论文标题
联邦学习的比例公平
Proportional Fairness in Federated Learning
论文作者
论文摘要
随着现实世界中联邦学习（FL）系统的越来越广泛的部署，确保FL的公平性，即为每个多样化的客户中的每个客户中的公平性，都至关重要，但具有挑战性。在这项工作中，我们介绍并研究了佛罗里达州的新公平概念，称为比例公平（PF），该概念基于每个客户绩效的相对变化。从与讨价还价游戏的联系来看，我们提出了Propfair，这是一种新颖且易于实现的算法，用于在FL中找到按比例公平的解决方案，并研究其收敛性。通过有关视觉和语言数据集的广泛实验，我们证明了Propfair可以大致找到PF解决方案，并且在所有客户的平均表现与最差的10％客户的平均表现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/main/fairfl}中找到。
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}.
