Dynamic Causal Graph Convolutional Network for Traffic Prediction

TL;DR

This paper introduces a novel traffic prediction model that dynamically captures changing spatiotemporal dependencies using a deep learning-based hyper-network to generate stepwise causal graphs, leading to improved forecasting accuracy.

Contribution

It proposes a dynamic causal graph convolutional network that models time-varying traffic dependencies with a hyper-network, enhancing prediction performance over static graph methods.

Findings

Superior prediction accuracy on real traffic data

Effective modeling of nonlinear traffic propagation patterns

Outperforms existing static graph-based models

Abstract

Modeling complex spatiotemporal dependencies in correlated traffic series is essential for traffic prediction. While recent works have shown improved prediction performance by using neural networks to extract spatiotemporal correlations, their effectiveness depends on the quality of the graph structures used to represent the spatial topology of the traffic network. In this work, we propose a novel approach for traffic prediction that embeds time-varying dynamic Bayesian network to capture the fine spatiotemporal topology of traffic data. We then use graph convolutional networks to generate traffic forecasts. To enable our method to efficiently model nonlinear traffic propagation patterns, we develop a deep learning-based module as a hyper-network to generate stepwise dynamic causal graphs. Our experimental results on a real traffic dataset demonstrate the superior prediction performance of the proposed method. The code is available at https://github.com/MonBG/DCGCN.