Unveiling the Potential of Spiking Dynamics in Graph Representation Learning through Spatial-Temporal Normalization and Coding Strategies

TL;DR

This paper introduces a spike-based graph neural network with novel normalization and coding strategies, demonstrating competitive performance and reduced computational costs for graph learning tasks.

Contribution

It presents a new SNN model for graph learning that incorporates spatial-temporal normalization and analyzes coding strategies, addressing efficiency and stability issues.

Findings

Achieves competitive accuracy with state-of-the-art GNNs

Reduces computational costs significantly

Provides insights into spiking dynamics benefits for graph learning

Abstract

In recent years, spiking neural networks (SNNs) have attracted substantial interest due to their potential to replicate the energy-efficient and event-driven processing of biological neurons. Despite this, the application of SNNs in graph representation learning, particularly for non-Euclidean data, remains underexplored, and the influence of spiking dynamics on graph learning is not yet fully understood. This work seeks to address these gaps by examining the unique properties and benefits of spiking dynamics in enhancing graph representation learning. We propose a spike-based graph neural network model that incorporates spiking dynamics, enhanced by a novel spatial-temporal feature normalization (STFN) technique, to improve training efficiency and model stability. Our detailed analysis explores the impact of rate coding and temporal coding on SNN performance, offering new insights into their advantages for deep graph networks and addressing challenges such as the oversmoothing problem. Experimental results demonstrate that our SNN models can achieve competitive performance with state-of-the-art graph neural networks (GNNs) while considerably reducing computational costs, highlighting the potential of SNNs for efficient neuromorphic computing applications in complex graph-based scenarios.