Spiking Graph Convolutional Networks

Zulun Zhu, Jiaying Peng, Jintang Li, Liang Chen, Qi Yu, Zibin Zheng

Keywords: Graph, spike, energy, neural network

Abstract: Graph Convolutional Networks (GCNs) achieve an impressive performance due to the remarkable representation ability in learning the graph information. However, GCNs, when implemented on a deep network, require expensive computation power, which makes them difficult to be deployed on battery-powered devices. In contrast, Spiking Neural Networks (SNNs), which perform a bio-fidelity inference process, offer an energy-efficient neural architecture. In this work, we propose SpikingGCN, an end-to-end framework that aims to integrate the embedding of GCNs with the biofidelity characteristics of SNNs. In particular, the original graph data are encoded into spike trains based on the incorporation of graph convolution. We further model biological information processing by utilizing a fully connected layer combined with neuron nodes. In a wide range of scenarios, including citation networks, image graph classification, and recommender systems, our experimental results show that the proposed method could gain competitive performance against state-of-art (SOTA) approaches. Furthermore, we show that SpikingGCN on a neuromorphic chip can bring a clear advantage of energy efficiency into graph data analysis, which demonstrates its great potential to construct environment-friendly machine learning models.

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2205.02767/code)