mlsanityData to 7 Oct 2026

Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting

arXiv 2208.05233 ↗First posted 10 Aug 2022cs.LGcited by 149

Not on the map. Why?

Abstract (arXiv)

Multivariate Time Series (MTS) forecasting plays a vital role in a wide range of applications. Recently, Spatial-Temporal Graph Neural Networks (STGNNs) have become increasingly popular MTS forecasting methods due to their state-of-the-art performance. However, recent works are becoming more sophisticated with limited performance improvements. This phenomenon motivates us to explore the critical factors of MTS forecasting and design a model that is as powerful as STGNNs, but more concise and efficient. In this paper, we identify the indistinguishability of samples in both spatial and temporal dimensions as a key bottleneck, and propose a simple yet effective baseline for MTS forecasting by attaching Spatial and Temporal IDentity information (STID), which achieves the best performance and efficiency simultaneously based on simple Multi-Layer Perceptrons (MLPs). These results suggest that we can design efficient and effective models as long as they solve the indistinguishability of samples, without being limited to STGNNs.

Key facts. Cited by 149 papers in the map (data through 7 Oct 2026). Builds on 15 of its 24 references that are in the map. First posted on arXiv 10 Aug 2022.

Builds on

15 of 24 references.

References · 15

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  4. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
  5. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,125
  6. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  7. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 820
  8. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 563
  9. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 525
  10. 2019GMAN: A Graph Multi-Attention Network for Traffic Predictioncited by 433
  11. 2021Spectral Temporal Graph Neural Network for Multivariate Time-series Forecastingcited by 298
  12. 2021Discrete Graph Structure Learning for Forecasting Multiple Time Seriescited by 169
3 more
  1. 2022Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecastingcited by 122
  2. 2022Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecastingcited by 117
  3. 2021Historical Inertia: A Neglected but Powerful Baseline for Long Sequence Time-series Forecastingcited by 26

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 19; 2024: 52; 2025: 40; 2026: 38.

149 papers.

Sort:

By area:

  1. 2023Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysiscited by 113
  2. 2024UniST: A Prompt-Empowered Universal Model for Urban Spatio-Temporal Predictioncited by 86
  3. 2023SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecastingcited by 53
  4. 2023ImputeFormer: Low Rankness-Induced Transformers for Generalizable Spatiotemporal Imputationcited by 50
  5. 2023DSformer: A Double Sampling Transformer for Multivariate Time Series Long-term Predictioncited by 49
  6. 2024Revitalizing Multivariate Time Series Forecasting: Learnable Decomposition with Inter-Series Dependencies and Intra-Series Variations Modelingcited by 44
  7. 2023Taming Local Effects in Graph-based Spatiotemporal Forecastingcited by 37
  8. 2023Mixture-of-Linear-Experts for Long-term Time Series Forecastingcited by 29
  9. 2025Temporal Query Network for Efficient Multivariate Time Series Forecastingcited by 29
  10. 2023Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecastingcited by 27
  11. 2023Graph Deep Learning for Time Series Forecastingcited by 26
  12. 2025Exploring the Roles of Large Language Models in Reshaping Transportation Systems: A Survey, Framework, and Roadmapcited by 26
38 more
  1. 2023PETformer: Long-term Time Series Forecasting via Placeholder-enhanced Transformercited by 22
  2. 2023ST-MLP: A Cascaded Spatio-Temporal Linear Framework with Channel-Independence Strategy for Traffic Forecastingcited by 21
  3. 2024GinAR: An End-To-End Multivariate Time Series Forecasting Model Suitable for Variable Missingcited by 20
  4. 2025Merlin: Multi-View Representation Learning for Robust Multivariate Time Series Forecasting with Unfixed Missing Ratescited by 19
  5. 2024Parsimony or Capability? Decomposition Delivers Both in Long-term Time Series Forecastingcited by 18
  6. 2024Heterogeneity-Informed Meta-Parameter Learning for Spatiotemporal Time Series Forecastingcited by 18
  7. 2024FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Predictioncited by 18
  8. 2024RPMixer: Shaking Up Time Series Forecasting with Random Projections for Large Spatial-Temporal Datacited by 17
  9. 2024Spatio-Temporal Few-Shot Learning via Diffusive Neural Network Generationcited by 14
  10. 2023HUTFormer: Hierarchical U-Net Transformer for Long-Term Traffic Forecastingcited by 12
  11. 2023Spatio-Temporal Meta Contrastive Learningcited by 11
  12. 2024Time Evidence Fusion Network: Multi-source View in Long-Term Time Series Forecastingcited by 11
  13. 2024STBench: Assessing the Ability of Large Language Models in Spatio-Temporal Analysiscited by 11
  14. 2025TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecastingcited by 11
  15. 2023Dynamic Frequency Domain Graph Convolutional Network for Traffic Forecastingcited by 10
  16. 2024Minusformer: Improving Time Series Forecasting by Progressively Learning Residualscited by 10
  17. 2024Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph Forecastingcited by 10
  18. 2024Diffusion Transformers as Open-World Spatiotemporal Foundation Modelscited by 10
  19. 2024A Universal Model for Human Mobility Predictioncited by 10
  20. 2024STGformer: Efficient Spatiotemporal Graph Transformer for Traffic Forecastingcited by 9
  21. 2024A Systematic Literature Review of Spatio-Temporal Graph Neural Network Models for Time Series Forecasting and Classificationcited by 9
  22. 2025Learning with Calibration: Exploring Test-Time Computing of Spatio-Temporal Forecastingcited by 9
  23. 2025Selective Learning for Deep Time Series Forecastingcited by 8
  24. 2023EasyDGL: Encode, Train and Interpret for Continuous-time Dynamic Graph Learningcited by 7
  25. 2023STG4Traffic: A Survey and Benchmark of Spatial-Temporal Graph Neural Networks for Traffic Predictioncited by 7
  26. 2023ChatTraffic: Text-to-Traffic Generation via Diffusion Modelcited by 7
  27. 2024DynST: Dynamic Sparse Training for Resource-Constrained Spatio-Temporal Forecastingcited by 7
  28. 2024SpoT-Mamba: Learning Long-Range Dependency on Spatio-Temporal Graphs with Selective State Spacescited by 7
  29. 2024Interpretable Cascading Mixture-of-Experts for Urban Traffic Congestion Predictioncited by 7
  30. 2024On the Integration of Spatial-Temporal Knowledge: A Lightweight Approach to Atmospheric Time Series Forecastingcited by 7
  31. 2024Evaluating the Generalization Ability of Spatiotemporal Model in Urban Scenariocited by 7
  32. 2024UniFlow: A Foundation Model for Unified Urban Spatio-Temporal Flow Predictioncited by 7
  33. 2025Rethinking Multimodality: Optimizing Multimodal Deep Learning for Biomedical Signal Classificationcited by 7
  34. 2024Modeling Temporal Dependencies within the Target for Long-Term Time Series Forecastingcited by 6
  35. 2024Joint Estimation and Prediction of City-wide Delivery Demand: A Large Language Model Empowered Graph-based Learning Approachcited by 6
  36. 2024EasyST: A Simple Framework for Spatio-Temporal Predictioncited by 6
  37. 2024Benchmarking Physics-Informed Time-Series Models for Operational Global Station Weather Forecastingcited by 5
  38. 2024CausalMob: Causal Human Mobility Prediction with LLMs-derived Human Intentions toward Public Eventscited by 5

50 most cited of 149 All 149 (JSON)