Federated Neuromorphic Learning of Spiking Neural Networks for Low-Power Edge Intelligence

TL;DR

This paper introduces FL-SNN, a federated learning approach for spiking neural networks that enables low-power, on-device training and inference by cooperative learning, reducing data constraints and communication costs.

Contribution

It proposes a novel federated learning rule for SNNs that uses local feedback and global communication, improving on separate training methods.

Findings

Significant accuracy improvements over isolated training.

Flexible trade-off between communication load and accuracy.

Effective online learning for low-power edge devices.

Abstract

Spiking Neural Networks (SNNs) offer a promising alternative to conventional Artificial Neural Networks (ANNs) for the implementation of on-device low-power online learning and inference. On-device training is, however, constrained by the limited amount of data available at each device. In this paper, we propose to mitigate this problem via cooperative training through Federated Learning (FL). To this end, we introduce an online FL-based learning rule for networked on-device SNNs, which we refer to as FL-SNN. FL-SNN leverages local feedback signals within each SNN, in lieu of backpropagation, and global feedback through communication via a base station. The scheme demonstrates significant advantages over separate training and features a flexible trade-off between communication load and accuracy via the selective exchange of synaptic weights.