mlsanityData to 14 Oct 2026

DRAN: A Distribution and Relation Adaptive Network for Spatio-temporal Forecasting

arXiv 2504.01531 ↗First posted 2 Apr 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Spatio-temporal forecasting remains challenging under non-stationary environments because both data distributions and spatial relations evolve over time. Temporal normalization and de-normalization are widely used to mitigate distribution shifts, but they may distort inter-node relationships and thereby impair spatial dependency modeling. To address these issues, we propose the Distribution and Relation Adaptive Network (DRAN) for spatio-temporal forecasting. DRAN incorporates a Spatial Factor Learner (SFL) module, which enables effective normalization and de-normalization while preserving spatial dependencies in spatio-temporal systems. To model evolving spatial interactions, DRAN further proposes the Dynamic-Static Fusion Learner (DSFL) module. DSFL decomposes features into static and dynamic components and adaptively fuses them according to input variability. Experiments on six benchmark datasets show that DRAN outperforms state-of-the-art baselines. Additional analyses demonstrate that SFL consistently reduces spatial-relation distortion across multiple normalization schemes, whereas DSFL captures complementary static and dynamic dependencies and adjusts their contributions according to temporal variability.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 42 of its 108 references that are in the map. First posted on arXiv 2 Apr 2025.

Builds on

42 of 108 references.

References · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  3. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  4. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  5. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
  6. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,136
  7. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  8. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
  9. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 530
  10. 2018T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Predictioncited by 401
  11. 2022Non-stationary Transformers: Exploring the Stationarity in Time Series Forecastingcited by 391
  12. 2016Structured Sequence Modeling with Graph Convolutional Recurrent Networkscited by 275
30 more
  1. 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 261
  2. 2017A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Predictioncited by 245
  3. 2021Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solutioncited by 157
  4. 2023PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Predictioncited by 137
  5. 2023Dish-TS: A General Paradigm for Alleviating Distribution Shift in Time Series Forecastingcited by 93
  6. 2022Spatio-Temporal Meta-Graph Learning for Traffic Forecastingcited by 88
  7. 2024ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEscited by 82
  8. 2021Graph Structure Learning with Variational Information Bottleneckcited by 81
  9. 2022Spatio-Temporal Self-Supervised Learning for Traffic Flow Predictioncited by 77
  10. 2022AirFormer: Predicting Nationwide Air Quality in China with Transformerscited by 73
  11. 2022Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting--Full Versioncited by 59
  12. 2022Scalable Spatiotemporal Graph Neural Networkscited by 52
  13. 2023Time Series Contrastive Learning with Information-Aware Augmentationscited by 52
  14. 2025Battling the Non-stationarity in Time Series Forecasting via Test-time Adaptationcited by 35
  15. 2023SwinRDM: Integrate SwinRNN with Diffusion Model towards High-Resolution and High-Quality Weather Forecastingcited by 32
  16. 2019Deep Learning for Time Series Forecasting: The Electric Load Casecited by 31
  17. 2020Perception and Navigation in Autonomous Systems in the Era of Learning: A Surveycited by 30
  18. 2023Graph Deep Learning for Time Series Forecastingcited by 26
  19. 2022Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecastingcited by 23
  20. 2025Spatiotemporal-aware Trend-Seasonality Decomposition Network for Traffic Flow Forecastingcited by 19
  21. 2024TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Expertscited by 18
  22. 2024Spatio-Spectral Graph Neural Networkscited by 17
  23. 2020Online Learning With Adaptive Rebalancing in Nonstationary Environmentscited by 16
  24. 2021Adaptive Kernel Graph Neural Networkcited by 15
  25. 2024Parametric Augmentation for Time Series Contrastive Learningcited by 12
  26. 2023MemDA: Forecasting Urban Time Series with Memory-based Drift Adaptationcited by 7
  27. 2024U-Mixer: An Unet-Mixer Architecture with Stationarity Correction for Time Series Forecastingcited by 7
  28. 2021Multi Scale Graph Wavenet for Wind Speed Forecastingcited by 3
  29. 2023SAMSGL: Series-Aligned Multi-Scale Graph Learning for Spatio-Temporal Forecastingcited by 1
  30. 2024Caformer: Rethinking Time Series Analysis from Causal Perspectivecited by 1

Built on by

Not cited yet.