ST-Hyper: Learning High-Order Dependencies Across Multiple Spatial-Temporal Scales for Multivariate Time Series Forecasting

2025/09/02 by Binqing Wu, Wu, Binqing, Jianlong Huang +5
Computer Science · Decision Sciences · Engineering · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Forecasting Techniques and Applications #Machine Learning (cs.LG) #Time Series Analysis and Forecasting #Traffic Prediction and Management Techniques

paper · pdf · doi:10.48550/arxiv.2509.02217

openalex publication_date 2025/09/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In multivariate time series (MTS) forecasting, many deep learning based methods have been proposed for modeling dependencies at multiple spatial (inter-variate) or temporal (intra-variate) scales. However, existing methods may fail to model dependencies across multiple spatial-temporal scales (ST-scales, i.e., scales that jointly consider spatial and temporal scopes). In this work, we propose ST-Hyper to model the high-order dependencies across multiple ST-scales through adaptive hypergraph modeling. Specifically, we introduce a Spatial-Temporal Pyramid Modeling (STPM) module to extract features at multiple ST-scales. Furthermore, we introduce an Adaptive Hypergraph Modeling (AHM) module that learns a sparse hypergraph to capture robust high-order dependencies among features. In addition, we interact with these features through tri-phase hypergraph propagation, which can comprehensively capture multi-scale spatial-temporal dynamics. Experimental results on six real-world MTS datasets demonstrate that ST-Hyper achieves the state-of-the-art performance, outperforming the best baselines with an average MAE reduction of 3.8% and 6.8% for long-term and short-term forecasting, respectively.

Citations

• Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting
• CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns
• MSGNet: Learning Multi-Scale Inter-Series Correlations for Multivariate Time Series Forecasting
• FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective
• WeatherGNN: Exploiting Meteo- and Spatial-Dependencies for Local Numerical Weather Prediction Bias-Correction
• Graph-based Time Series Clustering for End-to-End Hierarchical Forecasting
• PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction
• AirFormer: Predicting Nationwide Air Quality in China with Transformers
• A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
• Spatio-Temporal Meta-Graph Learning for Traffic Forecasting
• Are Transformers Effective for Time Series Forecasting?
• FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting
• Group-Aware Graph Neural Network for Nationwide City Air Quality Forecasting
• Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting
• Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting
• Hypergraph Convolution and Hypergraph Attention
• Hypergraph convolution and hypergraph attention
• Graph Attention Networks
• Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks
• Memory Networks

Related

• Multi-Scale Adaptive Graph Neural Network for Multivariate Time Series Forecasting
• HyperIMTS: Hypergraph Neural Network for Irregular Multivariate Time Series Forecasting
• Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting
• MSHyper: Multi-Scale Hypergraph Transformer for Long-Range Time Series Forecasting
• Scale-Aware Neural Architecture Search for Multivariate Time Series Forecasting