Graph Neural Network for Traffic Forecasting: A Survey

2021/01/31 by Weiwei Jiang, Jiayun Luo · 44 citations
Computer Science · Engineering · Social Sciences · #Human Mobility and Location-Based Analysis #Traffic Prediction and Management Techniques #Transportation Planning and Optimization #cs.AI #cs.LG

paper · pdf · doi:10.1016/j.eswa.2022.117921

published as Expert Systems with Applications Volume, vol. 207, 30 November 2022, 117921

arxiv created 2022/02/22 · openalex publication_date 2022/06/23 · crossref created 2022/06/23 · arxiv updated 2022/07/08 · crossref issued 2022/11/01 · crossref published 2022/11/01 · crossref published-print 2022/11/01 · openalex created_date 2025/10/10 · crossref deposited 2025/10/17 · crossref indexed 2026/07/29 · openalex updated_date 2026/07/31

Abstract

Traffic forecasting is important for the success of intelligent transportation systems. Deep learning models, including convolution neural networks and recurrent neural networks, have been extensively applied in traffic forecasting problems to model spatial and temporal dependencies. In recent years, to model the graph structures in transportation systems as well as contextual information, graph neural networks have been introduced and have achieved state-of-the-art performance in a series of traffic forecasting problems. In this survey, we review the rapidly growing body of research using different graph neural networks, e.g. graph convolutional and graph attention networks, in various traffic forecasting problems, e.g. road traffic flow and speed forecasting, passenger flow forecasting in urban rail transit systems, and demand forecasting in ride-hailing platforms. We also present a comprehensive list of open data and source resources for each problem and identify future research directions. To the best of our knowledge, this paper is the first comprehensive survey that explores the application of graph neural networks for traffic forecasting problems. We have also created a public GitHub repository where the latest papers, open data, and source resources will be updated.

Citations

• Deep Convolutional Networks on Graph-Structured Data
• Diffusion-Convolutional Neural Networks
• Variational Graph Auto-Encoders
• Neural Message Passing for Quantum Chemistry
• Few-Shot Learning with Graph Neural Networks
• Graph-Based Deep Modeling and Real Time Forecasting of Sparse Spatio-Temporal Data
• Machine Learning for Spatiotemporal Sequence Forecasting: A Survey
• Efficient Metropolitan Traffic Prediction Based on Graph Recurrent Neural Network
• Graph Neural Networks: A Review of Methods and Applications
• Graph Hierarchical Convolutional Recurrent Neural Network (GHCRNN) for Vehicle Condition Prediction
• ST-UNet: A Spatio-Temporal U-Network for Graph-structured Time Series Modeling
• A Hybrid Traffic Speed Forecasting Approach Integrating Wavelet Transform and Motif-based Graph Convolutional Recurrent Neural Network
• Graph WaveNet for Deep Spatial-Temporal Graph Modeling
• Explainability Techniques for Graph Convolutional Networks
• GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs
• Detecting Functionality-Specific Vulnerabilities via Retrieving Individual Functionality-Equivalent APIs in Open-Source Repositories
• Learning to Propagate for Graph Meta-Learning
• GNNExplainer: Generating Explanations for Graph Neural Networks
• Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting
• GMAN: A Graph Multi-Attention Network for Traffic Prediction
• Spatial-Temporal Transformer Networks for Traffic Flow Forecasting
• Constructing Geographic and Long-term Temporal Graph for Traffic Forecasting
• A3T-GCN: Attention Temporal Graph Convolutional Network for Traffic Forecasting
• Spatial-Temporal Dynamic Graph Attention Networks for Ride-hailing Demand Prediction
• Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting
• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
• Auto-STGCN: Autonomous Spatial-Temporal Graph Convolutional Network Search Based on Reinforcement Learning and Existing Research Results
• AST-GCN: Attribute-Augmented Spatiotemporal Graph Convolutional Network for Traffic Forecasting
• Coupled Layer-wise Graph Convolution for Transportation Demand Prediction
• Uncertainty Intervals for Graph-based Spatio-Temporal Traffic Prediction
• Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting
• Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting
• Graph neural networks: A review of methods and applications
• A Comprehensive Survey on Graph Neural Networks
• Targeted Branching for the Maximum Independent Set Problem Using Graph Neural Networks
• Generative Adversarial Nets
• Multi-Modal Graph Interaction for Multi-Graph Convolution Network in Urban Spatiotemporal Forecasting
• Exploiting Generative AI to Scale up Intelligent Tutoring Systems
• Wasserstein GAN

