STG-Mamba: Spatial-Temporal Graph Learning via Selective State Space Model

arXiv:2403.12418v1 Announce Type: new
Abstract: Spatial-Temporal Graph (STG) data is characterized as dynamic, heterogenous, and non-stationary, leading to the continuous challenge of spatial-temporal graph learning. In the past few years, various GNN-based methods have been proposed to solely focus on mimicking the relationships among node individuals of the STG network, ignoring the significance of modeling the intrinsic features that exist in STG system over time. In contrast, modern Selective State Space Models (SSSMs) present a new approach which treat STG …

abstract arxiv challenge continuous cs.ai cs.lg data dynamic focus gnn graph graph learning mamba network node relationships space spatial state temporal type via