A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks

TL;DR

This paper introduces SpikeGCL, a graph contrastive learning framework using spiking neural networks to learn compact 1-bit graph representations, significantly reducing storage while maintaining or improving performance.

Contribution

It proposes a novel GCL method with spiking neural networks that learns binarized graph representations, offering a balance between efficiency and accuracy.

Findings

SpikeGCL achieves nearly 32x storage compression.

It is comparable to or outperforms state-of-the-art methods.

Theoretical guarantees show comparable expressiveness.

Abstract

While contrastive self-supervised learning has become the de-facto learning paradigm for graph neural networks, the pursuit of higher task accuracy requires a larger hidden dimensionality to learn informative and discriminative full-precision representations, raising concerns about computation, memory footprint, and energy consumption burden (largely overlooked) for real-world applications. This work explores a promising direction for graph contrastive learning (GCL) with spiking neural networks (SNNs), which leverage sparse and binary characteristics to learn more biologically plausible and compact representations. We propose SpikeGCL, a novel GCL framework to learn binarized 1-bit representations for graphs, making balanced trade-offs between efficiency and performance. We provide theoretical guarantees to demonstrate that SpikeGCL has comparable expressiveness with its full-precision counterparts. Experimental results demonstrate that, with nearly 32x representation storage compression, SpikeGCL is either comparable to or outperforms many fancy state-of-the-art supervised and self-supervised methods across several graph benchmarks.