《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (1): 1-14.DOI: 10.11772/j.issn.1001-9081.2023121881

• 人工智能 •    下一篇

联邦学习的公平性综述

张淑芬1,2,3, 张宏扬1,2,4, 任志强1,2,4, 陈学斌1,2,4()   

  1. 1.华北理工大学 理学院,河北 唐山 063210
    2.河北省数据科学与应用重点实验室(华北理工大学),河北 唐山 063210
    3.唐山市大数据安全与智能计算重点实验室(华北理工大学),河北 唐山 063210
    4.唐山市数据科学重点实验室(华北理工大学),河北 唐山 063210
  • 收稿日期:2024-01-12 修回日期:2024-03-18 接受日期:2024-03-22 发布日期:2024-04-02 出版日期:2025-01-10
  • 通讯作者: 陈学斌
  • 作者简介:张淑芬(1972—),女,河北唐山人,教授,博士,CCF高级会员,主要研究方向:云计算、智能信息处理、数据安全、隐私保护;
    张宏扬(1999—),男,江苏淮安人,硕士研究生,CCF会员,主要研究方向:数据安全、隐私保护;
    任志强(2000—),男,四川广元人,硕士研究生,CCF会员,主要研究方向:数据安全、隐私保护;
  • 基金资助:
    国家自然科学基金资助项目(U20A20179)

Survey of fairness in federated learning

Shufen ZHANG1,2,3, Hongyang ZHANG1,2,4, Zhiqiang REN1,2,4, Xuebin CHEN1,2,4()   

  1. 1.College of Sciences,North China University of Science and Technology,Tangshan Hebei 063210,China
    2.Hebei Provincial Key Laboratory of Data Science and Application (North China University of Science and Technology),Tangshan Hebei 063210,China
    3.Tangshan Key Laboratory of Big Data Security and Intelligent Computing (North China University of Science and Technology),Tangshan Hebei 063210,China
    4.Tangshan Key Laboratory of Data Science (North China University of Science and Technology),Tangshan Hebei 063210,China
  • Received:2024-01-12 Revised:2024-03-18 Accepted:2024-03-22 Online:2024-04-02 Published:2025-01-10
  • Contact: Xuebin CHEN
  • About author:ZHANG Shufen, born in 1972, Ph. D., professor. Her research interests include cloud computing, intelligent information processing, data security, privacy protection.
    ZHANG Hongyang, born in 1999, M. S. candidate. His research interests include data security, privacy protection.
    REN Zhiqiang, born in 2000, M. S. candidate. His research interests include data security, privacy protection.
  • Supported by:
    National Natural Science Foundation of China(U20A20179)

摘要:

联邦学习(FL)凭借分布式结构和隐私安全的优势快速发展,但大规模FL引发的公平性问题影响了FL系统的可持续性。针对FL的公平性问题,对近年FL公平性的研究工作进行了系统梳理和深度分析。首先,对FL的工作流程和定义进行了解释,总结了FL中的偏见和公平性概念;其次,详细归纳了FL公平性研究中常用的数据集,探讨了公平性研究所面临的挑战;最后,从数据源选择、模型优化、贡献评估和激励机制这4个方面归纳梳理了相关研究工作的优缺点、适用场景以及实验设置等,并展望了FL公平性未来的研究方向和趋势。

关键词: 联邦学习, 公平性, 数据选择, 模型优化, 贡献评估, 激励机制

Abstract:

Federated Learning(FL) has experienced rapid development due to its advantages in distributed structure and privacy security. However, the fairness issues caused by large-scale FL affect the sustainability of FL systems. In response to the fairness issues in FL, recent researches on fairness in FL was reviewed systematically and analyzed deeply. Firstly, the workflow and definitions of FL were explained, and biases and fairness concepts in FL were summarized. Secondly, commonly used datasets in fairness research of FL were detailed, and the challenges faced by fairness research were discussed. Finally, the advantages, disadvantages, applicable scenarios, and experimental setting of relevant research work were summed up from four aspects: data source selection, model optimization, contribution evaluation, and incentive mechanism, and the future research directions and trends in fairness of FL were prospected.

Key words: Federated Learning (FL), fairness, data selection, model optimization, contribution evaluation, incentive mechanism

中图分类号: