mlsanityData to 14 Oct 2026

AdaST: Adaptive Coupling for Spatial-Temporal Forecasting

arXiv 2609.36119 ↗First posted 28 Sep 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Spatial-temporal (ST) forecasting underpins many real-world systems such as traffic, climate, and energy networks. While existing methods implicitly assume strong spatiotemporal coupling, we observe that real-world ST data exhibits distinct coupling regimes, ranging from temporal-dominated and spatial-dominated to strongly coupled patterns. This mismatch causes current models to suffer from spurious dependencies and degraded performance when one correlation dominates. To overcome this limitation, we aim to dynamically modulate spatial and temporal modeling based on the data's inherent coupling structure. However, three key challenges exist: unknown coupling structure, heterogeneous coupling dynamics, and suboptimal spatial modeling. We propose AdaST, an adaptive ST forecasting framework that tackles these challenges through a decompose-recompose paradigm. AdaST factorizes inputs into components capturing different coupling patterns using heterogeneity-aware experts. Each component is processed by role-aligned modules, and a correlation-informed adaptive recomposer integrates them for final prediction. Extensive experiments confirm that AdaST significantly outperforms state-of-the-art baselines, validating the necessity of an adaptive approach.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 48 references that are in the map. First posted on arXiv 28 Sep 2026.

Builds on

30 of 48 references.

References · 30

  1. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  2. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  3. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,136
  4. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
  5. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 829
  6. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
  7. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 566
  8. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 530
  9. 2019GMAN: A Graph Multi-Attention Network for Traffic Predictioncited by 434
  10. 2021Spectral Temporal Graph Neural Network for Multivariate Time-series Forecastingcited by 299
  11. 2020Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecastingcited by 213
  12. 2019Deep Learning for Spatio-Temporal Data Mining: A Surveycited by 172
18 more
  1. 2021Discrete Graph Structure Learning for Forecasting Multiple Time Seriescited by 171
  2. 2022Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecastingcited by 151
  3. 2022Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecastingcited by 123
  4. 2023Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysiscited by 117
  5. 2024A Survey on Diffusion Models for Time Series and Spatio-Temporal Datacited by 67
  6. 2021KVT: k-NN Attention for Boosting Vision Transformerscited by 65
  7. 2023Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatmentcited by 47
  8. 2021Long-Range Transformers for Dynamic Spatiotemporal Forecastingcited by 46
  9. 2018Robust Graph Learning from Noisy Datacited by 34
  10. 2021Historical Inertia: A Neglected but Powerful Baseline for Long Sequence Time-series Forecastingcited by 26
  11. 2023Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecastingcited by 19
  12. 2025Spatiotemporal-aware Trend-Seasonality Decomposition Network for Traffic Flow Forecastingcited by 19
  13. 2024Heterogeneity-Informed Meta-Parameter Learning for Spatiotemporal Time Series Forecastingcited by 18
  14. 2023STAEformer: Spatio-Temporal Adaptive Embedding Makes Vanilla Transformer SOTA for Traffic Forecastingcited by 12
  15. 2024Deep Coupling Network For Multivariate Time Series Forecastingcited by 6
  16. 2025TyphoFormer: Language-Augmented Transformer for Accurate Typhoon Track Forecastingcited by 6
  17. 2026GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?cited by 4
  18. 2024ST-FiT: Inductive Spatial-Temporal Forecasting with Limited Training Datacited by 3

Built on by

Not cited yet.