ISTD-GCN: Iterative Spatial-Temporal Diffusion Graph Convolutional Network for Traffic Speed Forecasting

2020/08/10 by Yi Xie, Xie, Yi, Yun Xiong +3
Computer Science · Engineering · Social Sciences · #FOS: Computer and information sciences #Human Mobility and Location-Based Analysis #Social and Information Networks (cs.SI) #Time Series Analysis and Forecasting #Traffic Prediction and Management Techniques

paper · pdf · doi:10.48550/arxiv.2008.03970

openalex publication_date 2020/08/10 · openalex created_date 2020/08/13 · openalex updated_date 2026/07/28

Abstract

Most of the existing algorithms for traffic speed forecasting split spatial features and temporal features to independent modules, and then associate information from both dimensions. However, features from spatial and temporal dimensions influence mutually, separated extractions isolate such dependencies, and might lead to inaccurate results. In this paper, we incorporate the perspective of information diffusion to model spatial features and temporal features synchronously. Intuitively, vertices not only diffuse information to the neighborhood but also to the subsequent state along with the temporal dimension. Therefore, we can model such heterogeneous spatial-temporal structures as a homogeneous process of diffusion. On this basis, we propose an Iterative Spatial-Temporal Diffusion Graph Convolutional Network (ISTD-GCN) to extract spatial and temporal features synchronously, thus dependencies between both dimensions can be better modeled. Experiments on two traffic datasets illustrate that our ISTD-GCN outperforms 10 baselines in traffic speed forecasting tasks. The source code is available at https://github.com/Anonymous.

Citations

• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains
• Sequence to Sequence Learning with Neural Networks
• ImageNet classification with deep convolutional neural networks
• Detecting Functionality-Specific Vulnerabilities via Retrieving Individual Functionality-Equivalent APIs in Open-Source Repositories
• Layer Normalization

Related

• Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network
• ICST-DNET: An Interpretable Causal Spatio-Temporal Diffusion Network for Traffic Speed Prediction
• DDP-GCN: Multi-Graph Convolutional Network for Spatiotemporal Traffic Forecasting
• Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting
• A3T-GCN: Attention Temporal Graph Convolutional Network for Traffic Forecasting