Spiking Neural Networks in Vertical Federated Learning: Performance Trade-offs

TL;DR

This paper explores the use of energy-efficient Spiking Neural Networks in vertical federated learning, analyzing their performance trade-offs and privacy implications compared to traditional neural networks.

Contribution

It is the first to analyze SNNs in VFL, comparing different architectures and evaluating their accuracy and energy efficiency on benchmark datasets.

Findings

SNNs achieve comparable accuracy to ANNs in VFL.

SNNs are significantly more energy efficient.

Model splitting affects privacy and performance trade-offs.

Abstract

Federated machine learning enables model training across multiple clients while maintaining data privacy. Vertical Federated Learning (VFL) specifically deals with instances where the clients have different feature sets of the same samples. As federated learning models aim to improve efficiency and adaptability, innovative neural network architectures like Spiking Neural Networks (SNNs) are being leveraged to enable fast and accurate processing at the edge. SNNs, known for their efficiency over Artificial Neural Networks (ANNs), have not been analyzed for their applicability in VFL, thus far. In this paper, we investigate the benefits and trade-offs of using SNN models in a vertical federated learning setting. We implement two different federated learning architectures -- with model splitting and without model splitting -- that have different privacy and performance implications. We evaluate the setup using CIFAR-10 and CIFAR-100 benchmark datasets along with SNN implementations of VGG9 and ResNET classification models. Comparative evaluations demonstrate that the accuracy of SNN models is comparable to that of traditional ANNs for VFL applications, albeit significantly more energy efficient.