Byzantine-resilient decentralized network learning

Pub Date : 2024-01-10 DOI:10.1007/s42952-023-00249-w
Yaohong Yang, Lei Wang
{"title":"Byzantine-resilient decentralized network learning","authors":"Yaohong Yang, Lei Wang","doi":"10.1007/s42952-023-00249-w","DOIUrl":null,"url":null,"abstract":"<p>Decentralized federated learning based on fully normal nodes has drawn attention in modern statistical learning. However, due to data corruption, device malfunctioning, malicious attacks and some other unexpected behaviors, not all nodes can obey the estimation process and the existing decentralized federated learning methods may fail. An unknown number of abnormal nodes, called Byzantine nodes, arbitrarily deviate from their intended behaviors, send wrong messages to their neighbors and affect all honest nodes across the entire network through passing polluted messages. In this paper, we focus on decentralized federated learning in the presence of Byzantine attacks and then propose a unified Byzantine-resilient framework based on the network gradient descent and several robust aggregation rules. Theoretically, the convergence of the proposed algorithm is guaranteed under some weakly balanced conditions of network structure. The finite-sample performance is studied through simulations under different network topologies and various Byzantine attacks. An application to Communities and Crime Data is also presented.</p>","PeriodicalId":0,"journal":{"name":"","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"","FirstCategoryId":"100","ListUrlMain":"https://doi.org/10.1007/s42952-023-00249-w","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

Decentralized federated learning based on fully normal nodes has drawn attention in modern statistical learning. However, due to data corruption, device malfunctioning, malicious attacks and some other unexpected behaviors, not all nodes can obey the estimation process and the existing decentralized federated learning methods may fail. An unknown number of abnormal nodes, called Byzantine nodes, arbitrarily deviate from their intended behaviors, send wrong messages to their neighbors and affect all honest nodes across the entire network through passing polluted messages. In this paper, we focus on decentralized federated learning in the presence of Byzantine attacks and then propose a unified Byzantine-resilient framework based on the network gradient descent and several robust aggregation rules. Theoretically, the convergence of the proposed algorithm is guaranteed under some weakly balanced conditions of network structure. The finite-sample performance is studied through simulations under different network topologies and various Byzantine attacks. An application to Communities and Crime Data is also presented.

Abstract Image

分享
查看原文
拜占庭式弹性分散网络学习
基于完全正常节点的分散联合学习在现代统计学习中备受关注。然而,由于数据损坏、设备故障、恶意攻击和其他一些意外行为,并非所有节点都能遵守估计过程,现有的分散联合学习方法可能会失败。数量未知的异常节点(称为拜占庭节点)会任意偏离其预期行为,向其邻居发送错误信息,并通过传递污染信息影响整个网络中的所有诚实节点。在本文中,我们将重点放在拜占庭攻击下的分散式联合学习上,然后提出了一种基于网络梯度下降和几种鲁棒聚合规则的统一拜占庭抗性框架。从理论上讲,在网络结构的某些弱平衡条件下,所提算法的收敛性是有保证的。通过模拟研究了不同网络拓扑结构和各种拜占庭攻击下的有限样本性能。此外,还介绍了该算法在社区和犯罪数据中的应用。
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
×
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