DAS-GNN: Degree-Aware Spiking Graph Neural Networks for Graph Classification

SunJong Park, Hyeyoon Lee, Kanghyun Choi, Dain Kwon, Jongkil Park, Seongsik Park, Jinho Lee

Keywords: Spiking Neural Network, Graph Neural Network, Graph Classification

TL;DR: DAS-GNN applies spiking neural networks (SNNs) to graph classification using degree-aware group-adaptive neurons and an adaptive threshold mechanism, leading to significant performance improvements over existing methods.

Abstract: The recent integration of spiking neurons into graph neural networks has been gaining much attraction due to its superior energy efficiency. Especially because the sparse connection among graph nodes fits the nature of the spiking neural networks, spiking graph neural networks are considered strong alternatives to vanilla graph neural networks. However, there is still a large performance gap for graph tasks between the spiking neural networks and artificial neural networks. The gaps are especially large when they are adapted to graph classification tasks, where none of the nodes in the test set graphs are connected to the training set graphs. We diagnose the problem as the existence of neurons under starvation, caused by the sparse connections among the nodes and the neurons. To alleviate the problem, we propose DAS-GNN. Based on a set of observations on spiking neurons on graph classification tasks, we devise several techniques to utilize more neurons to deliver meaningful information to the connected neurons. Experiments on diverse datasets show significant improvements compared to the baselines, demonstrating the effectiveness of the DAS-GNN.

Primary Area: applications to neuroscience & cognitive science

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 6448