MSSTAN: A Multi-Scale Spatio-Temporal Attention Network for Traffic Forecasting
ACM Transactions on Knowledge Discovery from Data · 31.08.2026 · 20 (7) · 1-26
DOI: 10.1145/3821212 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Knowledge Discovery from Data, online erschienen am 06.08.2026. Verfasst von Junji Zhu und 5 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Chengdu Key R&D Support Program Project, Major Science and Technology Projects in Sichuan Province, National Natural Science Foundation of China.
Abstract (Originalsprache)
Traffic forecasting is pivotal but challenging due to intricate spatio-temporal dynamics. Existing models often apply a uniform spatial mechanism across distinct temporal scales and rely on static feature embeddings. Consequently, they are inadequate in capturing scale-specific spatial heterogeneity and dynamic feature interdependencies. To address these limitations, we propose the Multi-Scale Spatio-Temporal Attention Network (MSSTAN) with a novel dual-branch architecture: (1) A Global-Local Feature Attention Network (GLFAN) that explicitly decouples spatial interactions across decomposed temporal components to capture multi-scale spatial patterns; and (2) A Spatio-Temporal Feature Attention Network (STFAN) that dynamically recalibrates feature importance based on specific spatio-temporal contexts. A dynamic branch fusion mechanism integrates these branches to optimally aggregate their complementary views. Extensive experiments on five real-world datasets demonstrate that MSSTAN achieves state-of-the-art or highly competitive performance, validating its efficacy for traffic forecasting.
Förderung
- Chengdu Key R&D Support Program Project
- Major Science and Technology Projects in Sichuan Province
- National Natural Science Foundation of China
- Joint Fund of National Natural Science Foundation of China
Zitieren
APA
Zhu, J., Shi, H., Du, S., Li, T., Yang, Y., & Hu, J. (2026). MSSTAN: A Multi-Scale Spatio-Temporal Attention Network for Traffic Forecasting. ACM Transactions on Knowledge Discovery from Data, 20(7), 1-26. https://doi.org/10.1145/3821212
Vancouver
Zhu J, Shi H, Du S, Li T, Yang Y, Hu J. MSSTAN: A Multi-Scale Spatio-Temporal Attention Network for Traffic Forecasting. ACM Transactions on Knowledge Discovery from Data. 2026;20(7):1-26. doi:10.1145/3821212
BibTeX
@article{Zhu2026,
author = {Zhu, Junji and Shi, Haochen and Du, Shengdong and Li, Tianrui and Yang, Yan and Hu, Jie},
title = {MSSTAN: A Multi-Scale Spatio-Temporal Attention Network for Traffic Forecasting},
journal = {ACM Transactions on Knowledge Discovery from Data},
year = {2026},
volume = {20},
number = {7},
pages = {1--26},
doi = {10.1145/3821212}
}
EUVIMED