arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.01666cs.LGcs.AImath.OCstat.ML
收藏

联邦学习中的比例公平性

Proportional Fairness in Federated Learning

Huawei Noah’s Ark Lab(华为诺亚方舟实验室);University of Waterloo(滑铁卢大学)

Guojun Zhang, Saber Malekmohammadi, Xi Chen, Yaoliang Yu

AI总结:

本文提出联邦学习中的比例公平性概念,基于性能相对变化,并设计PropFair算法近似求解,平衡整体与最差10%客户端性能。

摘要:

随着联邦学习(FL)系统在现实世界中的部署日益广泛,确保FL中的公平性,即让众多不同客户端中的每一个都能获得合理满意的性能,变得至关重要且具有挑战性。在这项工作中,我们引入并研究了一种新的FL公平性概念,称为比例公平性(PF),它基于每个客户端性能的相对变化。基于其与讨价还价博弈的联系,我们提出了PropFair,一种新颖且易于实现的算法,用于在FL中寻找比例公平解,并研究了其收敛性质。通过在视觉和语言数据集上的大量实验,我们证明PropFair能够近似找到PF解,并且在所有客户端的平均性能与最差10%客户端的平均性能之间取得了良好的平衡。我们的代码可在\url{https://github.com/huawei-noah/Federated-Learning/tree/main/FairFL}获取。

英文摘要:

With the increasingly broad deployment of federated learning (FL) systems in the real world, it is critical but challenging to ensure fairness in FL, i.e. reasonably satisfactory performances for each of the numerous diverse clients. In this work, we introduce and study a new fairness notion in FL, called proportional fairness (PF), which is based on the relative change of each client's performance. From its connection with the bargaining games, we propose PropFair, a novel and easy-to-implement algorithm for finding proportionally fair solutions in FL and study its convergence properties. Through extensive experiments on vision and language datasets, we demonstrate that PropFair can approximately find PF solutions, and it achieves a good balance between the average performances of all clients and of the worst 10% clients. Our code is available at \url{https://github.com/huawei-noah/Federated-Learning/tree/main/FairFL}.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