TPformer: a deep graphic transformer for long-term traffic flow prediction from node perspective

Long-term traffic flow prediction plays a crucial role in intelligent transportation systems. However, the temporal nonstationary nature of data from traffic detector nodes and the interdependence among nodes pose significant challenges in this prediction task. Therefore, we propose a traffic prediction transformer framework, called TPformer, to learn the spatiotemporal correlations of traffic features among traffic detector nodes. The success of applying the transformer to traffic flow prediction relies on the following key factors: 1) The length of both the input sequence and the predicted sequence is equal to the number of detector nodes, facilitating the construction of a node-node attention mechanism. 2) A node triplet encoding is introduced to allocate additional local contextual structural features to each node. 3) The topological structural features of the transportation network are incorporated into the self-attention mechanism, allowing the model to focus more on neighboring nodes when encoding the node traffic feature. Experimental results on two real-world datasets from the Performance Measurement System (PeMS) demonstrate that the proposed model outperforms state-of-the-art baselines in both short-term and long-term prediction tasks.