Contribution Evaluation of Heterogeneous Participants in Federated Learning via Prototypical Representations

TL;DR

This paper introduces a novel contribution evaluation method for federated learning that leverages class contribution momentum, effectively addressing heterogeneity without auxiliary datasets.

Contribution

The paper proposes a new contribution evaluation approach using class contribution momentum, improving accuracy and efficiency in heterogeneous federated learning scenarios.

Findings

Outperforms existing methods in fidelity and effectiveness

Effective without auxiliary test datasets

Handles data heterogeneity well

Abstract

Contribution evaluation in federated learning (FL) has become a pivotal research area due to its applicability across various domains, such as detecting low-quality datasets, enhancing model robustness, and designing incentive mechanisms. Existing contribution evaluation methods, which primarily rely on data volume, model similarity, and auxiliary test datasets, have shown success in diverse scenarios. However, their effectiveness often diminishes due to the heterogeneity of data distributions, presenting a significant challenge to their applicability. In response, this paper explores contribution evaluation in FL from an entirely new perspective of representation. In this work, we propose a new method for the contribution evaluation of heterogeneous participants in federated learning (FLCE), which introduces a novel indicator \emph{class contribution momentum} to conduct refined contribution evaluation. Our core idea is the construction and application of the class contribution momentum indicator from individual, relative, and holistic perspectives, thereby achieving an effective and efficient contribution evaluation of heterogeneous participants without relying on an auxiliary test dataset. Extensive experimental results demonstrate the superiority of our method in terms of fidelity, effectiveness, efficiency, and heterogeneity across various scenarios.