STAMImputer: Spatio-Temporal Attention MoE for Traffic Data Imputation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909645707149312 |
|---|---|
| author | Wang, Yiming Peng, Hao Wang, Senzhang Du, Haohua Liu, Chunyang Wu, Jia Wu, Guanlin |
| author_facet | Wang, Yiming Peng, Hao Wang, Senzhang Du, Haohua Liu, Chunyang Wu, Jia Wu, Guanlin |
| contents | Traffic data imputation is fundamentally important to support various applications in intelligent transportation systems such as traffic flow prediction. However, existing time-to-space sequential methods often fail to effectively extract features in block-wise missing data scenarios. Meanwhile, the static graph structure for spatial feature propagation significantly constrains the models flexibility in handling the distribution shift issue for the nonstationary traffic data. To address these issues, this paper proposes a SpatioTemporal Attention Mixture of experts network named STAMImputer for traffic data imputation. Specifically, we introduce a Mixture of Experts (MoE) framework to capture latent spatio-temporal features and their influence weights, effectively imputing block missing. A novel Low-rank guided Sampling Graph ATtention (LrSGAT) mechanism is designed to dynamically balance the local and global correlations across road networks. The sampled attention vectors are utilized to generate dynamic graphs that capture real-time spatial correlations. Extensive experiments are conducted on four traffic datasets for evaluation. The result shows STAMImputer achieves significantly performance improvement compared with existing SOTA approaches. Our codes are available at https://github.com/RingBDStack/STAMImupter. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_08054 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | STAMImputer: Spatio-Temporal Attention MoE for Traffic Data Imputation Wang, Yiming Peng, Hao Wang, Senzhang Du, Haohua Liu, Chunyang Wu, Jia Wu, Guanlin Machine Learning Artificial Intelligence Traffic data imputation is fundamentally important to support various applications in intelligent transportation systems such as traffic flow prediction. However, existing time-to-space sequential methods often fail to effectively extract features in block-wise missing data scenarios. Meanwhile, the static graph structure for spatial feature propagation significantly constrains the models flexibility in handling the distribution shift issue for the nonstationary traffic data. To address these issues, this paper proposes a SpatioTemporal Attention Mixture of experts network named STAMImputer for traffic data imputation. Specifically, we introduce a Mixture of Experts (MoE) framework to capture latent spatio-temporal features and their influence weights, effectively imputing block missing. A novel Low-rank guided Sampling Graph ATtention (LrSGAT) mechanism is designed to dynamically balance the local and global correlations across road networks. The sampled attention vectors are utilized to generate dynamic graphs that capture real-time spatial correlations. Extensive experiments are conducted on four traffic datasets for evaluation. The result shows STAMImputer achieves significantly performance improvement compared with existing SOTA approaches. Our codes are available at https://github.com/RingBDStack/STAMImupter. |
| title | STAMImputer: Spatio-Temporal Attention MoE for Traffic Data Imputation |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2506.08054 |