AI RESEARCH
FedDBP: Enhancing Federated Prototype Learning with Dual-Branch Features and Personalized Global Fusion
arXiv CS.CV
•
ArXi:2603.29455v1 Announce Type: new Federated prototype learning (FPL), as a solution to heterogeneous federated learning (HFL), effectively alleviates the challenges of data and model heterogeneity. However, existing FPL methods fail to balance the fidelity and discriminability of the feature, and are limited by a single global prototype. In this paper, we propose FedDBP, a novel FPL method to address the above issues.