Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting

Abstract

Timely accurate traffic forecast is crucial for urban traffic control and guidance. Due to the high nonlinearity and complexity of traffic flow, traditional methods cannot satisfy the requirements of mid-and-long term prediction tasks and often neglect spatial and temporal dependencies. In this paper, we propose a novel deep learning framework, Spatio-Temporal Graph Convolutional Networks (STGCN), to tackle the time series prediction problem in traffic domain. Instead of applying regular convolutional and recurrent units, we formulate the problem on graphs and build the model with complete convolutional structures, which enable much faster training speed with fewer parameters. Experiments show that our model STGCN effectively captures comprehensive spatio-temporal correlations through modeling multi-scale traffic networks and consistently outperforms state-of-the-art baselines on various real-world traffic datasets.

Proceedings of the 27th International Joint Conference on Artificial Intelligence

References in corpus (2)

• Sequence to Sequence Learning with Neural Networks
• Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting

Cited by in corpus (92)

• A Comprehensive Survey on Graph Neural Networks
• Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting
• Deep Learning on Traffic Prediction: Methods, Analysis and Future Directions
• A Gentle Introduction to Deep Learning for Graphs
• How to Build a Graph-Based Deep Learning Architecture in Traffic Domain: A Survey
• Higher-Order Explanations of Graph Neural Networks via Relevant Walks
• Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future
• Spatio-temporal graph neural networks for multi-site PV power forecasting
• Traffic Prediction using Artificial Intelligence: Review of Recent Advances and Emerging Opportunities
• Graph-Based Spatial-Temporal Convolutional Network for Vehicle Trajectory Prediction in Autonomous Driving
• Gated Graph Recurrent Neural Networks
• A Novel Framework for Spatio-Temporal Prediction of Environmental Data Using Deep Learning
• Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs
• ST-GRAT: A Novel Spatio-temporal Graph Attention Network for Accurately Forecasting Dynamically Changing Road Speed
• Multi-graph convolutional network for short-term passenger flow forecasting in urban rail transit
• One-Class Graph Neural Networks for Anomaly Detection in Attributed Networks
• Hybrid Spatio-Temporal Graph Convolutional Network: Improving Traffic Prediction with Navigation Data
• Spatial-Temporal Interactive Dynamic Graph Convolution Network for Traffic Forecasting
• Spatio-Temporal Graph Few-Shot Learning with Cross-City Knowledge Transfer
• Graph-Partitioning-Based Diffusion Convolutional Recurrent Neural Network for Large-Scale Traffic Forecasting
• Heterogeneous Graph Representation Learning with Relation Awareness
• SageFormer: Series-Aware Framework for Long-term Multivariate Time Series Forecasting
• Geometric deep learning reveals the spatiotemporal fingerprint of microscopic motion
• Spatial-Temporal Hypergraph Self-Supervised Learning for Crime Prediction
• Pay Attention to Evolution: Time Series Forecasting with Deep Graph-Evolution Learning
• Incorporating dynamicity of transportation network with multi-weight traffic graph convolutional network for traffic forecasting
• Graph Neural Networks for Multivariate Time Series Regression with Application to Seismic Data
• Relational Fusion Networks: Graph Convolutional Networks for Road Networks
• Exploring Human Mobility for Multi-Pattern Passenger Prediction: A Graph Learning Framework
• Preserving Dynamic Attention for Long-Term Spatial-Temporal Prediction
• Forecast Network-Wide Traffic States for Multiple Steps Ahead: A Deep Learning Approach Considering Dynamic Non-Local Spatial Correlation and Non-Stationary Temporal Dependency
• Uncertainty Quantification of Sparse Travel Demand Prediction with Spatial-Temporal Graph Neural Networks
• Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors
• Continuous-Time and Multi-Level Graph Representation Learning for Origin-Destination Demand Prediction
• Uncertainty-Aware Probabilistic Graph Neural Networks for Road-Level Traffic Accident Prediction
• Exploring the Generalizability of Spatio-Temporal Traffic Prediction: Meta-Modeling and an Analytic Framework
• Deep learning for dynamic graphs: models and benchmarks
• INCREASE: Inductive Graph Representation Learning for Spatio-Temporal Kriging
• Graph Deep Learning for Time Series Forecasting
• Uncertainty Quantification via Spatial-Temporal Tweedie Model for Zero-inflated and Long-tail Travel Demand Prediction
• Distributed Training of Graph Convolutional Networks
