DyMGCN: Dynamic Multi-Graph Convolution Networks for Spatio-Temporal Forecasting

Numerous pervasive applications, such as guiding outdoor health activities and allocating public transportation resources, rely on accurate predictions. Intuitively, the readings of a region may be influenced by various relational patterns with other regions, which can be revealed by exploring the complex spatial correlations between them. Recent studies have demonstrated the potential for improving spatiotemporal prediction performance by modeling various spatial correlations as graphs and capturing spatial dependencies using parallel multi-graph convolution network methods. However, these methods cannot directly learn dynamic spatial dependencies across graphs, leading to insufficient utilization of spatial contextual information. To address the above issues, we propose a novel dynamic multi-graph convolution networks, named DyMGCN, for spatiotemporal forecasting. Specifically, we introduce fuzzy theory, which combines fuzzy systems and neural networks, to learn uncertain dynamic dependencies across graphs and represent them as weight matrices. We further improve the understanding and utilization of spatial correlations by capturing stable long-term autocorrelations between regions. Many experiments on multiple real-world spatiotemporal datasets demonstrate that our proposed DyMGCN outperforms other baselines in spatiotemporal prediction methods.