MPNNLight: A Self-Attention Enhanced Message Passing Graph Neural Network for Multi-Intersection Traffic Signal Control
Electronics · 15.04.2026 · 15 (8) · 1655
DOI: 10.3390/electronics15081655 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 15.04.2026. Verfasst von Zhiyuan Hu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Beijing Natural Science Foundation.
Abstract (Originalsprache)
Coordinated control of multiple intersections remains a major challenge in urban traffic systems due to complex local–global dependencies. To address this issue, the MPNNLight framework is proposed, a message-passing graph neural network for cooperative multi-intersection traffic signal control. The core innovation of this work is the proposed Attention-Wavelet Spatial Transformer (AWSformer), a message computation module that combines self-attention mechanisms and 2D discrete wavelet transform (2D-DWT) to adaptively compute inter-agent messages across spatial and frequency domains. This design enables efficient extraction of multi-scale dependencies and enhances coordination among intersections. Experiments on diverse datasets demonstrate that MPNNLight achieves superior performance and efficiency, compared with existing GNN-based traffic signal control methods.
Förderung
- National Natural Science Foundation of China
- Beijing Natural Science Foundation
Zitieren
APA
Hu, Z., Liu, B., Hu, J., Wang, Z., Peng, L., & Zhang, Y. (2026). MPNNLight: A Self-Attention Enhanced Message Passing Graph Neural Network for Multi-Intersection Traffic Signal Control. Electronics, 15(8), 1655. https://doi.org/10.3390/electronics15081655
Vancouver
Hu Z, Liu B, Hu J, Wang Z, Peng L, Zhang Y. MPNNLight: A Self-Attention Enhanced Message Passing Graph Neural Network for Multi-Intersection Traffic Signal Control. Electronics. 2026;15(8):1655. doi:10.3390/electronics15081655
BibTeX
@article{Hu2026,
author = {Hu, Zhiyuan and Liu, Bowen and Hu, Jianming and Wang, Zihang and Peng, Lihui and Zhang, Yi},
title = {MPNNLight: A Self-Attention Enhanced Message Passing Graph Neural Network for Multi-Intersection Traffic Signal Control},
journal = {Electronics},
year = {2026},
volume = {15},
number = {8},
pages = {1655},
doi = {10.3390/electronics15081655}
}
EUVIMED