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

VFedCS: Optimizing Client Selection for Volatile Federated Learning

Shi, Fang; Hu, Chunchao; Lin, Weiwei*; Fan, Lisheng; Huang, Tiansheng; Wu, Wentai广州大学; 南方电网技术研究中心
IEEE Internet of Things Journal2022-12-15DOI: 10.1109/JIOT.2022.3195073
3被引10阅读
引用收藏
分享

摘要

Federated learning (FL) has shown great potential as a privacy-preserving solution to training a centralized model based on local data from available clients. However, we argue that, over the course of training, the available clients may exhibit some volatility in terms of the client population, client data, and training status. Considering these volatilities, we propose a new learning scenario termed volatile federated learning (volatile FL) featuring set volatility, statistical volatility, and training volatility. The volatile client set along with the dynamic of clients' data and the unreliable nature of clients (e.g., unintentional shutdown and network instability) greatly increase the difficulty of client selection. In this article, we formulate and decompose the global problem into two subproblems based on alternating minimization. For an efficient settlement for the proposed selection problem, we quantify the impact of clients' data and resource heterogeneity for volatile FL and introduce the cumulative effective participation data (CEPD) as an optimization objective. Based on this, we propose upper confidence bound-based greedy selection, dubbed UCB-GS, to address the client selection problem in volatile FL. Theoretically, we prove that the regret of UCB-GS is strictly bounded by a finite constant, justifying its theoretical feasibility. Furthermore, experimental results show that our method significantly reduces the number of training rounds (by up to 62%) while increasing the global model's accuracy by 7.51%.

学科与关键词

关键词
Client selectioncombinatorial multiarm bandit (CMAB)submodular functionvolatile clientvolatile federated learning (volatile FL)
相关
加载中…

文献加载失败,请重试

重试

发表信息

论文状态
公开发表
期刊
IEEE Internet of Things Journal
发表日期
2022-12-15
卷期
第 9 卷, 第 24 期
页码
24995-25010
DOI
10.1109/JIOT.2022.3195073
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]; Guangdong Special Project for Marine Economy Development [GDNRC[2022]17]; Guangdong Major Project of Basic and Applied Basic Research [2019B030302002]; Guangzhou Development Zone Science and Technology [2021GH10, 2020GH10]

作者

  • S

    Shi, Fang (第一作者)

  • H

    Hu, Chunchao

    china southern power grid

查看全部 6 位作者收起作者
  • L

    Lin, Weiwei (通讯)

  • F

    Fan, Lisheng

    guangzhou univ

  • H

    Huang, Tiansheng

  • W

    Wu, Wentai

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