MCG-STNet: Multi-level Cross-view Graph Convolution Networks for Spatio-Temporal Forecasting

Accurate spatiotemporal prediction is crucial for improving public health and enhancing travel efficiency. However, this task is challenging due to the complex spatiotemporal dependencies between regions. Most methods learn spatial representations without considering spatially skewed distributions, where data from the different regions often exhibit long-tailed distributions, limiting the spatial representation capabilities of the tail distribution regions. To address the above challenges, we propose a novel Multi-level Cross-view Graph Convolution Network (MCG-STNet) for spatiotemporal prediction. The core advantage of MCG-STNet is its ability to jointly capture non-Euclidean dependencies from global and local views while enhancing the spatial feature representation of tail distribution regions through an adaptive cross-view information transfer network. Specifically, we design a fuzzy neural network-based soft clustering approach to capture the functional relationships of regions with long-tail distributed data in the global view, integrating domain expertise to capture spatial dependencies among regional functionalities representations adaptively. We propose an adaptive cross-view information transfer network, allowing for the adaptive extraction of supplementary spatial feature representations from global to local view. Experimental results on five real-world datasets demonstrate that our proposed MCG-STNet outperforms other baselines. Further analysis validates the insights into the effectiveness of MCG-STNet.