DSSA-TCN: Exploiting adaptive sparse attention and diffusion graph convolutions in temporal convolutional networks for traffic flow forecasting
PLOS One · 2025
DOI: 10.1371/journal.pone.0336787 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Zhouyuan Zhang und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer and Information Science, Chongqing Normal University, Chongqing, China. Hauptthemen laut MEDLINE: Transportation, Neural Networks, Computer. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Chongqing, Natural Science Foundation of Tianjin Municipal Science and Technology Commission, Science and Technology Research Program of Chongqing Municipal Education Commission.
Abstract (Originalsprache)
Accurate traffic flow forecasting is essential for intelligent transportation systems, yet the nonlinear and dynamically evolving spatio-temporal dependencies in urban road networks make reliable prediction challenging. Existing graph-based and attention-based approaches have improved performance but often decouple spatial and temporal learning, which leads to redundant computation and weak directional interpretability. To address these limitations, we propose DSSA-TCN, a unified framework that establishes an alternating spatio-temporal coupling mechanism, where each temporal convolutional block is tightly integrated with an adaptive spatial module that combines sparse attention with diffusion-based graph convolution. Within this mechanism, adaptive sparse attention dynamically selects the most informative neighbors to reduce spatial complexity, and bidirectional diffusion convolution enforces physically consistent directional and multi-hop propagation over the road topology. Temporal patterns are modeled with gated dilated convolutions to preserve parallelism and stability. Comprehensive experiments on six real-world datasets demonstrate that DSSA-TCN achieves superior forecasting accuracy and computational efficiency while providing interpretable spatial reasoning. These results indicate that layer-wise coupling of adaptive sparsity and diffusion within a causal temporal backbone offers a scalable and physically grounded paradigm for spatio-temporal traffic prediction.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Computer and Information Science, Chongqing Normal University, Chongqing, China.
- Chongqing Changan Automobile Company Limited, Chongqing, China.
- China Telecom Zhi'an Technology Co., Ltd., Chongqing, China.
- National Center for Applied Mathematics in Chongqing, Chongqing Normal University, Chongqing, China.
ORCID-Profile: Jiatian Pi
Förderung
- Natural Science Foundation of Chongqing
- Natural Science Foundation of Tianjin Municipal Science and Technology Commission
- Science and Technology Research Program of Chongqing Municipal Education Commission
Zitieren
APA
Zhang, Z., Wang, X., Tan, X., & Pi, J. (2025). DSSA-TCN: Exploiting adaptive sparse attention and diffusion graph convolutions in temporal convolutional networks for traffic flow forecasting. PLOS One. https://doi.org/10.1371/journal.pone.0336787
Vancouver
Zhang Z, Wang X, Tan X, Pi J. DSSA-TCN: Exploiting adaptive sparse attention and diffusion graph convolutions in temporal convolutional networks for traffic flow forecasting. PLOS One. 2025. doi:10.1371/journal.pone.0336787
BibTeX
@article{Zhang2025,
author = {Zhang, Zhouyuan and Wang, Xin and Tan, Xu and Pi, Jiatian},
title = {DSSA-TCN: Exploiting adaptive sparse attention and diffusion graph convolutions in temporal convolutional networks for traffic flow forecasting},
journal = {PLOS One},
year = {2025},
doi = {10.1371/journal.pone.0336787}
}
EUVIMED