DGTNet:dynamic graph attention transformer network for traffic flow forecasting

Abstract Graph-based traffic flow prediction plays a crucial role in urban traffic management and planning. In this paper, we propose a novel Dynamic Graph Attention Transformer Network (DGTNet), which is designed to address the issue of inadequate integration of temporal and spatial dimensions in traditional models. DGTNet maintains temporal continuity while revealing the complex dynamic relationships between key nodes in the urban traffic system, capturing the periodic changes in the rhythm of city life. Specifically, this study adopts adaptive signal decomposition technology to decompose traffic data into multiple Intrinsic Mode Functions (IMFs), effectively capturing the dynamic changes in traffic flow. This decomposition method is key to the implementation of DGTNet’s dynamic graph construction, enabling the analysis of traffic flow at different time scales, thereby providing a new perspective for traffic flow prediction research. In the traffic prediction module, we comprehensively consider node, edge, and graph structural information, adopting a multi-head self-attention mechanism to achieve direct cross-modeling in both temporal and spatial dimensions. Finally, we introduce a position-wise feedforward network layer to integrate different types of data and capture nonlinear relationships. The experimental results, based on public transportation network datasets METR_LA, PEMS_BAY, PEMS03, and PEMS07, demonstrate that DGTNet exhibits notable enhancements in three evaluation indicators, namely the Mean Absolute Percentage Error (MAPE), the Root Mean Square Error (RMSE), and the Mean Absolute Error (MAE). The pertinent code has been made available for public access at https://github.com/chenjing0616/DGTNet .