Differentially Private and Heterogeneity-Robust Federated Learning With Theoretical Guarantee

Xiuhua Wang;Shuai Wang;Yiwei Li;Fengrui Fan;Shikang Li;Xiaodong Lin
{"title":"Differentially Private and Heterogeneity-Robust Federated Learning With Theoretical Guarantee","authors":"Xiuhua Wang;Shuai Wang;Yiwei Li;Fengrui Fan;Shikang Li;Xiaodong Lin","doi":"10.1109/TAI.2024.3446759","DOIUrl":null,"url":null,"abstract":"Federated learning (FL) is a popular distributed paradigm where enormous clients collaboratively train a machine learning (ML) model under the orchestration of a central server without knowing the clients’ private raw data. The development of effective FL algorithms faces multiple practical challenges including data heterogeneity and clients’ privacy protection. Despite that numerous attempts have been made to deal with data heterogeneity or rigorous privacy protection, none have effectively tackled both issues simultaneously. In this article, we propose a differentially private and heterogeneity-robust FL algorithm, named \n<monospace>DP-FedCVR</monospace>\n to mitigate the data heterogeneity by following the client-variance-reduction strategy. Besides, it adopts a sophisticated differential privacy (DP) mechanism where the privacy-amplified strategy is applied, to achieve a rigorous privacy protection guarantee. We show that the proposed \n<monospace>DP-FedCVR</monospace>\n algorithm maintains its heterogeneity-robustness though DP noises are incorporated, while achieving a sublinear convergence rate for a nonconvex FL problem. Numerical experiments based on image classification tasks are presented to demonstrate that \n<monospace>DP-FedCVR</monospace>\n provides superior performance over the benchmark algorithms in the presence of data heterogeneity and various DP privacy budgets.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 12","pages":"6369-6384"},"PeriodicalIF":0.0000,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on artificial intelligence","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10643038/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Federated learning (FL) is a popular distributed paradigm where enormous clients collaboratively train a machine learning (ML) model under the orchestration of a central server without knowing the clients’ private raw data. The development of effective FL algorithms faces multiple practical challenges including data heterogeneity and clients’ privacy protection. Despite that numerous attempts have been made to deal with data heterogeneity or rigorous privacy protection, none have effectively tackled both issues simultaneously. In this article, we propose a differentially private and heterogeneity-robust FL algorithm, named DP-FedCVR to mitigate the data heterogeneity by following the client-variance-reduction strategy. Besides, it adopts a sophisticated differential privacy (DP) mechanism where the privacy-amplified strategy is applied, to achieve a rigorous privacy protection guarantee. We show that the proposed DP-FedCVR algorithm maintains its heterogeneity-robustness though DP noises are incorporated, while achieving a sublinear convergence rate for a nonconvex FL problem. Numerical experiments based on image classification tasks are presented to demonstrate that DP-FedCVR provides superior performance over the benchmark algorithms in the presence of data heterogeneity and various DP privacy budgets.
具有理论保证的差分私有和异构鲁棒联邦学习
联邦学习(FL)是一种流行的分布式范例,其中大量客户端在中央服务器的编排下协作训练机器学习(ML)模型,而无需知道客户端的私有原始数据。开发有效的FL算法面临着数据异构和客户端隐私保护等诸多现实挑战。尽管在处理数据异构或严格的隐私保护方面已经做了许多尝试,但没有一个能同时有效地解决这两个问题。在本文中,我们提出了一种不同的私有和异构鲁棒的FL算法,命名为DP-FedCVR,通过遵循客户端方差减少策略来减轻数据异质性。并采用了复杂的差分隐私(DP)机制,采用了隐私放大策略,实现了严格的隐私保护保障。结果表明,本文提出的DP- fedcvr算法在引入DP噪声的情况下保持了其异质鲁棒性,同时对非凸FL问题达到了亚线性收敛速度。基于图像分类任务的数值实验表明,在数据异构和不同DP隐私预算的情况下,DP- fedcvr比基准算法具有更好的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
7.70
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信