Hybrid Transformer and Spatial-Temporal Self-Supervised Learning for Long-term Traffic Prediction

Long-term traffic prediction has always been a challenging task due to its dynamic temporal dependencies and complex spatial dependencies. In this paper, we propose a model that combines hybrid Transformer and spatio-temporal self-supervised learning. The model enhances its robustness by applying adaptive data augmentation techniques at the sequence-level and graph-level of the traffic data. It utilizes Transformer to overcome the limitations of recurrent neural networks in capturing long-term sequences, and employs Chebyshev polynomial graph convolution to capture complex spatial dependencies. Furthermore, considering the impact of spatio-temporal heterogeneity on traffic speed, we design two self-supervised learning tasks to model the temporal and spatial heterogeneity, thereby improving the accuracy and generalization ability of the model. Experimental evaluations are conducted on two real-world datasets, PeMS04 and PeMS08, and the results are visualized and analyzed, demonstrating the superior performance of the proposed model.

Paper

References (3)

01demonstrating the superior performance of the proposed modelon two real-world datasets, PeMS04 and PeMS08, and the results are visualized and analyzed,
02No T-Block: This variant removes the Transformer in the temporal block, which cannot capture long-term temporal dependencies in the traffic sequences
03This variant removes the temporal heterogeneity supervision, meaning that it does not consider the temporal heterogeneity in the traffic sequences

Similar papers

© 2026 NYSGPT2525 LLC