联邦学习的公平性研究综述
A survey on the fairness of federated learning
朱智韬 1司世景 2王健宗 2程宁 2孔令炜 2黄章成 2肖京2
作者信息
- 1. 平安科技(深圳)有限公司,广东 深圳 518063;中国科学技术大学,安徽 合肥 230026
- 2. 平安科技(深圳)有限公司,广东 深圳 518063
- 折叠
摘要
联邦学习使用来自多个参与者提供的数据协同训练全局模型,近年来在促进企业间数据合作方面发挥着越来越重要的作用.另外,联邦学习训练范式常常面临数据不足的困境,因此为联邦学习参与者提供公平性保证以激励更多参与者贡献他们宝贵的资源是非常重要的.针对联邦学习的公平性问题,首先依据公平目标不同,从模型表现均衡、贡献评估公平、消除群体歧视出发进行了联邦学习公平性的3种分类;然后对现有的公平性促进方法进行了深入介绍与比较,旨在帮助研究者开发新的公平性促进方法;最后通过对联邦学习落地过程中的需求进行剖析,提出了未来联邦学习公平性研究的5个方向.
Abstract
Federated learning uses data from multiple participants to collaboratively train global models and has played an increasingly important role in recent years in facilitating inter-firm data collaboration.On the other hand,the federal learning training paradigm often faces the dilemma of insufficient data,so it is important to provide assurance of fairness to motivate more participants to contribute their valuable resources.This paper illustrates the issue of fairness in federated learning.Firstly,three classifications of fairness based on different equity goals,from model performance balance,contribution assessment equity,and elimination of group discrimination are proposed,and then we provide in-depth introduction and comparison of existing fairness promotion methods,aiming to help researchers develop new fairness promotion methods.Finally,by dissecting the needs in the process of federal learning implementation,five directions for future federated learning fairness research are proposed.
关键词
联邦学习/公平性/表现均衡/贡献衡量Key words
federated learning/fairness/balance in performance/measure of contributions引用本文复制引用
基金项目
广东省重点领域研发计划(2021B0101400003)
出版年
2024
国家科技期刊平台
NSTL
维普
万方数据