FedDBP: Enhancing Federated Prototype Learning with Dual-Branch Features and Personalized Global Fusion
This addresses data and model heterogeneity in federated learning, but it is incremental as it builds on existing federated prototype learning methods.
The paper tackles the problem of balancing feature fidelity and discriminability in federated prototype learning for heterogeneous federated learning, proposing FedDBP with a dual-branch feature projector and personalized global prototype fusion, achieving superiority over ten existing methods in experiments.
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. On the client-side, we design a Dual-Branch feature projector that employs L2 alignment and contrastive learning simultaneously, thereby ensuring both the fidelity and discriminability of local features. On the server-side, we introduce a Personalized global prototype fusion approach that leverages Fisher information to identify the important channels of local prototypes. Extensive experiments demonstrate the superiority of FedDBP over ten existing advanced methods.