EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CATI: Cross-Attention-Based Task Interaction for Multi-Granular Metro Passenger Flow Forecasting

Qiong Yang, Xianghua Xu, Juan Yu, Qifeng Gao, Cheng Zhang

Symmetry · 08.05.2026 · 18 (5) · 809

DOI: 10.3390/sym18050809 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Symmetry, online erschienen am 08.05.2026. Verfasst von Qiong Yang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Ministry of education of Humanities and Social Science project, Major Humanities and Social Sciences Research Projects in Zhejiang higher education institutions, the National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate short-term metro passenger flow forecasting plays a key role in urban transit management, supporting train scheduling, crowd control, and operational planning. Jointly modeling station-level inflow/outflow (IO) and inter-station origin–destination flows (OD/DO) has proven effective for improving prediction accuracy, as it allows the model to leverage dependencies across different flow granularities. However, effectively exploiting such dependencies remains nontrivial. Station-level intensity (IO) and inter-station migration patterns (OD/DO) differ substantially in both representation and dynamics, and the dependencies between them are inherently directional and uneven. As a result, commonly used parameter-sharing mechanisms in multi-task learning are often insufficient to capture informative cross-task interactions. To address this issue, we propose CATI (Cross-Attention-based Task Interaction), a unified framework for joint multi-granular metro flow forecasting. CATI first learns task-specific spatiotemporal representations for IO, OD, and DO flows, and then introduces directed cross-attention with Gated Residual Fusion to model selective and asymmetric interactions across tasks. In addition, an aggregation-consistency regularization is employed to maintain structural coherence between station-level and inter-station predictions. Experiments on real-world metro datasets from Hangzhou and Shanghai show that CATI consistently outperforms strong baselines across multiple prediction horizons and tasks. Further analysis indicates that the model learns adaptive attention patterns, task-dependent gating behaviors, and controlled interaction strengths, which together explain its improved performance. These results suggest that explicitly modeling asymmetric cross-task interactions is important for multi-granular spatiotemporal forecasting in metro systems.

Förderung

  • the Ministry of education of Humanities and Social Science project
  • Major Humanities and Social Sciences Research Projects in Zhejiang higher education institutions
  • the National Natural Science Foundation of China

Zitieren

APA

Yang, Q., Xu, X., Yu, J., Gao, Q., & Zhang, C. (2026). CATI: Cross-Attention-Based Task Interaction for Multi-Granular Metro Passenger Flow Forecasting. Symmetry, 18(5), 809. https://doi.org/10.3390/sym18050809

Vancouver

Yang Q, Xu X, Yu J, Gao Q, Zhang C. CATI: Cross-Attention-Based Task Interaction for Multi-Granular Metro Passenger Flow Forecasting. Symmetry. 2026;18(5):809. doi:10.3390/sym18050809

BibTeX
@article{Yang2026,
  author = {Yang, Qiong and Xu, Xianghua and Yu, Juan and Gao, Qifeng and Zhang, Cheng},
  title = {CATI: Cross-Attention-Based Task Interaction for Multi-Granular Metro Passenger Flow Forecasting},
  journal = {Symmetry},
  year = {2026},
  volume = {18},
  number = {5},
  pages = {809},
  doi = {10.3390/sym18050809}
}
Kostenlos starten →