Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network

Authors

  • Xiyue Zhang South China University of Technology, China
  • Chao Huang JD Finance America Corporation, USA
  • Yong Xu South China University of Technology, China Communication and Computer Network Laboratory of Guangdong, China Peng Cheng Laboratory, China
  • Lianghao Xia South China University of Technology, China
  • Peng Dai JD Finance America Corporation, USA
  • Liefeng Bo JD Finance America Corporation, USA
  • Junbo Zhang JD Intelligent Cities Research, China JD Intelligent Cities Business Unit, JD Digits, China
  • Yu Zheng JD Intelligent Cities Research, China JD Intelligent Cities Business Unit, JD Digits, China

DOI:

https://doi.org/10.1609/aaai.v35i17.17761

Keywords:

Mobility/Transportation

Abstract

Accurate forecasting of citywide traffic flow has been playing critical role in a variety of spatial-temporal mining applications, such as intelligent traffic control and public risk assessment. While previous work has made significant efforts to learn traffic temporal dynamics and spatial dependencies, two key limitations exist in current models. First, only the neighboring spatial correlations among adjacent regions are considered in most existing methods, and the global interregion dependency is ignored. Additionally, these methods fail to encode the complex traffic transition regularities exhibited with time-dependent and multi-resolution in nature. To tackle these challenges, we develop a new traffic prediction framework–Spatial-Temporal Graph Diffusion Network (ST-GDN). In particular, ST-GDN is a hierarchically structured graph neural architecture which learns not only the local region-wise geographical dependencies, but also the spatial semantics from a global perspective. Furthermore, a multi-scale attention network is developed to empower ST-GDN with the capability of capturing multi-level temporal dynamics. Experiments on four real-life traffic datasets demonstrate that ST-GDN outperforms different types of state-of-the-art baselines.

Downloads

Published

2021-05-18

How to Cite

Zhang, X., Huang, C., Xu, Y., Xia, L., Dai, P., Bo, L., Zhang, J., & Zheng, Y. (2021). Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network. Proceedings of the AAAI Conference on Artificial Intelligence, 35(17), 15008-15015. https://doi.org/10.1609/aaai.v35i17.17761

Issue

Section

AAAI Special Track on AI for Social Impact