EUVIMEDEUVIMED entdecken
Crossref

TRACK: Temporal Decoupled Kriging for Inductive Spatio-Temporal Graph

Jianping Zhou, Weida Wang, Bin Lu, Guanjie Zheng, Lei Bai, Xinbing Wang, Chenghu Zhou

IEEE Transactions on Knowledge and Data Engineering · 2026-06 · 38 (6) · 3991-4005

DOI: 10.1109/tkde.2026.3674348 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, 2026-06. Verfasst von Jianping Zhou und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: National Natural Science Foundation of China, 2025 Shanghai Key Technology Research and Development Program, Next-Generation Information Technology Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The deployment of sensors enables data-driven urban management, but necessitates inductive spatio-temporal kriging to infer unmonitored areas. Existing methods impute these unknown observations by smoothing temporal features based on spatial dependencies, overlooking the decoupling of inherent properties and dynamic correlations in message passing. In particular, the inherent properties reveal non-transitive signals, and current coupled aggregation leads to inaccurate results. To this end, we propose TempoRAl deCoupled Kriging, named TRACK, to decouple two factors with the help of node-specific inherency. Specifically, we first construct a node-specific profile to represent its inherency including geographical and periodic features, which is subsequently transformed into decoupling prompts. Secondly, the coupled temporal features are separated through querying each prompt embedding, facilitating precise temporal aggregation for inherent properties and spatial aggregation for dynamic correlations. Finally, a multi-task training strategy is further adopted to mimic the inductive scenarios during testing. We evaluate TRACK on four real-world datasets spanning urban traffic and air quality prediction tasks. TRACK achieves state-of-the-art performance, with average improvements of 3.10% in MAE and 4.45% in RMSE over strong baselines. Moreover, we further demonstrated its robust generalization in a challenging cross-city inductive setting.

Förderung

  • National Natural Science Foundation of China
  • 2025 Shanghai Key Technology Research and Development Program
  • Next-Generation Information Technology Project
  • Postdoctoral Fellowship Program of CPSF

Zitieren

APA

Zhou, J., Wang, W., Lu, B., Zheng, G., Bai, L., Wang, X., & Zhou, C. (2026). TRACK: Temporal Decoupled Kriging for Inductive Spatio-Temporal Graph. IEEE Transactions on Knowledge and Data Engineering, 38(6), 3991-4005. https://doi.org/10.1109/tkde.2026.3674348

Vancouver

Zhou J, Wang W, Lu B, Zheng G, Bai L, Wang X, et al. TRACK: Temporal Decoupled Kriging for Inductive Spatio-Temporal Graph. IEEE Transactions on Knowledge and Data Engineering. 2026;38(6):3991-4005. doi:10.1109/tkde.2026.3674348

BibTeX
@article{Zhou2026,
  author = {Zhou, Jianping and Wang, Weida and Lu, Bin and Zheng, Guanjie and Bai, Lei and Wang, Xinbing and Zhou, Chenghu},
  title = {TRACK: Temporal Decoupled Kriging for Inductive Spatio-Temporal Graph},
  journal = {IEEE Transactions on Knowledge and Data Engineering},
  year = {2026},
  volume = {38},
  number = {6},
  pages = {3991--4005},
  doi = {10.1109/tkde.2026.3674348}
}
Kostenlos starten →