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

FedProf: Selective Federated Learning Based on Distributional Representation Profiling

Wu, Wentai; He, Ligang*; Lin, Weiwei*; Maple, Carsten
IEEE Transactions on Parallel and Distributed Systems2023-6DOI: 10.1109/TPDS.2023.3265588
1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 learning from decentralized data that are only accessible to end devices (i.e., clients). The data locality constraint offers strong privacy protection but also makes FL sensitive to the condition of local data. Apart from statistical heterogeneity, a large proportion of the clients, in many scenarios, are probably in possession of low-quality data that are biased, noisy or even irrelevant. As a result, they could significantly slow down the convergence of the global model we aim to build and also compromise its quality. In light of this, we first present a new view of local data by looking into the representation space and observing that they converge in distribution to Normal distributions before activation. We provide theoretical analysis to support our finding. Further, we propose FedProf, a novel algorithm for optimizing FL over non-IID data of mixed quality. The key of our approach is a distributional representation profiling and matching scheme that uses the global model to dynamically profile data representations and allows for low-cost, lightweight representation matching. Using the scheme we sample clients adaptively in FL to mitigate the impact of low-quality data on the training process. We evaluated our solution with extensive experiments on different tasks and data conditions under various FL settings. The results demonstrate that the selective behavior of our algorithm leads to a significant reduction in the number of communication rounds and the amount of time (up to 2.4x speedup) for the global model to converge and also provides accuracy gain.

学科与关键词

关键词
TrainingDistributed databasesData modelsComputational modelingServersTask analysisConvergenceDistributed systemsfederated learningmachine learningneural networksrepresentation learning
相关
加载中…
  • Efficient Federated Learning Using Layer-Wise Regulation and Momentum Aggregation*
    Zhang, Fan; Fang, Zekuan; Li, Yiming; Chen, Mingsong*JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS, 2022, 31(18): 2250314.
  • Client Selection for Federated Learning With Non-IID Data in Mobile Edge Computing
    Zhang, Wenyu; Wang, Xiumin*; Zhou, Pan; Wu, Weiwei; Zhang, XinglinIEEE Access, 2021, 9: 24462-24474.被引 63
  • 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 Transactions on Parallel and Distributed Systems
发表日期
2023-06
卷期
第 34 卷, 第 6 期
页码
1942-1953
DOI
10.1109/TPDS.2023.3265588
语言
ENGLISH
成果收录
SCIE
资助标注
National Natural Science Foundation of China [62072187]; Key-Area Research and Development Program of Guangdong Province [2021B0101420002]; Guangdong Major Project of Basic and Applied Basic Research [2019B030302002]; Guangdong Marine Economic Development Special Fund Project [GDNRC[2022]17]; Guangzhou Development Zone Science and Technology Project [2021GH10, 2020GH10]

作者

  • W

    Wu, Wentai (第一作者)

  • H

    He, Ligang (通讯)

查看全部 4 位作者收起作者
  • L

    Lin, Weiwei (通讯)

  • M

    Maple, Carsten

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