Graph Neural Network for Traffic Forecasting: A Survey

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.

References in corpus (29)

• Deep Convolutional Networks on Graph-Structured Data
• Variational Graph Auto-Encoders
• Graph-based Deep Learning for Communication Networks: A Survey
• KST-GCN: A Knowledge-Driven Spatial-Temporal Graph Convolutional Network for Traffic Forecasting
• Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting
• Joint predictions of multi-modal ride-hailing demands: a deep multi-task multigraph learning-based approach
• Graph WaveNet for Deep Spatial-Temporal Graph Modeling
• Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting
• Relational Fusion Networks: Graph Convolutional Networks for Road Networks
• Explainability Techniques for Graph Convolutional Networks
• 3D Graph Convolutional Networks with Temporal Graphs: A Spatial Information Free Framework For Traffic Forecasting
• Coupled Layer-wise Graph Convolution for Transportation Demand Prediction
• A3T-GCN: Attention Temporal Graph Convolutional Network for Traffic Forecasting
• AST-GCN: Attribute-Augmented Spatiotemporal Graph Convolutional Network for Traffic Forecasting
• Incrementally Improving Graph WaveNet Performance on Traffic Prediction
• Spatio-Temporal Deep Graph Infomax
• Deep Multi-View Spatiotemporal Virtual Graph Neural Network for Significant Citywide Ride-hailing Demand Prediction
• Bayesian Spatio-Temporal Graph Convolutional Network for Traffic Forecasting
• A Hybrid Traffic Speed Forecasting Approach Integrating Wavelet Transform and Motif-based Graph Convolutional Recurrent Neural Network
• ISTD-GCN: Iterative Spatial-Temporal Diffusion Graph Convolutional Network for Traffic Speed Forecasting
• Knowledge Adaption for Demand Prediction based on Multi-task Memory Neural Network
• Auto-STGCN: Autonomous Spatial-Temporal Graph Convolutional Network Search Based on Reinforcement Learning and Existing Research Results
• Revisiting Flow Information for Traffic Prediction
• Graph Hierarchical Convolutional Recurrent Neural Network (GHCRNN) for Vehicle Condition Prediction
• SOUP: Spatial-Temporal Demand Forecasting and Competitive Supply
• Constructing Geographic and Long-term Temporal Graph for Traffic Forecasting
• Uncertainty Intervals for Graph-based Spatio-Temporal Traffic Prediction
• Relational State-Space Model for Stochastic Multi-Object Systems
• A Context Integrated Relational Spatio-Temporal Model for Demand and Supply Forecasting

Cited by in corpus (55)

• A Comprehensive Survey on Deep Graph Representation Learning
• Graph-based Deep Learning for Communication Networks: A Survey
• Traffic Prediction using Artificial Intelligence: Review of Recent Advances and Emerging Opportunities
• Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs
• LSTTN: A Long-Short Term Transformer-based Spatio-temporal Neural Network for Traffic Flow Forecasting
• Attention-based graph neural networks: a survey
• Joint Demand Prediction for Multimodal Systems: A Multi-task Multi-relational Spatiotemporal Graph Neural Network Approach
• End-to-end Wind Turbine Wake Modelling with Deep Graph Representation Learning
• Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities
• Graph Neural Networks for Pressure Estimation in Water Distribution Systems
• Is Homophily a Necessity for Graph Neural Networks?
• Big Data for Traffic Estimation and Prediction: A Survey of Data and Tools
• HP-GNN: Generating High Throughput GNN Training Implementation on CPU-FPGA Heterogeneous Platform
• Deep learning for dynamic graphs: models and benchmarks
• Adaptive Dependency Learning Graph Neural Networks
• Graph Foundation Models: Concepts, Opportunities and Challenges
• A Multi-Channel Spatial-Temporal Transformer Model for Traffic Flow Forecasting
• Graph Deep Learning for Time Series Forecasting
• DuETA: Traffic Congestion Propagation Pattern Modeling via Efficient Graph Learning for ETA Prediction at Baidu Maps
• Dynamic Interactive Relation Capturing via Scene Graph Learning for Robotic Surgical Report Generation
• DGNN: Decoupled Graph Neural Networks with Structural Consistency between Attribute and Graph Embedding Representations
• A Systematic Literature Review of Spatio-Temporal Graph Neural Network Models for Time Series Forecasting and Classification
• Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic Forecasting
• Counterfactual Explanations for Deep Learning-Based Traffic Forecasting
• Reconstruction Attack on Differential Private Trajectory Protection Mechanisms
• GraphGLOW: Universal and Generalizable Structure Learning for Graph Neural Networks
• Urban Computing in the Era of Large Language Models
• Forecasting West Nile Virus with Graph Neural Networks: Harnessing Spatial Dependence in Irregularly Sampled Geospatial Data
• Category Theory in Machine Learning
• A graph database for feature characterization of dislocation networks
• Knowledge Distillation on Spatial-Temporal Graph Convolutional Network for Traffic Prediction
• A Baselined Gated Attention Recurrent Network for Request Prediction in Ridesharing
• Spatiotemporal Covariance Neural Networks
• Prediction-based One-shot Dynamic Parking Pricing
• Frame invariance and scalability of neural operators for partial differential equations
• Enabling Automated FPGA Accelerator Optimization Using Graph Neural Networks
• SpotV2Net: Multivariate Intraday Spot Volatility Forecasting via Vol-of-Vol-Informed Graph Attention Networks
• ACGAN-GNNExplainer: Auxiliary Conditional Generative Explainer for Graph Neural Networks
• Efficient Unsupervised Domain Adaptation Regression for Spatial-Temporal Sensor Fusion
• Online Test-Time Adaptation of Spatial-Temporal Traffic Flow Forecasting
• Networkwide Traffic State Forecasting Using Exogenous Information: A Multi-Dimensional Graph Attention-Based Approach
• Evaluating the effects of Data Sparsity on the Link-level Bicycling Volume Estimation: A Graph Convolutional Neural Network Approach
• Reliable Graph Neural Network Explanations Through Adversarial Training
• Non-separable Spatio-temporal Graph Kernels via SPDEs
• Parallel Multi-Graph Convolution Network For Metro Passenger Volume Prediction
• A Composite-Loss Graph Neural Network for the Multivariate Post-Processing of Ensemble Weather Forecasts
• A Spatiotemporal Adaptive Local Search Method for Tracking Congestion Propagation in Dynamic Networks
• Structure-preserving contrastive learning for spatial time series
• HoGA: Higher-Order Graph Attention via Diversity-Aware k-Hop Sampling
• Neural Ranging Inertial Odometry
• Bounding the Interleaving Distance for Mapper Graphs with a Loss Function
• Exploitation of Hidden Context in Dynamic Movement Forecasting: A Neural Network Journey from Recurrent to Graph Neural Networks and General Purpose Transformers
• Edge but not Least: Cross-View Graph Pooling
• Generic Multimodal Spatially Graph Network for Spatially Embedded Network Representation Learning
• Proxy Reconstruction Pre-training for Ramp Flow Prediction at Highway Interchanges