SiGNN: A Spike-induced Graph Neural Network for Dynamic Graph Representation Learning
This work addresses a specific bottleneck in dynamic graph learning for applications like social networks or recommendation systems, but it is incremental as it builds on existing SNN and GNN methods.
The paper tackled the problem of limited representational capacity in dynamic graph representation learning when using Spiking Neural Networks (SNNs) by proposing SiGNN, a framework that integrates SNNs with Graph Neural Networks (GNNs) using a Temporal Activation mechanism, resulting in superior performance in node classification tasks on real-world datasets.
In the domain of dynamic graph representation learning (DGRL), the efficient and comprehensive capture of temporal evolution within real-world networks is crucial. Spiking Neural Networks (SNNs), known as their temporal dynamics and low-power characteristic, offer an efficient solution for temporal processing in DGRL task. However, owing to the spike-based information encoding mechanism of SNNs, existing DGRL methods employed SNNs face limitations in their representational capacity. Given this issue, we propose a novel framework named Spike-induced Graph Neural Network (SiGNN) for learning enhanced spatialtemporal representations on dynamic graphs. In detail, a harmonious integration of SNNs and GNNs is achieved through an innovative Temporal Activation (TA) mechanism. Benefiting from the TA mechanism, SiGNN not only effectively exploits the temporal dynamics of SNNs but also adeptly circumvents the representational constraints imposed by the binary nature of spikes. Furthermore, leveraging the inherent adaptability of SNNs, we explore an in-depth analysis of the evolutionary patterns within dynamic graphs across multiple time granularities. This approach facilitates the acquisition of a multiscale temporal node representation.Extensive experiments on various real-world dynamic graph datasets demonstrate the superior performance of SiGNN in the node classification task.