Multi-View Multi-Attention Graph Neural Network for Traffic Flow Forecasting

The key to intelligent traffic control and guidance lies in accurate prediction of flow. Since flow data is nonlinear, complex, dynamic, order overcome these issues, graph neural network techniques are employed address challenges. For this reason, we propose a deep-learning architecture called AMGC-AT apply it real passenger dataset the Hangzhou metro for evaluation. Based on priori knowledge, set up multi-view graphs express static feature similarity each station network, such as geographic location zone function, which then input multi-graph with goal extracting aggregating features realize complex spatial dependence station’s Furthermore, based periodic historical flows, categorize into three time patterns. Specifically, two different self-attention mechanisms fuse high-order spatiotemporal final step integrate modules obtain output results using gated convolution fully connected network. experimental show that proposed model has better performance than eight other baseline models at 10 min, 15 min 30 intervals.