Personalized Federated Learning (PFL) aims to learn personalized models for each client based on the knowledge across all clients in a privacy-preserving manner. Existing PFL methods generally assume that the underlying global data across all clients are uniformly distributed without considering the long-tail distribution. The joint problem of data heterogeneity and long-tail distribution in the FL environment is more challenging and severely affects the performance of personalized models. In this paper, we propose a PFL method called Federated Learning with Adversarial Feature Augmentation (FedAFA) to address this joint problem in PFL. FedAFA optimizes the personalized model for each client by producing a balanced feature set to enhance the local minority classes. The local minority class features are generated by transferring the knowledge from the local majority class features extracted by the global model in an adversarial example learning manner. The experimental results on benchmarks under different settings of data heterogeneity and long-tail distribution demonstrate that FedAFA significantly improves the personalized performance of each client compared with the state-of-the-art PFL algorithm. The code is available at https://github.com/pxqian/FedAFA.

翻译：个性化联邦学习（PFL）旨在基于所有客户端的知识，以保护隐私的方式为每个客户端学习个性化模型。现有的PFL方法通常假设所有客户端的基础全局数据均匀分布，而未考虑长尾分布。在联邦学习环境中，数据异构性与长尾分布的联合问题更具挑战性，并严重影响个性化模型的性能。本文提出一种名为对抗特征增强联邦学习（FedAFA）的PFL方法，以解决PFL中的这一联合问题。FedAFA通过生成平衡特征集来增强本地少数类，从而优化每个客户端的个性化模型。本地少数类特征通过以对抗样本学习方式，将全局模型提取的本地多数类特征的知识进行迁移来生成。在数据异构性和长尾分布不同设置下的基准实验结果表明，与最先进的PFL算法相比，FedAFA显著提升了每个客户端的个性化性能。代码请见https://github.com/pxqian/FedAFA。