FAST: A Synergistic Framework of Attention and State-space Models for Spatiotemporal Traffic Prediction
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910130252021760 |
|---|---|
| author | Li, Xinjin Cao, Jinghan Wang, Mengyue Wu, Yue Yan, Longxiang Zhou, Yeyang Sha, Ziqi Ma, Yu |
| author_facet | Li, Xinjin Cao, Jinghan Wang, Mengyue Wu, Yue Yan, Longxiang Zhou, Yeyang Sha, Ziqi Ma, Yu |
| contents | Traffic forecasting requires modeling complex temporal dynamics and long-range spatial dependencies over large sensor networks. Existing methods typically face a trade-off between expressiveness and efficiency: Transformer-based models capture global dependencies well but suffer from quadratic complexity, while recent selective state-space models are computationally efficient yet less effective at modeling spatial interactions in graph-structured traffic data. We propose FAST, a unified framework that combines attention and state-space modeling for scalable spatiotemporal traffic forecasting. FAST adopts a Temporal-Spatial-Temporal architecture, where temporal attention modules capture both short- and long-term temporal patterns, and a Mamba-based spatial module models long-range inter-sensor dependencies with linear complexity. To better represent heterogeneous traffic contexts, FAST further introduces a learnable multi-source spatiotemporal embedding that integrates historical traffic flow, temporal context, and node-level information, together with a multi-level skip prediction mechanism for hierarchical feature fusion. Experiments on PeMS04, PeMS07, and PeMS08 show that FAST consistently outperforms strong baselines from Transformer-, GNN-, attention-, and Mamba-based families. In particular, FAST achieves the best MAE and RMSE on all three benchmarks, with up to 4.3\% lower RMSE and 2.8\% lower MAE than the strongest baseline, demonstrating a favorable balance between accuracy, scalability, and generalization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_13453 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FAST: A Synergistic Framework of Attention and State-space Models for Spatiotemporal Traffic Prediction Li, Xinjin Cao, Jinghan Wang, Mengyue Wu, Yue Yan, Longxiang Zhou, Yeyang Sha, Ziqi Ma, Yu Machine Learning Traffic forecasting requires modeling complex temporal dynamics and long-range spatial dependencies over large sensor networks. Existing methods typically face a trade-off between expressiveness and efficiency: Transformer-based models capture global dependencies well but suffer from quadratic complexity, while recent selective state-space models are computationally efficient yet less effective at modeling spatial interactions in graph-structured traffic data. We propose FAST, a unified framework that combines attention and state-space modeling for scalable spatiotemporal traffic forecasting. FAST adopts a Temporal-Spatial-Temporal architecture, where temporal attention modules capture both short- and long-term temporal patterns, and a Mamba-based spatial module models long-range inter-sensor dependencies with linear complexity. To better represent heterogeneous traffic contexts, FAST further introduces a learnable multi-source spatiotemporal embedding that integrates historical traffic flow, temporal context, and node-level information, together with a multi-level skip prediction mechanism for hierarchical feature fusion. Experiments on PeMS04, PeMS07, and PeMS08 show that FAST consistently outperforms strong baselines from Transformer-, GNN-, attention-, and Mamba-based families. In particular, FAST achieves the best MAE and RMSE on all three benchmarks, with up to 4.3\% lower RMSE and 2.8\% lower MAE than the strongest baseline, demonstrating a favorable balance between accuracy, scalability, and generalization. |
| title | FAST: A Synergistic Framework of Attention and State-space Models for Spatiotemporal Traffic Prediction |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2604.13453 |