mlsanityData to 14 Oct 2026

Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey

arXiv 2303.14483 ↗First posted 25 Mar 2023cs.LGcited by 140

Not on the map. Why?

Abstract (arXiv)

With recent advances in sensing technologies, a myriad of spatio-temporal data has been generated and recorded in smart cities. Forecasting the evolution patterns of spatio-temporal data is an important yet demanding aspect of urban computing, which can enhance intelligent management decisions in various fields, including transportation, environment, climate, public safety, healthcare, and others. Traditional statistical and deep learning methods struggle to capture complex correlations in urban spatio-temporal data. To this end, Spatio-Temporal Graph Neural Networks (STGNN) have been proposed, achieving great promise in recent years. STGNNs enable the extraction of complex spatio-temporal dependencies by integrating graph neural networks (GNNs) and various temporal learning methods. In this manuscript, we provide a comprehensive survey on recent progress on STGNN technologies for predictive learning in urban computing. Firstly, we provide a brief introduction to the construction methods of spatio-temporal graph data and the prevalent deep-learning architectures used in STGNNs. We then sort out the primary application domains and specific predictive learning tasks based on existing literature. Afterward, we scrutinize the design of STGNNs and their combination with some advanced technologies in recent years. Finally, we conclude the limitations of existing research and suggest potential directions for future work.

Key facts. Cited by 140 papers in the map (data through 14 Oct 2026). Builds on 115 of its 274 references that are in the map. First posted on arXiv 25 Mar 2023.

Builds on

115 of 274 references.

References · 115

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  5. 2017Inductive Representation Learning on Large Graphscited by 6,320
  6. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  7. 2018Neural Ordinary Differential Equationscited by 3,779
  8. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  9. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  10. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  11. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  12. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,436
38 more
  1. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  2. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  3. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  4. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,136
  5. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,133
  6. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 829
  7. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
  8. 2016Language Modeling with Gated Convolutional Networkscited by 702
  9. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 566
  10. 2019GMAN: A Graph Multi-Attention Network for Traffic Predictioncited by 434
  11. 2018T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Predictioncited by 401
  12. 2015Recent Advances in Convolutional Neural Networkscited by 360
  13. 2020Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Predictioncited by 325
  14. 2021Spectral Temporal Graph Neural Network for Multivariate Time-series Forecastingcited by 299
  15. 2021Graph Neural Network for Traffic Forecasting: A Surveycited by 261
  16. 2017Gate-Variants of Gated Recurrent Unit (GRU) Neural Networkscited by 242
  17. 2023TSMixer: An All-MLP Architecture for Time Series Forecastingcited by 240
  18. 2019Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networkscited by 229
  19. 2020Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecastingcited by 213
  20. 2021Spatial-Temporal Graph ODE Networks for Traffic Flow Forecastingcited by 210
  21. 2019Deep Learning for Spatio-Temporal Data Mining: A Surveycited by 172
  22. 2021Discrete Graph Structure Learning for Forecasting Multiple Time Seriescited by 171
  23. 2021Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solutioncited by 157
  24. 2021Graph Neural Controlled Differential Equations for Traffic Forecastingcited by 133
  25. 2021ETA Prediction with Graph Neural Networks in Google Mapscited by 130
  26. 2022Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecastingcited by 123
  27. 2021AdaRNN: Adaptive Learning and Forecasting of Time Seriescited by 121
  28. 2022Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecastingcited by 117
  29. 2021SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Predictioncited by 97
  30. 2021Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibrationcited by 92
  31. 2022Spatio-Temporal Meta-Graph Learning for Traffic Forecastingcited by 88
  32. 2019Deep Factors for Forecastingcited by 86
  33. 2023DiffSTG: Probabilistic Spatio-Temporal Graph Forecasting with Denoising Diffusion Modelscited by 81
  34. 2022Spatio-Temporal Self-Supervised Learning for Traffic Flow Predictioncited by 77
  35. 2022AirFormer: Predicting Nationwide Air Quality in China with Transformerscited by 73
  36. 2022Multivariate Time Series Forecasting with Dynamic Graph Neural ODEscited by 72
  37. 2019Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecastingcited by 69
  38. 2020Examining COVID-19 Forecasting using Spatio-Temporal Graph Neural Networkscited by 64

50 most cited of 115 All 115 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 21; 2024: 42; 2025: 45; 2026: 32.

140 papers.

