Efficient Spiking Variational Graph Autoencoders for Unsupervised Graph Representation Learning Tasks

Hanxuan Yang, Qingchao Kong, Ruike Zhang, Wenji Mao

Abstract: Variational graph autoencoders (VGAEs) are popular artificial neural network (ANN)-based models for unsupervised graph representation learning tasks, including link prediction and graph generation, which are critical in many real-world applications. Despite the promising results of VGAEs on these tasks, existing VGAEs typically suffer from extremely high energy cost. Recently, spiking neural networks (SNNs) have emerged as energy-efficient alternatives for applications on graph-structured data, while they are typically trained under supervised settings using label information. To leverage the energy efficiency of SNNs for unsupervised graph learning tasks, in this article, we propose an SNN-based spiking VGAE (S-VGAE) to efficiently learn spiking node representations using graph structural information. We conduct extensive experiments on two typical unsupervised graph learning tasks using benchmark datasets. The results demonstrate that our method can significantly save energy consumption with little or no loss on performances compared to both ANN- and SNN-based baselines.