Long-term Spatio-Temporal Forecasting using Spectral Graph Neural Networks

Xiang Li, Yanping Zheng, Zhewei Wei, Ye Yuan

Abstract: Multivariate Time Series (MTS) forecasting is vital in various practical applications. Current research in this area is categorized into Spatial-Temporal Forecasting (STF) and Long-term Time Series Forecasting (LTSF). While these tasks share similarities, the methods and benchmarks used differ significantly. Spatio-Temporal Graph Neural Networks (STGNNs) excel at modeling interrelationships in STF tasks but face difficulties with long sequence inputs due to inefficient training. In contrast, LTSF models handle long sequences well but struggle with capturing complex variable interrelationships. This paper proposes the Spectral Spatio-Temporal Graph Neural Network (S2GNN) to address these challenges, proposing a framework capable of handling long-term spatiotemporal forecasting. S2GNN leverages a decoupled GNN along with an MLP architecture to ensure efficiency. Specifically, it employs spectral GNNs for global feature extraction on an adaptive graph structure; the visualization of the filters resembles a band-rejection shape, indicating the presence of both homophilic and heterophilic relationships between nodes. Additionally, we introduce scale-adaptive node embeddings and cross-correlation embeddings for better differentiation between similar temporal patterns. Extensive experiments on eight public datasets, including STF and LTSF, demonstrate that S2GNN consistently outperforms state-of-the-art models across diverse prediction tasks. Code is available at https://github.com/superarthurlx/S2GNN.

External IDs:dblp:conf/ijcnn/LiZWY25