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

DM-PFL: Hitchhiking Generic Federated Learning for Efficient Shift-Robust Personalization

Zhang, Wenhao*; Zhou, Zimu; Wang, Yansheng; Tong, Yongxin北京航空航天大学
29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)2023DOI: 10.1145/3580305.3599311
5阅读
引用收藏
分享

摘要

Personalized federated learning collaboratively trains client-specific models, which holds potential for various mobile and IoT applications with heterogeneous data. However, existing solutions are vulnerable to distribution shifts between training and test data, and involve high training workloads on local devices. These two shortcomings hinder the practical usage of personalized federated learning on real-world mobile applications. To overcome these drawbacks, we explore efficient shift-robust personalization for federated learning. The principle is to hitchhike the global model to improve the shift-robustness of personalized models with minimal extra training overhead. To this end, we present DM-PFL, a novel framework that utilizes a dual masking mechanism to train both global and personalized models with weight-level parameter sharing and end-to-end sparse training. Evaluations on various datasets show that our methods not only improve the test accuracy in presence of test-time distribution shifts but also save the communication and computation costs compared to state-of-the-art personalized federated learning schemes.

学科与关键词

关键词
Federated LearningSparse TrainingPersonalizationRobustness
相关
加载中…
  • Personalized Federated Learning on Non-IID Data via Group-based Meta-learning
    Yang, Lei; Huang, Jiaming; Lin, Wanyu*; Cao, JiannongACM Transactions on Knowledge Discovery from Data, 2023, 17(4).被引 13
  • Learning to Generalize in Heterogeneous Federated Networks
    Chen, Cen*; Ye, Tiandi; Wang, Li; Gao, Ming*31st ACM International Conference on Information and Knowledge Management (CIKM), Atlanta, GA, 2022-10-17 To 2022-10-21.
  • Hierarchical Personalized Federated Learning Over Massive Mobile Edge Computing Networks
    You, Chaoqun; Guo, Kun*; Yang, Howard H.; Quek, Tony Q. S.*IEEE Transactions on Wireless Communications, 2023, 22(11): 8141-8157.被引 1
查看全部 →

会议信息

会议名称
29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)
会议日期
2023-08-06 至 2023-08-10
论文集名
PROCEEDINGS OF THE 29TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2023
发表日期
2023
起止页码
3396-3408
DOI
10.1145/3580305.3599311
资助标注
National Science Foundation of China (NSFC) [U21A20516, 62076017]; Beihang University Basic Research Funding [YWF-22-L-531, 22-TQ23-14-ZD-01-001]; CityU APRC [9610633]; WeBank Scholars Program
收录
ISTP

作者

  • Z

    Zhang, Wenhao (通讯) (第一作者)

    beihang univ

  • Z

    Zhou, Zimu

查看全部 4 位作者收起作者
  • W

    Wang, Yansheng

    beihang univ

  • T

    Tong, Yongxin

    beihang univ

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