Dynamic Graph Convolution Network for Traffic Forecasting Based on Latent Network of Laplace Matrix Estimation

Traffic forecasting is a challenging problem in the transportation research field as the complexity and non-stationary changing of the traffic data, thus the key to the issue is how to explore proper spatial and temporal characteristics. Based on this thought, many creative methods have been proposed, in which Graph Convolution Network (GCN) based methods have shown promising performance. However, these methods depend on the graph construction, which mainly uses the prior knowledge of the road network. Recently, some works realized the fact of the road network graph changing and tried to construct dynamic graphs for GCN, but they do not fully exploit the spatial and temporal properties of the traffic data in the graph construction. In this paper, we propose a novel dynamic graph convolution network for traffic forecasting, in which a latent network is introduced to extract spatial-temporal features for constructing the dynamic road network graph matrices adaptively. The proposed method is evaluated on several traffic datasets and the experimental results show that it outperforms the state of the art traffic forecasting methods. The website of the code is https://github.com/guokan987/DGCN.git.

Automated summary

Traffic forecasting is a challenging problem due to the complexity and non-stationary nature of traffic data. Graph Convolution Network (GCN) based methods have shown promising performance in this area. However, current methods lack the utilization of spatial and temporal properties in graph construction. This paper proposes a novel dynamic graph convolution network that adaptively constructs dynamic road network graphs for traffic forecasting, achieving better performance than state-of-the-art methods.