Federated Learning (FL) is popular for its privacy-preserving and collaborative learning capabilities. Recently, personalized FL (pFL) has received attention for its ability to address statistical heterogeneity and achieve personalization in FL. However, from the perspective of feature extraction, most existing pFL methods only focus on extracting global or personalized feature information during local training, which fails to meet the collaborative learning and personalization goals of pFL. To address this, we propose a new pFL method, named GPFL, to simultaneously learn global and personalized feature information on each client. We conduct extensive experiments on six datasets in three statistically heterogeneous settings and show the superiority of GPFL over ten state-of-the-art methods regarding effectiveness, scalability, fairness, stability, and privacy. Besides, GPFL mitigates overfitting and outperforms the baselines by up to 8.99% in accuracy.

翻译：摘要：联邦学习因其隐私保护和协作学习能力而备受关注。近年来，个性化联邦学习（pFL）因能解决统计异质性并实现个性化学习而受到重视。然而，从特征提取的角度来看，现有大多数pFL方法在本地训练过程中仅关注提取全局或个性化特征信息，这无法满足pFL的协作学习与个性化目标。为解决这一问题，我们提出一种名为GPFL的新型pFL方法，可在每个客户端上同步学习全局与个性化特征信息。我们在三种统计异质性设置下的六个数据集上开展了大量实验，结果表明GPFL在有效性、可扩展性、公平性、稳定性和隐私性方面均优于十种最先进方法。此外，GPFL缓解了过拟合问题，在准确率上较基线方法最高提升8.99%。