Multibranch Adaptive Fusion Graph Convolutional Network for Traffic Flow Prediction

Urban road networks have complex spatial and temporal correlations, driving a surge of research interest in spatial-temporal traffic flow prediction. However, prior approaches often overlook the temporal-scale differentiation of spatial-temporal features, limiting their ability to extract complex structural information. In this work, we design the multibranch adaptive fusion graph convolutional network (MBAF-GCN) that explicitly exploits the prior spatial-temporal characteristics at different temporal scales, and each branch is responsible for extracting spatial-temporal features at a specific scale. Besides, we design the spatial-temporal feature fusion (STFF) module to refine the prediction results. Based on the multibranch complementary features, the module adopts a coarse-to-fine fusion strategy, incorporating different spatial-temporal scale features to obtain recalibrated prediction results. Finally, we evaluate the MBAF-GCN using two real-world traffic datasets. Experimentally, the newly designed multibranch can efficaciously utilize the prior information of different temporal scales. Our MBAF-GCN achieved better performance in the comparative model, indicating its potential and validity.