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

arXiv:2305.19306v2 Announce Type: replace-cross
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 …

abstract accuracy arxiv become computation concerns consumption cs.ai cs.lg cs.ne dimensionality energy graph graph neural networks hidden learn memory networks neural networks paradigm precision self-supervised learning spiking neural networks supervised learning type