Modern Structure-Aware Simplicial Spatiotemporal Neural Network

TL;DR

This paper introduces ModernSASST, a novel neural network that leverages simplicial complexes for efficient, high-order spatiotemporal modeling beyond traditional graph neural networks.

Contribution

It is the first to utilize simplicial complex structures with spatiotemporal random walks and parallel TCNs for improved topological feature extraction in large networks.

Findings

Effectively captures high-order topological relationships.

Maintains computational efficiency on large-scale networks.

Outperforms traditional GNN-based models in experiments.

Abstract

Spatiotemporal modeling has evolved beyond simple time series analysis to become fundamental in structural time series analysis. While current research extensively employs graph neural networks (GNNs) for spatial feature extraction with notable success, these networks are limited to capturing only pairwise relationships, despite real-world networks containing richer topological relationships. Additionally, GNN-based models face computational challenges that scale with graph complexity, limiting their applicability to large networks. To address these limitations, we present Modern Structure-Aware Simplicial SpatioTemporal neural network (ModernSASST), the first approach to leverage simplicial complex structures for spatiotemporal modeling. Our method employs spatiotemporal random walks on high-dimensional simplicial complexes and integrates parallelizable Temporal Convolutional Networks to capture high-order topological structures while maintaining computational efficiency. Our source code is publicly available on GitHub\footnote{Code is available at: https://github.com/ComplexNetTSP/ST_RUM.