A Dynamic Stiefel Graph Neural Network for Efficient Spatio-Temporal Time Series Forecasting
This addresses the problem of efficient and effective spatio-temporal forecasting for applications like traffic or weather prediction, but it appears incremental as it builds on existing graph neural network approaches.
The paper tackles the challenge of accurately forecasting spatio-temporal time series by proposing the Dynamic Spatio-Temporal Stiefel Graph Neural Network (DST-SGNN), which outperforms state-of-the-art methods on seven datasets while maintaining low computational costs.
Spatio-temporal time series (STTS) have been widely used in many applications. However, accurately forecasting STTS is challenging due to complex dynamic correlations in both time and space dimensions. Existing graph neural networks struggle to balance effectiveness and efficiency in modeling dynamic spatio-temporal relations. To address this problem, we propose the Dynamic Spatio-Temporal Stiefel Graph Neural Network (DST-SGNN) to efficiently process STTS. For DST-SGNN, we first introduce the novel Stiefel Graph Spectral Convolution (SGSC) and Stiefel Graph Fourier Transform (SGFT). The SGFT matrix in SGSC is constrained to lie on the Stiefel manifold, and SGSC can be regarded as a filtered graph spectral convolution. We also propose the Linear Dynamic Graph Optimization on Stiefel Manifold (LDGOSM), which can efficiently learn the SGFT matrix from the dynamic graph and significantly reduce the computational complexity. Finally, we propose a multi-layer SGSC (MSGSC) that efficiently captures complex spatio-temporal correlations. Extensive experiments on seven spatio-temporal datasets show that DST-SGNN outperforms state-of-the-art methods while maintaining relatively low computational costs.