Beyond homophily in spatial–temporal traffic flow forecasting
Neural Networks · 2025-03 · 183 · 106950
DOI: 10.1016/j.neunet.2024.106950 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neural Networks, 2025-03. Verfasst von Yuxin Chen und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Nanjing University of Science and Technology, Nanjing, 210094, Jiangsu, China. Hauptthemen laut MEDLINE: Neural Networks, Computer. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 53 Literaturangaben.
Abstract (Originalsprache)
Traffic flow forecasting is a crucial yet complex task due to the intricate spatial-temporal correlations arising from road interactions. Recent methods model these interactions using message-passing Graph Convolution Networks (GCNs), which work for homophily graphs where connected nodes primarily exhibit close observations. However, relying solely on homophily graphs presents inherent limitations in traffic modeling, as road interactions can yield not only close but also distant observations over time, revealing diverse and dynamic node-wise correlations. We designate this phenomenon as homophily-heterophily dynamics, which has been largely overlooked in previous works. To address this gap, we propose a homophily-heterophily Spatial-Temporal Graph Convolution Network (H2STGCN) that exploits both homophily and heterophily components in the spatial-temporal domain. Specifically, we first adopt time-related node attributes to disentangle the diverse and dynamic node-wise relations across time, thereby obtaining homophily and heterophily Spatial-Temporal Graphs (STGs), which provide comprehensive insights into road interactions. Subsequently, we construct dual information propagation branches, each outfitted with a specific type of STG, to exploit multiple ranges of spatial-temporal correlations from distinct perspectives through dilated causal spatial-temporal graph convolution operations on STGs. Additionally, we introduce a Graph Collaborative Learning Module (GCLM) to capture the complementary information of these two branches via mutual information transfer. Experimental evaluation on four real-world traffic datasets reveals that our model outperforms state-of-the-art methods.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Computer Science and Technology, Nanjing University of Science and Technology, Nanjing, 210094, Jiangsu, China.
- School of Computer Science and Technology, Nanjing University of Science and Technology, Nanjing, 210094, Jiangsu, China. Electronic address: yanhui@njust.edu.cn.
Zitieren
APA
Chen, Y., Huo, J., Lin, F., & Yan, H. (2025). Beyond homophily in spatial–temporal traffic flow forecasting. Neural Networks, 183, 106950. https://doi.org/10.1016/j.neunet.2024.106950
Vancouver
Chen Y, Huo J, Lin F, Yan H. Beyond homophily in spatial–temporal traffic flow forecasting. Neural Networks. 2025;183:106950. doi:10.1016/j.neunet.2024.106950
BibTeX
@article{Chen2025,
author = {Chen, Yuxin and Huo, Jingyi and Lin, Fangru and Yan, Hui},
title = {Beyond homophily in spatial–temporal traffic flow forecasting},
journal = {Neural Networks},
year = {2025},
volume = {183},
pages = {106950},
doi = {10.1016/j.neunet.2024.106950}
}
EUVIMED