联邦学习能够促进多方参与者之间的数据共享和协同计算,其已经成为一种流行的分布式机器学习范式.联邦学习目前的研究主要集中在性能提升和隐私保护方面.近年来,随着可信人工智能研究的深入,可信联邦学习的研究也受到越来越多的关注.其中,保证联邦学习的公平性是面临的关键问题之一.提升联邦学习的公平性能够保证客户端参与的积极性和联邦学习训练的可持续性.然而,由于联邦学习中通常存在着数据异构性和设备异构性,传统的联邦学习方法会导致客户端之间具有很大的差异,无法保证所有参与者之间的公平,这会极大地影响用户参与联邦学习的动力.基于此,对近年来联邦学习公平性的研究方法进行全面归纳梳理与深度探讨分析.首先对当前联邦学习公平性研究的主要方向进行划分,并对每个方向的公平性定义与评价标准进行了解释及对比.随后详细探讨了联邦学习公平性不同方向面临的挑战和主要解决方案.最后对联邦学习公平性研究中常用的数据集、实验场景设置和公平评价指标进行了归纳梳理,并对未来研究方向与发展趋势进行探讨和展望.
Federated learning is a distributed machine learning paradigm that facilitates data sharing and collaborative computing among multiple participants.Currently,research on federated learning primarily focuses on performance im-provement and privacy protection.With the emergence of trustworthy artificial intelligence,the research on trustworthy fed-erated learning methods has gained more attention,and ensuring fairness in federated learning is one of the main challeng-es.Improving the fairness of federated learning can motivate the enthusiasm of clients and ensure the sustainability of feder-ated learning training.However,due to the heterogeneity of data and devices in federated learning,traditional federated learning methods may lead to significant performance differences between clients,which may hinder fairness among all par-ticipants and significantly impact the motivation of users to participate in federated learning.Based on this,this paper pro-vides a comprehensive review of the research methods of fairness in federated learning.Firstly,we categorize the main re-search directions of fairness in federated learning,elaborates the definition and compares the evaluation criteria of fairness in each direction.Next,we discuss the challenges and main solutions for improving fairness in federated learning in each di-rection.Then,we summarize the commonly used datasets,experimental scenarios,and fairness evaluation metrics in the study of fairness.Finally,we prospectively explore the future research directions and development trends of fairness in fed-erated learning.