• Multi-frame Feature Aggregation for Real-time Instrument Segmentation in Endoscopic Video
• DuETA: Traffic Congestion Propagation Pattern Modeling via Efficient Graph Learning for ETA Prediction at Baidu Maps
• Real-time Hosting Capacity Assessment for Electric Vehicles: A Sequential Forecast-then-Optimize Method
• Rethinking Sensors Modeling: Hierarchical Information Enhanced Traffic Forecasting
• Enhancing the Robustness via Adversarial Learning and Joint Spatial-Temporal Embeddings in Traffic Forecasting
• Metapopulation Graph Neural Networks: Deep Metapopulation Epidemic Modeling with Human Mobility
• Learning Informative Representation for Fairness-aware Multivariate Time-series Forecasting: A Group-based Perspective
• STUaNet: Understanding uncertainty in spatiotemporal collective human mobility
• MoGERNN: An Inductive Traffic Predictor for Unobserved Locations
• Joint Estimation and Prediction of City-wide Delivery Demand: A Large Language Model Empowered Graph-based Learning Approach
• Graph-enabled Reinforcement Learning for Time Series Forecasting with Adaptive Intelligence
• A Multi-Layer CNN-GRUSKIP model based on transformer for spatial TEMPORAL traffic flow prediction
• Physically-interpretable classification of biological network dynamics for complex collective motions
• Network Level Spatial Temporal Traffic State Forecasting with Hierarchical-Attention-LSTM (HierAttnLSTM)
• Robust Spatiotemporal Traffic Forecasting with Reinforced Dynamic Adversarial Training
• Privacy-Preserving Individual-Level COVID-19 Infection Prediction via Federated Graph Learning
• Because Every Sensor Is Unique, so Is Every Pair: Handling Dynamicity in Traffic Forecasting
• Traffic Forecasting on New Roads Using Spatial Contrastive Pre-Training (SCPT)
• A Multidimensional Graph Fourier Transformation Neural Network for Vehicle Trajectory Prediction
• A Spatio-Temporal Graph Convolutional Network for Gesture Recognition from High-Density Electromyography
• FRIGATE: Frugal Spatio-temporal Forecasting on Road Networks
• Residual Correction in Real-Time Traffic Forecasting
• MemDA: Forecasting Urban Time Series with Memory-based Drift Adaptation
• EasyDGL: Encode, Train and Interpret for Continuous-time Dynamic Graph Learning
• Electric Vehicle Charging Station Location Selection using Geospatial Artificial Intelligence (GeoAI)
• Geometric graphs from data to aid classification tasks with graph convolutional networks
• Enhancing Spatiotemporal Traffic Prediction through Urban Human Activity Analysis
• Knowledge Distillation on Spatial-Temporal Graph Convolutional Network for Traffic Prediction
• Nearest Neighbor Multivariate Time Series Forecasting
• Accident Impact Prediction based on a deep convolutional and recurrent neural network model
• Decoupling Spatio-Temporal Prediction: When Lightweight Large Models Meet Adaptive Hypergraphs
• Message Passing Neural Networks for Hypergraphs
• Optimizing city-scale traffic through modeling observations of vehicle movements
• Spatiotemporal Forecasting of Traffic Flow using Wavelet-based Temporal Attention
• GACAN: Graph Attention-Convolution-Attention Networks for Traffic Forecasting Based on Multi-granularity Time Series
• Networkwide Traffic State Forecasting Using Exogenous Information: A Multi-Dimensional Graph Attention-Based Approach
• SUSTeR: Sparse Unstructured Spatio Temporal Reconstruction on Traffic Prediction
• A Graph Neural Network Model for Real-Time Gesture Recognition Based on sEMG Signals
• Efficient Learning-based Graph Simulation for Temporal Graphs
• Exploring Context Generalizability in Citywide Crowd Mobility Prediction: An Analytic Framework and Benchmark
• STGDPM:Vessel Trajectory Prediction with Spatio-Temporal Graph Diffusion Probabilistic Model
• Is Your Explanation Reliable: Confidence-Aware Explanation on Graph Neural Networks
• A Frequency-Structure Approach for Link Stream Analysis
• An Empirical Experiment on Deep Learning Models for Predicting Traffic Data
• Efficient Large-Scale Urban Parking Prediction: Graph Coarsening Based on Real-Time Parking Service Capability
• Global Spatio-Temporal Fusion-based Traffic Prediction Algorithm with Anomaly Aware
• Language-guided Recursive Spatiotemporal Graph Modeling for Video Summarization
• Lightweight Spatio-Temporal Attention Network with Graph Embedding and Rotational Position Encoding for Traffic Forecasting
• Network-Wide Traffic Volume Estimation from Speed Profiles using a Spatio-Temporal Graph Neural Network with Directed Spatial Attention
• A Transfer Framework for Enhancing Temporal Graph Learning in Data-Scarce Settings
• Traffic signal prediction on transportation networks using spatio-temporal correlations on graphs