang

Chinese University of Hong Kong, Shenzhen

Yanqing Xu

Chinese University of Hong Kong, Shenzhen

Xiuhua Wang

University of Alberta

Chien‐Wei Huang

National Yang Ming Chiao Tung University

Yanli Yuan

Beijing Institute of Technology

Zhiguo Wang

Sichuan University

Defeng Sun

Naval Aeronautical and Astronautical University

Cooperative Institutions

Huazhong University of Science and Technology

National Tsing Hua University

Beijing Institute of Technology

University of Science and Technology Beijing

Chinese Academy of Sciences

Chinese University of Hong Kong, Shenzhen

Tsinghua University

University of Southern California

Yangzhou University

University of Manchester

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Privacy-preserving Federated Primal-dual Learning for Non-convex and Non-smooth Problems with Model Sparsification

arXiv (Cornell University) (2023)

Yiwei Li Chien‐Wei Huang Shuai Wang Chong‐Yung Chi Tony Q. S. Quek

Federated learning (FL) has been recognized as a rapidly growing research area, where the model is trained over massively distributed clients under the orchestration of a parameter server (PS) without sharing clients' data. This paper delves into a class of federated problems characterized by non-convex and non-smooth loss functions, that are prevalent in FL applications but challenging to handle due to their intricate non-convexity and non-smoothness nature and the conflicting requirements on communication efficiency and privacy protection. In this paper, we propose a novel federated primal-dual algorithm with bidirectional model sparsification tailored for non-convex and non-smooth FL problems, and differential privacy is applied for privacy guarantee. Its unique insightful properties and some privacy and convergence analyses are also presented as the FL algorithm design guidelines. Extensive experiments on real-world data are conducted to demonstrate the effectiveness of the proposed algorithm and much superior performance than some state-of-the-art FL algorithms, together with the validation of all the analytical results and properties.

Differential Privacy

Convexity

Smoothness

Federated Learning

Distributed learning

Orchestration

10.48550/arxiv.2310.19558

Cite

Citations (0)

Federated Matrix Factorization: Algorithm Design and Application to Data Clustering

IEEE Transactions on Signal Processing (2022)

Shuai Wang Tsung‐Hui Chang

Recent demands on data privacy have called for federated learning (FL) as a new distributed learning paradigm in massive and heterogeneous networks. Although many FL algorithms have been proposed, few of them have considered the matrix factorization (MF) model, which is known to have a vast number of signal processing and machine learning applications. Since the MF problem involves two blocks of variables and the variables are usually subject to constraints related to specific solution structure, it requires new FL algorithm designs to achieve communication-efficient MF in heterogeneous data networks. In this paper, we address the challenge by proposing two new federated MF (FedMF) algorithms, namely, FedMAvg and FedMGS, based on the model averaging and gradient sharing principles, respectively. Both FedMAvg and FedMGS adopt multiple steps of local updates per communication round to speed up convergence, and allow only a randomly sampled subset of clients to communicate with the server for reducing the communication cost. Convergence properties for the two algorithms are thoroughly analyzed, which delineate the impacts of heterogeneous data distribution, local update number, and partial client communication on the algorithm performance, and guide the design of proposed algorithms. By focusing on a data clustering task, extensive experiment results are presented to examine the practical performance of proposed algorithms, as well as demonstrating their efficacy over the existing distributed clustering algorithms.

Algorithm design

10.1109/tsp.2022.3151505

Cite

Citations (14)

Beyond ADMM: A Unified Client-variance-reduced Adaptive Federated Learning Framework

arXiv (Cornell University) (2022)

Shuai Wang Yanqing Xu Zhiguo Wang Tsung‐Hui Chang Tony Q. S. Quek

As a novel distributed learning paradigm, federated learning (FL) faces serious challenges in dealing with massive clients with heterogeneous data distribution and computation and communication resources. Various client-variance-reduction schemes and client sampling strategies have been respectively introduced to improve the robustness of FL. Among others, primal-dual algorithms such as the alternating direction of method multipliers (ADMM) have been found being resilient to data distribution and outperform most of the primal-only FL algorithms. However, the reason behind remains a mystery still. In this paper, we firstly reveal the fact that the federated ADMM is essentially a client-variance-reduced algorithm. While this explains the inherent robustness of federated ADMM, the vanilla version of it lacks the ability to be adaptive to the degree of client heterogeneity. Besides, the global model at the server under client sampling is biased which slows down the practical convergence. To go beyond ADMM, we propose a novel primal-dual FL algorithm, termed FedVRA, that allows one to adaptively control the variance-reduction level and biasness of the global model. In addition, FedVRA unifies several representative FL algorithms in the sense that they are either special instances of FedVRA or are close to it. Extensions of FedVRA to semi/un-supervised learning are also presented. Experiments based on (semi-)supervised image classification tasks demonstrate superiority of FedVRA over the existing schemes in learning scenarios with massive heterogeneous clients and client sampling.

