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}.

翻译：随着联邦学习系统在现实世界中的日益广泛部署，确保联邦学习的公平性（即为众多各异的客户端提供合理满意的性能）变得至关重要且具有挑战性。本文提出并研究了一种新的联邦学习公平性概念——比例公平性，其基于每个客户端性能的相对变化。通过与讨价还价博弈的联系，我们提出PropFair——一种新颖且易于实现的算法，用于在联邦学习中寻找比例公平解，并研究其收敛性质。通过在视觉和语言数据集上的大量实验，我们证明PropFair能够近似找到比例公平解，并在所有客户端的平均性能与最差10%客户端的性能之间实现良好平衡。我们的代码开源在：\url{https://github.com/huawei-noah/Federated-Learning/tree/main/FairFL}。