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

Robust Communication Strategy for Federated Learning by Incorporating Self-Attention

Xu, Yawen*; Li, Xiaojun; Yang, Zeyu; Song, Hengjie
International Conference on Image, Video Processing and Artificial Intelligence2020DOI: 10.1117/12.2581491
11阅读
引用收藏
分享

摘要

Federated learning is an emerging machine learning setting, which can train a shared model on large amounts of decentralized data while protecting data privacy. However, the communication cost of federated learning is heavy, especially for mobile devices with higher latency and lower throughput. Although several algorithms have been proposed to reduce the communication cost, they are extremely sensitive to data distribution, even inapplicable to the real client Non-IID data. In this paper, we propose an effective communication strategy for federated learning called FedSAA, which increases the testing performance on Non-IID data by introducing selfattention mechanism. Two major innovations of our paper are presented here. Firstly, we utilize self-attention mechanism to optimize both the server-to-client and the client-to-client parameter divergence during the model aggregation process so as to improve the model robustness for Non-IID data. Secondly, we adopt the sign compression operator to help data transmission between nodes. The experimental results demonstrate that the model accuracy of our communication-efficient strategy for federated learning with Non-IID data is superior to other communication-efficient algorithms.

学科与关键词

关键词
Federated LearningDeep LearningSelf-AttentionComputer VisionData Privacy
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
  • Communication Efficient Federated Learning With Heterogeneous Structured Client Models
    Hu, Yao; Sun, Xiaoyan*; Tian, Ye; Song, Linqi*; Tan, Kay ChenIEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE, 2023, 7(3): 753-767.被引 2
查看全部 →

会议信息

会议名称
International Conference on Image, Video Processing and Artificial Intelligence
会议日期
2020-08-21 至 2020-08-23
论文集名
2020 INTERNATIONAL CONFERENCE ON IMAGE, VIDEO PROCESSING AND ARTIFICIAL INTELLIGENCE
发表日期
2020
DOI
10.1117/12.2581491
资助标注
National Natural Science Foundation of China [71671069]; National Key R&D Program of China [2018YFC0830900, 61400010205]
收录
ISTP

作者

  • X

    Xu, Yawen (通讯) (第一作者)

  • L

    Li, Xiaojun

查看全部 4 位作者收起作者
  • Y

    Yang, Zeyu

  • S

    Song, Hengjie

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