Influence-oriented Personalized Federated Learning

TL;DR

This paper introduces FedC^2I, a novel federated learning framework that models client and class influence to enable adaptive, personalized parameter aggregation, improving performance in heterogeneous data environments.

Contribution

The paper proposes a new influence-based approach for personalized federated learning, explicitly modeling inter-client and class influence for adaptive aggregation.

Findings

FedC^2I outperforms existing methods in non-IID settings.

Influence vectors and matrices effectively guide personalized aggregation.

The framework enhances model performance in heterogeneous data scenarios.

Abstract

Traditional federated learning (FL) methods often rely on fixed weighting for parameter aggregation, neglecting the mutual influence by others. Hence, their effectiveness in heterogeneous data contexts is limited. To address this problem, we propose an influence-oriented federated learning framework, namely FedC^2I, which quantitatively measures Client-level and Class-level Influence to realize adaptive parameter aggregation for each client. Our core idea is to explicitly model the inter-client influence within an FL system via the well-crafted influence vector and influence matrix. The influence vector quantifies client-level influence, enables clients to selectively acquire knowledge from others, and guides the aggregation of feature representation layers. Meanwhile, the influence matrix captures class-level influence in a more fine-grained manner to achieve personalized classifier aggregation. We evaluate the performance of FedC^2I against existing federated learning methods under non-IID settings and the results demonstrate the superiority of our method.