ProtoFedLA: Prototype Guided Personalized Federated Learning Based on Localized Aggregation across Heterogeneous Clients

In today’s data-driven era, data privacy protection is a key challenge in artificial intelligence development. Federated learning (FL) effectively addresses data silos and privacy concerns, but the statistical heterogeneity among clients limits the performance and generalization of traditional FL methods. Personalized federated learning (pFL) tackles this by training customized models for each client based on local data distributions. However, current pFL methods either focus on fine-tuning the global model on the client side or generating personalized models on the server side, failing to balance global collaboration and personalized learning. To address this, we propose ProtoFedLA, an innovative pFL framework that uses data prototypes to guide personalized model updates. This ensures consistency with the global data distribution while adapting to local data through localized aggregation. We evaluated ProtoFedLA using five publicly available image/text classification datasets under two heterogeneous data environments. The results show significant performance improvements over state-of-the-art pFL methods, with ProtoFedLA outperforming the best baseline by 5.83%. Additionally, ProtoFedLA handles data heterogeneity effectively, while demonstrating excellent stability and scalability.