Federated Learning with Spiking Neural Networks

TL;DR

This paper introduces a federated learning framework for Spiking Neural Networks (SNNs), demonstrating significant energy efficiency and accuracy improvements over traditional neural networks in resource-constrained, distributed environments.

Contribution

It presents the first large-scale federated learning framework for SNNs, enabling decentralized, privacy-preserving training and comprehensive evaluation on benchmark datasets.

Findings

SNNs outperform ANNs by over 15% accuracy in federated settings

SNNs provide up to 5.3x energy efficiency compared to ANNs

Federated SNNs are robust to data distribution, stragglers, and gradient noise

Abstract

As neural networks get widespread adoption in resource-constrained embedded devices, there is a growing need for low-power neural systems. Spiking Neural Networks (SNNs)are emerging to be an energy-efficient alternative to the traditional Artificial Neural Networks (ANNs) which are known to be computationally intensive. From an application perspective, as federated learning involves multiple energy-constrained devices, there is a huge scope to leverage energy efficiency provided by SNNs. Despite its importance, there has been little attention on training SNNs on a large-scale distributed system like federated learning. In this paper, we bring SNNs to a more realistic federated learning scenario. Specifically, we propose a federated learning framework for decentralized and privacy-preserving training of SNNs. To validate the proposed federated learning framework, we experimentally evaluate the advantages of SNNs on various aspects of federated learning with CIFAR10 and CIFAR100 benchmarks. We observe that SNNs outperform ANNs in terms of overall accuracy by over 15% when the data is distributed across a large number of clients in the federation while providing up to5.3x energy efficiency. In addition to efficiency, we also analyze the sensitivity of the proposed federated SNN framework to data distribution among the clients, stragglers, and gradient noise and perform a comprehensive comparison with ANNs.