CoRAF: State-Conditioned Source Coupling for Retrieval-Augmented Traffic Forecasting
Mathematics · 19.11.2026 · 14 (22) · 4262
DOI: 10.3390/math14224262 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 19.11.2026. Verfasst von Zixuan Wang und 2 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Traffic-flow forecasting estimates future traffic volumes across a road network from historical sensor observations. A central challenge in historical retrieval is balancing node-specific trajectory matching with the coordination of historical sources across related nodes. We propose CoRAF, a retrieval-augmented forecasting framework that adapts the degree of source sharing to the current traffic state. Node-specific source distributions match individual trajectories, while partition-shared distributions additionally consider the compatibility of local temporal relationships. A state-conditioned gate uses traffic dynamics, relation quality, and matching quality to couple the two forms of historical input-window residual evidence and their observation coverage, which are then encoded and integrated with the current traffic representation. Experiments on PEMS03, PEMS04, PEMS07, and PEMS08 with a one-hour forecasting horizon show that CoRAF achieves the lowest reported mean absolute error (MAE) and mean absolute percentage error (MAPE) among the compared methods, reducing MAE by 0.45%–6.29% relative to the best published baseline results on the respective datasets. Ablation and traffic-state analyses support the complementary value of individual and shared historical evidence, with larger gains over static coupling under high volatility.
Zitieren
APA
Wang, Z., Shen, C., & Zhang, J. (2026). CoRAF: State-Conditioned Source Coupling for Retrieval-Augmented Traffic Forecasting. Mathematics, 14(22), 4262. https://doi.org/10.3390/math14224262
Vancouver
Wang Z, Shen C, Zhang J. CoRAF: State-Conditioned Source Coupling for Retrieval-Augmented Traffic Forecasting. Mathematics. 2026;14(22):4262. doi:10.3390/math14224262
BibTeX
@article{Wang2026,
author = {Wang, Zixuan and Shen, Chao and Zhang, Jingbai},
title = {CoRAF: State-Conditioned Source Coupling for Retrieval-Augmented Traffic Forecasting},
journal = {Mathematics},
year = {2026},
volume = {14},
number = {22},
pages = {4262},
doi = {10.3390/math14224262}
}
EUVIMED