EUVIMEDEUVIMED entdecken
Crossref

Probabilistic Learning of Multivariate Time Series With Temporal Irregularity

Yijun Li, Cheuk Hang Leung, Qi Wu

IEEE Transactions on Knowledge and Data Engineering · 2025-05 · 37 (5) · 2874-2887

DOI: 10.1109/tkde.2025.3544348 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, 2025-05. Verfasst von Yijun Li und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: The CityU-JD Digits Joint Laboratory in Financial Technology and Engineering, The Hong Kong Research Grants Council, The CityU APRC.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Probabilistic forecasting of multivariate time series is essential for various downstream tasks. Most existing approaches rely on the sequences being uniformly spaced and aligned across all variables. However, real-world multivariate time series often suffer from temporal irregularities, including nonuniform intervals and misaligned variables, which pose significant challenges for accurate forecasting. To address these challenges, we propose an end-to-end framework that models temporal irregularities while capturing the joint distribution of variables at arbitrary continuous-time points. Specifically, we introduce a dynamic conditional continuous normalizing flow to model data distributions in a non-parametric manner, accommodating the complex, non-Gaussian characteristics commonly found in real-world datasets. Then, by leveraging a carefully factorized log-likelihood objective, our approach captures both temporal and cross-sectional dependencies efficiently. Extensive experiments on a range of real-world datasets demonstrate the superiority and adaptability of our method compared to existing approaches.

Förderung

  • The CityU-JD Digits Joint Laboratory in Financial Technology and Engineering
  • The Hong Kong Research Grants Council
  • The CityU APRC
  • InnoHK initiative
  • Government of the HKSAR
  • Laboratory for AI-Powered Financial Technologies

Zitieren

APA

Li, Y., Leung, C. H., & Wu, Q. (2025). Probabilistic Learning of Multivariate Time Series With Temporal Irregularity. IEEE Transactions on Knowledge and Data Engineering, 37(5), 2874-2887. https://doi.org/10.1109/tkde.2025.3544348

Vancouver

Li Y, Leung CH, Wu Q. Probabilistic Learning of Multivariate Time Series With Temporal Irregularity. IEEE Transactions on Knowledge and Data Engineering. 2025;37(5):2874-2887. doi:10.1109/tkde.2025.3544348

BibTeX
@article{Li2025,
  author = {Li, Yijun and Leung, Cheuk Hang and Wu, Qi},
  title = {Probabilistic Learning of Multivariate Time Series With Temporal Irregularity},
  journal = {IEEE Transactions on Knowledge and Data Engineering},
  year = {2025},
  volume = {37},
  number = {5},
  pages = {2874--2887},
  doi = {10.1109/tkde.2025.3544348}
}
Kostenlos starten →