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

Abstract

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.

Figures (3)

• Figure 1: Overview of FedDBP.
• Figure 2: Visualization of training curves of the average accuracy(%) of FedDBP and other HFL methods on the CIFAR-10 dataset.
• Figure 3: Visualization of accuracy(%) of our method and others on different degrees of non-IID, which is indicated by the $\alpha$ parameter of the Dirichlet distribution.