Federated learning aims to collaboratively train models without accessing their client's local private data. The data may be Non-IID for different clients and thus resulting in poor performance. Recently, personalized federated learning (PFL) has achieved great success in handling Non-IID data by enforcing regularization in local optimization or improving the model aggregation scheme on the server. However, most of the PFL approaches do not take into account the unfair competition issue caused by the imbalanced data distribution and lack of positive samples for some classes in each client. To address this issue, we propose a novel and generic PFL framework termed Federated Averaging via Binary Classification, dubbed FedABC. In particular, we adopt the ``one-vs-all'' training strategy in each client to alleviate the unfair competition between classes by constructing a personalized binary classification problem for each class. This may aggravate the class imbalance challenge and thus a novel personalized binary classification loss that incorporates both the under-sampling and hard sample mining strategies is designed. Extensive experiments are conducted on two popular datasets under different settings, and the results demonstrate that our FedABC can significantly outperform the existing counterparts.

翻译：联邦学习旨在不访问客户端本地私有数据的情况下协作训练模型。不同客户端的数据可能存在非独立同分布（Non-IID）问题，导致模型性能下降。近年来，个性化联邦学习（PFL）通过加强本地优化的正则化或改进服务器端的模型聚合方案，在处理Non-IID数据方面取得了显著成功。然而，大多数PFL方法未考虑因数据分布不平衡及某些类别在客户端中缺乏正样本所引发的不公平竞争问题。为解决该问题，我们提出了一种新颖且通用的PFL框架——基于二分类的联邦平均（Federated Averaging via Binary Classification，简称FedABC）。具体而言，我们在每个客户端采用“一对多”训练策略，通过为每个类别构建个性化的二分类问题来缓解类别间的竞争不公。但这可能加剧类别不平衡挑战，为此我们设计了一种融合欠采样与难样本挖掘策略的新型个性化二分类损失函数。在两个主流数据集上不同设置下的广泛实验表明，我们的FedABC性能显著优于现有方法。