GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learning
This addresses statistical heterogeneity and personalization challenges in federated learning for privacy-preserving collaborative systems, representing a novel method for a known bottleneck.
The paper tackles the problem of personalized federated learning by proposing GPFL, a method that simultaneously learns global and personalized feature information on each client. The results show GPFL outperforms ten state-of-the-art methods by up to 8.99% in accuracy across six datasets in three statistically heterogeneous settings.
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.