Heterogeneous Federated Learning with Convolutional and Spiking Neural Networks

TL;DR

This paper explores heterogeneous federated learning involving both convolutional neural networks and spiking neural networks, benchmarking various aggregation methods and demonstrating the effectiveness of CNN-SNN fusion on MNIST.

Contribution

It introduces and evaluates a CNN-SNN fusion framework for heterogeneous federated learning, addressing model aggregation challenges across different neural network types.

Findings

CNN-SNN fusion outperforms other aggregation methods on MNIST

Competitive suppression observed during multi-model FL convergence

Benchmarking of various aggregation approaches for heterogeneous FL

Abstract

Federated learning (FL) has emerged as a promising paradigm for training models on decentralized data while safeguarding data privacy. Most existing FL systems, however, assume that all machine learning models are of the same type, although it becomes more likely that different edge devices adopt different types of AI models, including both conventional analogue artificial neural networks (ANNs) and biologically more plausible spiking neural networks (SNNs). This diversity empowers the efficient handling of specific tasks and requirements, showcasing the adaptability and versatility of edge computing platforms. One main challenge of such heterogeneous FL system lies in effectively aggregating models from the local devices in a privacy-preserving manner. To address the above issue, this work benchmarks FL systems containing both convoluntional neural networks (CNNs) and SNNs by comparing various aggregation approaches, including federated CNNs, federated SNNs, federated CNNs for SNNs, federated SNNs for CNNs, and federated CNNs with SNN fusion. Experimental results demonstrate that the CNN-SNN fusion framework exhibits the best performance among the above settings on the MNIST dataset. Additionally, intriguing phenomena of competitive suppression are noted during the convergence process of multi-model FL.