Traffic Prediction with Graph Neural Network: A Survey

Traffic prediction plays an important role in intelligent transportation systems. Accurate traffic forecasting can make for better traffic management and alleviate traffic problems, such as traffic congestion and traffic pollution. Graph data structure can well express the topology structure of traffic network, so graph model has more development space in the field of traffic prediction. The main purpose of this paper is to provide a comprehensive survey for the graph neural network in the field of traffic prediction. First, the graph model framework was divided into four categories, namely graph convolution networks, graph attention networks, graph auto-encoders and graph generative networks. Then, related literatures are introduced around the four frames. Finally, suggestions on the future development direction of the graph neural network are given.