mlsanityData to 7 Oct 2026

A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection

arXiv 2307.03759 ↗First posted 7 Jul 2023cs.LG cs.AIcited by 145

Not on the map. Why?

Abstract (arXiv)

Time series are the primary data type used to record dynamic system measurements and generated in great volume by both physical sensors and online processes (virtual sensors). Time series analytics is therefore crucial to unlocking the wealth of information implicit in available data. With the recent advancements in graph neural networks (GNNs), there has been a surge in GNN-based approaches for time series analysis. These approaches can explicitly model inter-temporal and inter-variable relationships, which traditional and other deep neural network-based methods struggle to do. In this survey, we provide a comprehensive review of graph neural networks for time series analysis (GNN4TS), encompassing four fundamental dimensions: forecasting, classification, anomaly detection, and imputation. Our aim is to guide designers and practitioners to understand, build applications, and advance research of GNN4TS. At first, we provide a comprehensive task-oriented taxonomy of GNN4TS. Then, we present and discuss representative research works and introduce mainstream applications of GNN4TS. A comprehensive discussion of potential future research directions completes the survey. This survey, for the first time, brings together a vast array of knowledge on GNN-based time series research, highlighting foundations, practical applications, and opportunities of graph neural networks for time series analysis.

Key facts. Cited by 145 papers in the map (data through 7 Oct 2026). Builds on 186 of its 387 references that are in the map. First posted on arXiv 7 Jul 2023.

Builds on

186 of 387 references.

References · 186

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Graph Attention Networkscited by 8,854
  5. 2017Inductive Representation Learning on Large Graphscited by 6,284
  6. 2018Neural Ordinary Differential Equationscited by 3,733
  7. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  8. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  9. 2023A Survey of Large Language Modelscited by 2,537
  10. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  11. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  12. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,125
38 more
  1. 2019An Introduction to Variational Autoencoderscited by 997
  2. 2021E(n) Equivariant Graph Neural Networkscited by 951
  3. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  4. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  5. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 820
  6. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 813
  7. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 663
  8. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 583
  9. 2018Deep learning for time series classification: a reviewcited by 575
  10. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 563
  11. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 548
  12. 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 540
  13. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 525
  14. 2016Temporal Convolutional Networks for Action Segmentation and Detectioncited by 504
  15. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 503
  16. 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 501
  17. 2022Transformers in Time Series: A Surveycited by 489
  18. 2018Hypergraph Neural Networkscited by 482
  19. 2020Time Series Forecasting With Deep Learning: A Surveycited by 457
  20. 2020A Transformer-based Framework for Multivariate Time Series Representation Learningcited by 449
  21. 2019GMAN: A Graph Multi-Attention Network for Traffic Predictioncited by 433
  22. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  23. 2018The UCR Time Series Archivecited by 421
  24. 2019Diffusion Improves Graph Learningcited by 414
  25. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 407
  26. 2019Hyperbolic Graph Convolutional Neural Networkscited by 400
  27. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 387
  28. 2018GAIN: Missing Data Imputation using Generative Adversarial Netscited by 349
  29. 2019ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernelscited by 336
  30. 2018The UEA multivariate time series classification archive, 2018cited by 330
  31. 2018Session-based Recommendation with Graph Neural Networkscited by 312
  32. 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 300
  33. 2021Spectral Temporal Graph Neural Network for Multivariate Time-series Forecastingcited by 298
  34. 2021Graph Self-Supervised Learning: A Surveycited by 289
  35. 2015Diffusion-Convolutional Neural Networkscited by 268
  36. 2021Graph Neural Network for Traffic Forecasting: A Surveycited by 260
  37. 2017A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Predictioncited by 245
  38. 2019Hyperbolic Graph Neural Networkscited by 244

50 most cited of 186 All 186 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 14; 2024: 50; 2025: 47; 2026: 34.

145 papers.

