SFedCA: Credit Assignment-Based Active Client Selection Strategy for Spiking Federated Learning

TL;DR

This paper introduces SFedCA, a novel client selection strategy for spiking federated learning that improves convergence and accuracy by considering client contribution based on firing intensity, especially under non-IID data distributions.

Contribution

It proposes a credit assignment-based active client selection method that enhances federated learning efficiency and accuracy in resource-constrained, non-IID environments.

Findings

SFedCA outperforms existing methods in convergence speed.

Requires fewer communication rounds for effective training.

Improves global model accuracy under non-IID data scenarios.

Abstract

Spiking federated learning is an emerging distributed learning paradigm that allows resource-constrained devices to train collaboratively at low power consumption without exchanging local data. It takes advantage of both the privacy computation property in federated learning (FL) and the energy efficiency in spiking neural networks (SNN). Thus, it is highly promising to revolutionize the efficient processing of multimedia data. However, existing spiking federated learning methods employ a random selection approach for client aggregation, assuming unbiased client participation. This neglect of statistical heterogeneity affects the convergence and accuracy of the global model significantly. In our work, we propose a credit assignment-based active client selection strategy, the SFedCA, to judiciously aggregate clients that contribute to the global sample distribution balance. Specifically, the client credits are assigned by the firing intensity state before and after local model training, which reflects the local data distribution difference from the global model. Comprehensive experiments are conducted on various non-identical and independent distribution (non-IID) scenarios. The experimental results demonstrate that the SFedCA outperforms the existing state-of-the-art spiking federated learning methods, and requires fewer communication rounds.