Robustness

Variance reduction

10.48550/arxiv.2212.01519

Cite

Citations (1)

Convergence Analysis for Differentially Private Federated Averaging in Heterogeneous Settings

Mathematics (2025)

Yiwei Li Shuai Wang Q. M. Jonathan Wu

Federated learning (FL) has emerged as a prominent approach for distributed machine learning, enabling collaborative model training while preserving data privacy. However, the presence of non-i.i.d. data and the need for robust privacy protection introduce significant challenges in theoretically analyzing the performance of FL algorithms. In this paper, we present novel theoretical analysis on typical differentially private federated averaging (DP-FedAvg) by judiciously considering the impact of non-i.i.d. data on convergence and privacy guarantees. Our contributions are threefold: (i) We introduce a theoretical framework for analyzing the convergence of DP-FedAvg algorithm by considering different client sampling and data sampling strategies, privacy amplification and non-i.i.d. data. (ii) We explore the privacy–utility tradeoff and demonstrate how client strategies interact with differential privacy to affect learning performance. (iii) We provide extensive experimental validation using real-world datasets to verify our theoretical findings.

Differential Privacy

Federated Learning

Distributed learning

10.3390/math13030497

Cite

Citations (0)

Toward Fast Personalized Semi-Supervised Federated Learning in Edge Networks: Algorithm Design and Theoretical Guarantee

IEEE Transactions on Wireless Communications (2023)

Shuai Wang Yanqing Xu Yanli Yuan Tony Q. S. Quek

Recent years have witnessed a huge demand for artificial intelligence and machine learning applications in wireless edge networks to assist individuals with real-time services. Federated learning (FL) has emerged as a suitable and appealing distributed learning paradigm to deploy these applications at the network edge. Despite the many successful efforts made to apply FL to wireless edge networks, the adopted algorithms mostly follow the same spirit as FedAvg, thereby heavily suffering from the practical challenges of label deficiency and device heterogeneity. These challenges not only decelerate the model training in FL but also downgrade the application performance. In this paper, we focus on the algorithm design and address these challenges by investigating the personalized semi-supervised FL problem and proposing an effective algorithm, named FedCPSL. In particular, the techniques of pseudo-labeling, and interpolation-based model personalization are judiciously combined to provide a new problem formulation for personalized semi-supervised FL. The proposed FedCPSL algorithm employs novel strategies, including adaptive client variance reduction, local momentum, and normalized global aggregation, to combat the challenge of device heterogeneity and boost algorithm convergence. The convergence property of FedCPSL is also thoroughly analyzed and shows that FedCPSL is resilient to both statistical and system heterogeneity, obtaining a sublinear convergence rate. Experimental results on image classification tasks are presented to demonstrate that the proposed approach outperforms its counterparts in terms of both convergence speed and application performance.

Edge device

10.1109/twc.2023.3286990

Cite

Citations (7)

Privacy-Preserving Federated Primal-Dual Learning for Non-Convex and Non-Smooth Problems With Model Sparsification

IEEE Internet of Things Journal (2024)

Yiwei Li Chien‐Wei Huang Shuai Wang Chong‐Yung Chi Tony Q. S. Quek

10.1109/jiot.2024.3376552

Cite

Citations (0)

Experimental evidence for spinodal decomposition along with simultaneous ordering in Al-12.7 at% Li alloy

Materials Letters (1996)

Yang Wei Shuai Wang

Spinodal decomposition

Spinodal

10.1016/0167-577x(96)00042-0

Cite

Citations (5)

An Evaluation Model of Tuition Fee in Higher Education

International Journal of Education and Management Engineering (2012)

Dong Xin Deng Chang Cheng Shuai Wang Feng Ming

This paper surveys evaluation and pricing of tuition fee from two perspectives: society and school.We use the optimization theory in fuzzy mathematics and operations research to establish the evaluation model based on overall society and school satisfaction degree; Taking maximum overall Satisfaction degree as our goal and all factors of comprehensive tuition fee evaluation as the restriction, we establish the optimization model of tuition fee pricing to get the tuition standard in higher education.Then we classify disciplines according to the specific reality and calculate the grades and reference prices in disciplines of three schools in Guangdong Province, China.We further obtain the reference tuition fee in other provinces using the regional conversion coefficient.At last we give our directions for tuition fee pricing of higher education.

10.5815/ijeme.2012.12.01

Cite

Citations (0)

Attribute-Based Access Control Encryption

IEEE Transactions on Dependable and Secure Computing (2024)

Xiuhua Wang Mengyang Yu Yaohui Wang Yecan Pi Peng Xu

10.1109/tdsc.2024.3481497

Cite

Citations (1)

Differentially Private Federated Clustering Over Non-IID Data

IEEE Internet of Things Journal (2023)

Yiwei Li Shuai Wang Chong‐Yung Chi Tony Q. S. Quek

In this article, we investigate the federated clustering (FedC) problem, which aims to accurately partition unlabeled data samples distributed over massive clients into finite clusters under the orchestration of a parameter server (PS), meanwhile considering data privacy. Though it is an NP-hard optimization problem involving real variables denoting cluster centroids and binary variables denoting the cluster membership of each data sample, we judiciously reformulate the FedC problem into a nonconvex optimization problem with only one convex constraint, accordingly yielding a soft clustering solution. Then, a novel FedC algorithm using differential privacy (DP) technique, referred to as DP- FedC, is proposed in which partial clients participation (PCP) and multiple local model updating steps are also considered. Furthermore, various attributes of the proposed DP- FedC are obtained through theoretical analyses of privacy protection and convergence rate, especially for the case of nonidentically and independently distributed (non-i.i.d.) data, that ideally serve as the guidelines for the design of the proposed DP- FedC. Then, some experimental results on two real datasets are provided to demonstrate the efficacy of the proposed DP- FedC together with its much superior performance over some state-of-the-art FedC algorithms, and the consistency with all the presented analytical results.

10.1109/jiot.2023.3312852

Cite

Citations (10)