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

• URL: http://arxiv.org/abs/2509.02217v1
• Date: Tue, 02 Sep 2025 11:37:08 GMT
• Title: ST-Hyper: Learning High-Order Dependencies Across Multiple Spatial-Temporal Scales for Multivariate Time Series Forecasting
• Authors: Binqing Wu, Jianlong Huang, Zongjiang Shang, Ling Chen,
• Abstract summary: We propose ST-Hyper to model the high-order dependencies across multiple spatial-temporal scales.<n>Specifically, we introduce a Spatial-Temporal Pyramid Modeling (STPM) module to extract features at multiple ST-scales.<n>We also introduce an Adaptive Hypergraph Modeling (AHM) module that learns a sparse hypergraph to capture robust high-order dependencies among features.
• Score: 10.473579316054186
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Leveraging Multivariate Long-Term History Representation for Time Series Forecasting [6.661358934189792]
  We propose a framework called Long-term Multivariate Representation (LMHR) for MTS forecasting.<n>LMHR encodes the long-term history into segment-level contextual representations and reduces point-level noise.<n>It consistently improves prediction accuracy by 9.8% on the top 10% of rapidly changing patterns.
  arXiv  Detail & Related papers  (2025-05-20T03:46:36Z)
• STDHL: Spatio-Temporal Dynamic Hypergraph Learning for Wind Power Forecasting [5.003934238878358]
  We present a dynamic hypergraph learning (STDHL) model to represent spatial features among wind farms.<n>STDHL model incorporates novel dynamic hypergraph convolutional layer to model dynamic spatial correlations and grouped temporal convolutional layer for channel-independent temporal modeling.
  arXiv  Detail & Related papers  (2024-12-16T02:43:29Z)
• Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting [5.431115840202783]
  We propose Adaptive Multi-Scale Hypergraph Transformer (Ada-MSHyper) for time series forecasting. Ada-MSHyper achieves state-of-the-art performance, reducing prediction errors by an average of 4.56%, 10.38%, and 4.97% in MSE for long-range, short-range, and ultra-long-range time series forecasting.
  arXiv  Detail & Related papers  (2024-10-31T14:51:09Z)
• UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecasting [98.12558945781693]
  We propose a transformer-based model UniTST containing a unified attention mechanism on the flattened patch tokens. Although our proposed model employs a simple architecture, it offers compelling performance as shown in our experiments on several datasets for time series forecasting.
  arXiv  Detail & Related papers  (2024-06-07T14:39:28Z)
• TSCMamba: Mamba Meets Multi-View Learning for Time Series Classification [13.110156202816112]
  We propose a novel multi-view approach to capture patterns with properties like shift equivariance.<n>Our method integrates diverse features, including spectral, temporal, local, and global features, to obtain rich, complementary contexts for TSC.<n>Our approach achieves average accuracy improvements of 4.01-6.45% and 7.93% respectively, over leading TSC models.
  arXiv  Detail & Related papers  (2024-06-06T18:05:10Z)
• MSHyper: Multi-Scale Hypergraph Transformer for Long-Range Time Series Forecasting [5.431115840202783]
  We propose a Multi-Scale Hypergraph Transformer (MSHyper) framework to promote more comprehensive pattern interaction modeling.<n>MSHyper achieves state-of-the-art (SOTA) performance across various settings.
  arXiv  Detail & Related papers  (2024-01-17T15:12:11Z)
• A Decoupled Spatio-Temporal Framework for Skeleton-based Action Segmentation [89.86345494602642]
  Existing methods are limited in weak-temporal modeling capability. We propose a Decoupled Scoupled Framework (DeST) to address the issues. DeST significantly outperforms current state-of-the-art methods with less computational complexity.
  arXiv  Detail & Related papers  (2023-12-10T09:11:39Z)
• Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data [50.84488941336865]
  We propose a novel method called Fully- Spatial-Temporal Graph Neural Network (FC-STGNN) For graph construction, we design a decay graph to connect sensors across all timestamps based on their temporal distances. For graph convolution, we devise FC graph convolution with a moving-pooling GNN layer to effectively capture the ST dependencies for learning effective representations.
  arXiv  Detail & Related papers  (2023-09-11T08:44:07Z)
• Multi-scale Attention Flow for Probabilistic Time Series Forecasting [68.20798558048678]
  We propose a novel non-autoregressive deep learning model, called Multi-scale Attention Normalizing Flow(MANF) Our model avoids the influence of cumulative error and does not increase the time complexity. Our model achieves state-of-the-art performance on many popular multivariate datasets.
  arXiv  Detail & Related papers  (2022-05-16T07:53:42Z)
• Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs [65.18780403244178]
  We propose a continuous model to forecast Multivariate Time series with dynamic Graph neural Ordinary Differential Equations (MTGODE) Specifically, we first abstract multivariate time series into dynamic graphs with time-evolving node features and unknown graph structures. Then, we design and solve a neural ODE to complement missing graph topologies and unify both spatial and temporal message passing.
  arXiv  Detail & Related papers  (2022-02-17T02:17:31Z)
• Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition [79.33539539956186]
  We propose a simple method to disentangle multi-scale graph convolutions and a unified spatial-temporal graph convolutional operator named G3D. By coupling these proposals, we develop a powerful feature extractor named MS-G3D based on which our model outperforms previous state-of-the-art methods on three large-scale datasets.
  arXiv  Detail & Related papers  (2020-03-31T11:28:25Z)
• Convolutional Tensor-Train LSTM for Spatio-temporal Learning [116.24172387469994]
  We propose a higher-order LSTM model that can efficiently learn long-term correlations in the video sequence. This is accomplished through a novel tensor train module that performs prediction by combining convolutional features across time. Our results achieve state-of-the-art performance-art in a wide range of applications and datasets.
  arXiv  Detail & Related papers  (2020-02-21T05:00:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.