Urban Traffic Flow Forecasting Based on Graph Structure Learning

Abstract

The transportation system is a complex dynamic giant system which integrates and intertwines the elements of people, vehicles, roads, and the environment. The city-level traffic flow forecasting can effectively reflect the flow changes of the traffic system and provide practical guidance for the formulation of traffic rules. Recent city-level traffic flow forecasting works rely on accurate prior knowledge of graphs (i.e., the spatial relationships between roads), which hinders their effectiveness and application in the real world. We propose a novel framework for urban traffic flow forecasting, which simultaneously infers and utilizes the relationship between time series. In our model, the graph structure learning module dynamically captures the correlation and causation between the different time series and infers a potentially fully connected graph. At the same time, the temporal convolution network captures the temporal correlation between a single time series. The graph neural network uses the graph for forecasting. Our model no longer relies on accurate graph priors and achieves better forecasting results than previous work. Experiments on two public datasets verify that the proposed model is very competitive.