ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Stochastic Client Selection for Federated Learning With Volatile Clients

Huang, Tiansheng; Lin, Weiwei*; Shen, Li; Li, Keqin; Zomaya, Albert Y.new
IEEE Internet of Things Journal2022-10-15DOI: 10.1109/JIOT.2022.3172113
17被引6阅读
引用收藏
分享

摘要

Federated learning (FL), arising as a privacy-preserving machine learning paradigm, has received notable attention from the public. In each round of synchronous FL training, only a fraction of available clients are chosen to participate, and the selection decision might have a significant effect on the training efficiency, as well as the final model performance. In this article, we investigate the client selection problem under a volatile context, in which the local training of heterogeneous clients is likely to fail due to various kinds of reasons and in different levels of frequency. Intuitively, too much training failure might potentially reduce the training efficiency, while too much selection on clients with greater stability might introduce bias, thereby resulting in degradation of the training effectiveness. To tackle this tradeoff, we, in this article, formulate the client selection problem under joint consideration of effective participation and fairness. Furthermore, we propose E3CS, a stochastic client selection scheme as a solution. According to our experimental results over a public data set, the proposed selection scheme is able to achieve up to 2x faster convergence to a fixed model accuracy while maintaining the same level of final model accuracy, compared with the state-of-the-art selection schemes.

学科与关键词

关键词
Adversarial multiarm bandit (MAB)client selectionexponential-weight algorithm for exploration and exploitation (Exp3)fairness schedulingfederated learning (FL)
相关
加载中…
  • VFedCS: Optimizing Client Selection for Volatile Federated Learning
    Shi, Fang; Hu, Chunchao; Lin, Weiwei*; Fan, Lisheng; Huang, Tiansheng; Wu, WentaiIEEE Internet of Things Journal, 2022, 9(24): 24995-25010.被引 3
  • Efficient Client Selection Based on Contextual Combinatorial Multi-Arm Bandits
    Shi, Fang; Lin, Weiwei*; Fan, Lisheng; Lai, Xiazhi; Wang, XiuminIEEE Transactions on Wireless Communications, 2023, 22(8): 5265-5277.
  • Contribution-based Federated Learning client selection
    Lin, Weiwei*; Xu, Yinhai; Liu, Bo*; Li, Dongdong; Huang, Tiansheng; Shi, FangINTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, 2022, 37(10): 7235-7260.被引 4
查看全部 →

发表信息

论文状态
公开发表
期刊
IEEE Internet of Things Journal
发表日期
2022-10-15
卷期
第 9 卷, 第 20 期
页码
20055-20070
DOI
10.1109/JIOT.2022.3172113
期刊等级
1区
成果收录
SCIE
资助标注
Key-Area Research and Development Program of Guangdong Province [2021B0101420002]; National Natural Science Foundation of China [62072187, 61872084]; Guangzhou Science and Technology Program Key Projects [202007040002]; Guangzhou Development Zone Science and Technology [2020GH10]; Guangdong Marine Economic Development Special Fund Project [GDNRC[2022]17]; Science and Technology Innovation 2030-"Brain Science and Brain-Like Research" Major Project [2021ZD0201402, 2021ZD0201405]

作者

  • H

    Huang, Tiansheng (第一作者)

  • L

    Lin, Weiwei (通讯)

查看全部 5 位作者收起作者
  • S

    Shen, Li

  • L

    Li, Keqin

    new

  • Z

    Zomaya, Albert Y.

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417