Cited by

• Predicting electric vehicle charging demand using a heterogeneous spatio-temporal graph convolutional network
• Metropolis-Scale Road Network Datasets for Fine-Grained Urban Traffic Modeling
• PruneGCRN: Minimizing and explaining spatio-temporal problems through node pruning
• Structure Over Signal: A Globalized Approach to Multi-relational GNNs for Stock Prediction
• TAWRMAC: A Novel Dynamic Graph Representation Learning Method
• Deep Learning to Identify the Spatio-Temporal Cascading Effects of Train Delays in a High-Density Network
• Digital Twins for Intelligent Intersections: A Literature Review
• Cross-Modal Reconstruction Pretraining for Ramp Flow Prediction at Highway Interchanges
• Rethinking and Benchmarking Large Language Models for Graph Reasoning
• Graph Neural Networks with Diversity-aware Neighbor Selection and Dynamic Multi-scale Fusion for Multivariate Time Series Forecasting
• Facing & mitigating common challenges when working with real-world data: The Data Learning Paradigm
• Is Homophily a Necessity for Graph Neural Networks?
• A Spatiotemporal Adaptive Local Search Method for Tracking Congestion Propagation in Dynamic Networks
• A Composite-Loss Graph Neural Network for the Multivariate Post-Processing of Ensemble Weather Forecasts
• Model Context Protocols in Adaptive Transport Systems: A Survey
• Edge but not Least: Cross-View Graph Pooling
• Dynamic Mixture-of-Experts for Incremental Graph Learning
• BadTime: An Effective Backdoor Attack on Multivariate Long-Term Time Series Forecasting
• KFS: KAN based adaptive Frequency Selection learning architecture for long term time series forecasting
• Multi-Grained Temporal-Spatial Graph Learning for Stable Traffic Flow Forecasting
• Logical Characterizations of GNNs with Mean Aggregation
• Learning to Locate: GNN-Powered Vulnerability Path Discovery in Open Source Code
• BikeVAE-GNN: A Variational Autoencoder-Augmented Hybrid Graph Neural Network for Sparse Bicycle Volume Estimation
• Beyond Feature and Structure Alignment: Learning Transferable Propagation Knowledge for Graph Foundation Models
• Robust Vehicle Rebalancing with Deep Uncertainty in Autonomous Mobility-on-Demand Systems
• When Will It Fail?: Anomaly to Prompt for Forecasting Future Anomalies in Time Series
• Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting
• Permutation Equivariant Neural Controlled Differential Equations for Dynamic Graph Representation Learning
• Enhancing Spectral Graph Neural Networks with LLM-Predicted Homophily
• A Gravity-informed Spatiotemporal Transformer for Human Activity Intensity Prediction
• Forecast-Then-Optimize Deep Learning Methods
• Enabling Automated FPGA Accelerator Optimization Using Graph Neural Networks
• Flow-Attentional Graph Neural Networks
• Spatio-Temporal Graph Neural Network for Urban Spaces: Interpolating Citywide Traffic Volume
• A Benchmark Dataset for Graph Regression with Homogeneous and Multi-Relational Variants
• Simple yet Effective Graph Distillation via Clustering
• A Consensus-Driven Multi-LLM Pipeline for Missing-Person Investigations
• Quantifying the Noise of Structural Perturbations on Graph Adversarial Attacks
• Safe Urban Traffic Control via Uncertainty-Aware Conformal Prediction and World-Model Reinforcement Learning
• Reliable Graph Neural Network Explanations Through Adversarial Training
• A novel method for accurate and enhanced prediction of proton exchange membrane fuel cell performance based on graph neural networks
• HP-GNN: Generating High Throughput GNN Training Implementation on CPU-FPGA Heterogeneous Platform
• Parallel Multi-Graph Convolution Network For Metro Passenger Volume Prediction
• Efficient Traffic State Prediction With Dynamic Joint Spatio-Temporal Relation Inference