Sort:

By area:

  1. 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
  2. 2023Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysiscited by 117
  3. 2023Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlookcited by 110
  4. 2024Spatial-Temporal Large Language Model for Traffic Predictioncited by 83
  5. 2024A Survey on Diffusion Models for Time Series and Spatio-Temporal Datacited by 67
  6. 2023Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatmentcited by 47
  7. 2024Deep Learning for Cross-Domain Data Fusion in Urban Computing: Taxonomy, Advances, and Outlookcited by 33
  8. 2024A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challengescited by 30
  9. 2024OpenCity: Open Spatio-Temporal Foundation Models for Traffic Predictioncited by 27
  10. 2023From Continuous Dynamics to Graph Neural Networks: Neural Diffusion and Beyondcited by 26
  11. 2023Graph Deep Learning for Time Series Forecastingcited by 26
  12. 2025Foundation Models for Spatio-Temporal Data Science: A Tutorial and Surveycited by 24
38 more
  1. 2024Trajectory Data Management and Mining: A Survey from Deep Learning to the LLM Eracited by 23
  2. 2023Graph Meets LLMs: Towards Large Graph Modelscited by 20
  3. 2023Towards Unifying Diffusion Models for Probabilistic Spatio-Temporal Graph Learningcited by 20
  4. 2023Graph Neural Processes for Spatio-Temporal Extrapolationcited by 19
  5. 2023Uncertainty Quantification via Spatial-Temporal Tweedie Model for Zero-inflated and Long-tail Travel Demand Predictioncited by 19
  6. 2023Towards Generative Modeling of Urban Flow through Knowledge-enhanced Denoising Diffusioncited by 17
  7. 2024BIGCity: A Universal Spatiotemporal Model for Unified Trajectory and Traffic State Data Analysiscited by 16
  8. 2025Improving Time Series Forecasting via Instance-aware Post-hoc Revisioncited by 15
  9. 2024A Survey of Generative Techniques for Spatial-Temporal Data Miningcited by 14
  10. 2023HUTFormer: Hierarchical U-Net Transformer for Long-Term Traffic Forecastingcited by 12
  11. 2024Spatio-Temporal Field Neural Networks for Air Quality Inferencecited by 12
  12. 2024Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph Forecastingcited by 10
  13. 2025Unraveling Spatio-Temporal Foundation Models via the Pipeline Lens: A Comprehensive Reviewcited by 10
  14. 2023Attend Who is Weak: Enhancing Graph Condensation via Cross-Free Adversarial Trainingcited by 9
  15. 2024Continual Learning for Smart City: A Surveycited by 9
  16. 2024ST-LoRA: Low-rank Adaptation for Spatio-Temporal Forecastingcited by 9
  17. 2024A Systematic Literature Review of Spatio-Temporal Graph Neural Network Models for Time Series Forecasting and Classificationcited by 9
  18. 2025Learning with Calibration: Exploring Test-Time Computing of Spatio-Temporal Forecastingcited by 9
  19. 2023Machine Learning for Urban Air Quality Analytics: A Surveycited by 8
  20. 2024Hierarchical Multimodal LLMs with Semantic Space Alignment for Enhanced Time Series Classificationcited by 7
  21. 2024UniFlow: A Foundation Model for Unified Urban Spatio-Temporal Flow Predictioncited by 7
  22. 2023Graph Neural Network for spatiotemporal data: methods and applicationscited by 6
  23. 2023MSGNN: Multi-scale Spatio-temporal Graph Neural Network for Epidemic Forecastingcited by 6
  24. 2024LLM-based Knowledge Pruning for Time Series Data Analytics on Edge-computing Devicescited by 6
  25. 2024A Primer on Temporal Graph Learningcited by 5
  26. 2024SpecSTG: A Fast Spectral Diffusion Framework for Probabilistic Spatio-Temporal Traffic Forecastingcited by 5
  27. 2024Towards Robust Trajectory Representations: Isolating Environmental Confounders with Causal Learningcited by 4
  28. 2024Graph Neural Backdoor: Fundamentals, Methodologies, Applications, and Future Directionscited by 4
  29. 2025Network-wide Freeway Traffic Estimation Using Sparse Sensor Data: A Dirichlet Graph Auto-Encoder Approachcited by 4
  30. 2025Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approachcited by 4
  31. 2025Large Language Model Powered Intelligent Urban Agents: Concepts, Capabilities, and Applicationscited by 4
  32. 2023Rethinking Urban Mobility Prediction: A Super-Multivariate Time Series Forecasting Approachcited by 3
  33. 2024FairSTG: Countering performance heterogeneity via collaborative sample-level optimizationcited by 3
  34. 2024ODMixer: Fine-grained Spatial-temporal MLP for Metro Origin-Destination Predictioncited by 3
  35. 2024ForecastGrapher: Redefining Multivariate Time Series Forecasting with Graph Neural Networkscited by 3
  36. 2024Edge Graph Intelligence: Reciprocally Empowering Edge Networks with Graph Intelligencecited by 3
  37. 2024Navigating Spatio-Temporal Heterogeneity: A Graph Transformer Approach for Traffic Forecastingcited by 3
  38. 2024WardropNet: Traffic Flow Predictions via Equilibrium-Augmented Learningcited by 3

50 most cited of 140 All 140 (JSON)