Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting

Abstract

Spatial-temporal forecasting has attracted tremendous attention in a wide range of applications, and traffic flow prediction is a canonical and typical example. The complex and long-range spatial-temporal correlations of traffic flow bring it to a most intractable challenge. Existing works typically utilize shallow graph convolution networks (GNNs) and temporal extracting modules to model spatial and temporal dependencies respectively. However, the representation ability of such models is limited due to: (1) shallow GNNs are incapable to capture long-range spatial correlations, (2) only spatial connections are considered and a mass of semantic connections are ignored, which are of great importance for a comprehensive understanding of traffic networks. To this end, we propose Spatial-Temporal Graph Ordinary Differential Equation Networks (STGODE). Specifically, we capture spatial-temporal dynamics through a tensor-based ordinary differential equation (ODE), as a result, deeper networks can be constructed and spatial-temporal features are utilized synchronously. To understand the network more comprehensively, semantical adjacency matrix is considered in our model, and a well-design temporal dialated convolution structure is used to capture long term temporal dependencies. We evaluate our model on multiple real-world traffic datasets and superior performance is achieved over state-of-the-art baselines.

References in corpus (12)

• Semi-Supervised Classification with Graph Convolutional Networks
• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• Inductive Representation Learning on Large Graphs
• Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting
• T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction
• Graph Neural Networks: A Review of Methods and Applications
• Neural Ordinary Differential Equations
• Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
• Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction
• Parseval Networks: Improving Robustness to Adversarial Examples
• Graph WaveNet for Deep Spatial-Temporal Graph Modeling
• Theoretically Improving Graph Neural Networks via Anonymous Walk Graph Kernels

Cited by in corpus (20)

• A Comprehensive Survey on Deep Graph Representation Learning
• Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs
• Spatial-Temporal Interactive Dynamic Graph Convolution Network for Traffic Forecasting
• Learning Graph ODE for Continuous-Time Sequential Recommendation
• Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities
• Spatio-Temporal Graph Neural Point Process for Traffic Congestion Event Prediction
• Graph Deep Learning for Time Series Forecasting
• Modeling Network-level Traffic Flow Transitions on Sparse Data
• Enhancing the Robustness via Adversarial Learning and Joint Spatial-Temporal Embeddings in Traffic Forecasting
• Spatial Heterophily Aware Graph Neural Networks
• Inductive Graph Alignment Prompt: Bridging the Gap between Graph Pre-training and Inductive Fine-tuning From Spectral Perspective
• OpenCity: Open Spatio-Temporal Foundation Models for Traffic Prediction
• Network Level Spatial Temporal Traffic State Forecasting with Hierarchical-Attention-LSTM (HierAttnLSTM)
• A Data-driven Region Generation Framework for Spatiotemporal Transportation Service Management
• FRIGATE: Frugal Spatio-temporal Forecasting on Road Networks
• Decoupling Spatio-Temporal Prediction: When Lightweight Large Models Meet Adaptive Hypergraphs
• Exploring Context Generalizability in Citywide Crowd Mobility Prediction: An Analytic Framework and Benchmark
• Fine-Grained Traffic Inference from Road to Lane via Spatio-Temporal Graph Node Generation
• Space-Time Graph Neural Networks
• Lightweight Spatio-Temporal Attention Network with Graph Embedding and Rotational Position Encoding for Traffic Forecasting