Ningzhi Gao

FedDBP: Enhancing Federated Prototype Learning with Dual-Branch Features and Personalized Global Fusion

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 protot…