FedProK: Trustworthy Federated Class-Incremental Learning via Prototypical Feature Knowledge Transfer

TL;DR

FedProK introduces a novel federated class-incremental learning method that uses prototypical feature transfer to enhance continual learning, privacy, and efficiency amidst data heterogeneity and catastrophic forgetting.

Contribution

It proposes a new knowledge transfer approach using prototypical features for federated class-incremental learning, addressing trustworthiness and data heterogeneity challenges.

Findings

FedProK outperforms state-of-the-art methods in trustworthiness metrics.

Effective in both synchronous and asynchronous federated learning settings.

Demonstrates robustness against catastrophic forgetting and data heterogeneity.

Abstract

Federated Class-Incremental Learning (FCIL) focuses on continually transferring the previous knowledge to learn new classes in dynamic Federated Learning (FL). However, existing methods do not consider the trustworthiness of FCIL, i.e., improving continual utility, privacy, and efficiency simultaneously, which is greatly influenced by catastrophic forgetting and data heterogeneity among clients. To address this issue, we propose FedProK (Federated Prototypical Feature Knowledge Transfer), leveraging prototypical feature as a novel representation of knowledge to perform spatial-temporal knowledge transfer. Specifically, FedProK consists of two components: (1) feature translation procedure on the client side by temporal knowledge transfer from the learned classes and (2) prototypical knowledge fusion on the server side by spatial knowledge transfer among clients. Extensive experiments conducted in both synchronous and asynchronous settings demonstrate that our FedProK outperforms the other state-of-the-art methods in three perspectives of trustworthiness, validating its effectiveness in selectively transferring spatial-temporal knowledge.