mlsanityData to 7 Oct 2026

Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks

arXiv 2005.11650 ↗First posted 24 May 2020cs.LG stat.MLcited by 563

Not on the map. Why?

Abstract (arXiv)

Modeling multivariate time series has long been a subject that has attracted researchers from a diverse range of fields including economics, finance, and traffic. A basic assumption behind multivariate time series forecasting is that its variables depend on one another but, upon looking closely, it is fair to say that existing methods fail to fully exploit latent spatial dependencies between pairs of variables. In recent years, meanwhile, graph neural networks (GNNs) have shown high capability in handling relational dependencies. GNNs require well-defined graph structures for information propagation which means they cannot be applied directly for multivariate time series where the dependencies are not known in advance. In this paper, we propose a general graph neural network framework designed specifically for multivariate time series data. Our approach automatically extracts the uni-directed relations among variables through a graph learning module, into which external knowledge like variable attributes can be easily integrated. A novel mix-hop propagation layer and a dilated inception layer are further proposed to capture the spatial and temporal dependencies within the time series. The graph learning, graph convolution, and temporal convolution modules are jointly learned in an end-to-end framework. Experimental results show that our proposed model outperforms the state-of-the-art baseline methods on 3 of 4 benchmark datasets and achieves on-par performance with other approaches on two traffic datasets which provide extra structural information.

Key facts. Cited by 563 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 48; 2022: 85; 2023: 129; 2024: 112; 2025: 111; 2026: 78.

563 papers.

Sort:

By area:

  1. 2021Graph Neural Network for Traffic Forecasting: A Surveycited by 260
  2. 2024Deep Time Series Models: A Comprehensive Survey and Benchmarkcited by 191
  3. 2021Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learningcited by 175
  4. 2022Graph Neural Networks for Graphs with Heterophily: A Surveycited by 175
  5. 2023Frequency-domain MLPs are More Effective Learners in Time Series Forecastingcited by 170
  6. 2021Discrete Graph Structure Learning for Forecasting Multiple Time Seriescited by 169
  7. 2022Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structurescited by 158
  8. 2021Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solutioncited by 156
  9. 2022Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecastingcited by 149
  10. 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
  11. 2023Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Surveycited by 140
  12. 2023PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Predictioncited by 135
38 more
  1. 2022GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoningcited by 128
  2. 2023FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspectivecited by 126
  3. 2022Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecastingcited by 122
  4. 2021PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Modelscited by 118
  5. 2022Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecastingcited by 117
  6. 2023Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysiscited by 113
  7. 2021Graph-Guided Network for Irregularly Sampled Multivariate Time Seriescited by 110
  8. 2021Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoTcited by 104
  9. 2023The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecastingcited by 100
  10. 2023Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospectscited by 97
  11. 2021Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networkscited by 93
  12. 2022Spatio-Temporal Meta-Graph Learning for Traffic Forecastingcited by 88
  13. 2024SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time seriescited by 81
  14. 2023Time Series as Images: Vision Transformer for Irregularly Sampled Time Seriescited by 79
  15. 2024SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusioncited by 75
  16. 2021DL-Traff: Survey and Benchmark of Deep Learning Models for Urban Traffic Predictioncited by 73
  17. 2022AirFormer: Predicting Nationwide Air Quality in China with Transformerscited by 73
  18. 2022Multivariate Time Series Forecasting with Dynamic Graph Neural ODEscited by 72
  19. 2021Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detectioncited by 67
  20. 2022When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learningcited by 64
  21. 2022Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting--Full Versioncited by 59
  22. 2025A Comprehensive Survey of Deep Learning for Multivariate Time Series Forecasting: A Channel Strategy Perspectivecited by 58
  23. 2022Forecast Evaluation for Data Scientists: Common Pitfalls and Best Practicescited by 54
  24. 2025Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baselinecited by 54
  25. 2022Scalable Spatiotemporal Graph Neural Networkscited by 52
  26. 2023ImputeFormer: Low Rankness-Induced Transformers for Generalizable Spatiotemporal Imputationcited by 50
  27. 2023MSGNet: Learning Multi-Scale Inter-Series Correlations for Multivariate Time Series Forecastingcited by 50
  28. 2021AutoCTS: Automated Correlated Time Series Forecasting -- Extended Versioncited by 48
  29. 2022PanGu-Coder: Program Synthesis with Function-Level Language Modelingcited by 47
  30. 2023Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatmentcited by 47
  31. 2021Long-Range Transformers for Dynamic Spatiotemporal Forecastingcited by 46
  32. 2022STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Predictioncited by 45
  33. 2024Frequency Adaptive Normalization For Non-stationary Time Series Forecastingcited by 45
  34. 2022Multi-Scale Adaptive Graph Neural Network for Multivariate Time Series Forecastingcited by 42
  35. 2022Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Seriescited by 42
  36. 2023TimeMAE: Self-Supervised Representations of Time Series with Decoupled Masked Autoencoderscited by 42
  37. 2021Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signalscited by 41
  38. 2022Spatial-Temporal Hypergraph Self-Supervised Learning for Crime Predictioncited by 39

50 most cited of 563 All 563 (JSON)