Hybrid Transformer and Spatial-Temporal Self-Supervised Learning for Long-term Traffic Prediction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913214924587008 |
|---|---|
| author | Zhu, Wang Zhang, Doudou Long, Baichao Xiao, Jianli |
| author_facet | Zhu, Wang Zhang, Doudou Long, Baichao Xiao, Jianli |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_16453 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Hybrid Transformer and Spatial-Temporal Self-Supervised Learning for Long-term Traffic Prediction Zhu, Wang Zhang, Doudou Long, Baichao Xiao, Jianli Machine Learning Artificial Intelligence 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. |
| title | Hybrid Transformer and Spatial-Temporal Self-Supervised Learning for Long-term Traffic Prediction |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2401.16453 |