Sort:

By area:

  1. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 680
  2. 2024Deep Time Series Models: A Comprehensive Survey and Benchmarkcited by 191
  3. 2023Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlookcited by 109
  4. 2024A Survey on Diffusion Models for Time Series and Spatio-Temporal Datacited by 66
  5. 2023ImputeFormer: Low Rankness-Induced Transformers for Generalizable Spatiotemporal Imputationcited by 50
  6. 2024Position: What Can Large Language Models Tell Us about Time Series Analysiscited by 47
  7. 2025ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Datasetcited by 35
  8. 2024TSI-Bench: Benchmarking Time Series Imputationcited by 33
  9. 2024Graph Transformers: A Surveycited by 32
  10. 2024Universal Time-Series Representation Learning: A Surveycited by 28
  11. 2023From Continuous Dynamics to Graph Neural Networks: Neural Diffusion and Beyondcited by 26
  12. 2023Graph Deep Learning for Time Series Forecastingcited by 26
38 more
  1. 2023Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Datacited by 23
  2. 2023ST-MLP: A Cascaded Spatio-Temporal Linear Framework with Channel-Independence Strategy for Traffic Forecastingcited by 21
  3. 2023Graph Meets LLMs: Towards Large Graph Modelscited by 19
  4. 2025Foundation Models for Time Series: A Surveycited by 19
  5. 2023Correlation-aware Spatial-Temporal Graph Learning for Multivariate Time-series Anomaly Detectioncited by 17
  6. 2023Towards Data-centric Graph Machine Learning: Review and Outlookcited by 15
  7. 2024Graph-based Forecasting with Missing Data through Spatiotemporal Downsamplingcited by 15
  8. 2025Deep Learning Advancements in Anomaly Detection: A Comprehensive Surveycited by 15
  9. 2024Graph Neural Networks for Tabular Data Learning: A Survey with Taxonomy and Directionscited by 13
  10. 2025A Survey on Diffusion Models for Anomaly Detectioncited by 13
  11. 2024Online GNN Evaluation Under Test-time Graph Distribution Shiftscited by 12
  12. 2024Time Evidence Fusion Network: Multi-source View in Long-Term Time Series Forecastingcited by 11
  13. 2025Relational Conformal Prediction for Correlated Time Seriescited by 11
  14. 2024Graph Spatiotemporal Process for Multivariate Time Series Anomaly Detection with Missing Valuescited by 10
  15. 2024Scalable Spatiotemporal Prediction with Bayesian Neural Fieldscited by 10
  16. 2024Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph Forecastingcited by 10
  17. 2025Learning Soft Sparse Shapes for Efficient Time-Series Classificationcited by 10
  18. 2023BayOTIDE: Bayesian Online Multivariate Time series Imputation with functional decompositioncited by 9
  19. 2024A Systematic Literature Review of Spatio-Temporal Graph Neural Network Models for Time Series Forecasting and Classificationcited by 9
  20. 2025Vision-Enhanced Time Series Forecasting via Latent Diffusion Modelscited by 9
  21. 2025Learning with Calibration: Exploring Test-Time Computing of Spatio-Temporal Forecastingcited by 9
  22. 2024Graph-based Virtual Sensing from Sparse and Partial Multivariate Observationscited by 8
  23. 2024Higher-order Spatio-temporal Physics-incorporated Graph Neural Network for Multivariate Time Series Imputationcited by 8
  24. 2024Cluster-wise Graph Transformer with Dual-granularity Kernelized Attentioncited by 8
  25. 2025Anomaly Detection and Generation with Diffusion Models: A Surveycited by 8
  26. 2024Graph Neural Networks for Virtual Sensing in Complex Systems: Addressing Heterogeneous Temporal Dynamicscited by 7
  27. 2025AutoHFormer: Efficient Hierarchical Autoregressive Transformer for Time Series Predictioncited by 7
  28. 2024Physics-Enhanced Graph Neural Networks For Soft Sensing in Industrial Internet of Thingscited by 6
  29. 2024Task-oriented Time Series Imputation Evaluation via Generalized Representerscited by 6
  30. 2025Over-squashing in Spatiotemporal Graph Neural Networkscited by 6
  31. 2025mTSBench: Benchmarking Multivariate Time Series Anomaly Detection and Model Selection at Scalecited by 6
  32. 2024SpecSTG: A Fast Spectral Diffusion Framework for Probabilistic Spatio-Temporal Traffic Forecastingcited by 5
  33. 2024A Survey of Transformer Enabled Time Series Synthesiscited by 5
  34. 2024How Deep is your Guess? A Fresh Perspective on Deep Learning for Medical Time-Series Imputationcited by 5
  35. 2024Time Series Analysis for Education: Methods, Applications, and Future Directionscited by 5
  36. 2024OXYGENERATOR: Reconstructing Global Ocean Deoxygenation Over a Century with Deep Learningcited by 4
  37. 2024Temporal Source Recovery for Time-Series Source-Free Unsupervised Domain Adaptationcited by 4
  38. 2026Unlocking the Value of Text: Event-Driven Reasoning and Multi-Level Alignment for Time Series Forecastingcited by 4

50 most cited of 145 All 145 (JSON)