EUVIMEDEUVIMED entdecken
Crossref

Revitalizing Canonical Pre-Alignment for Irregular Multivariate Time Series Forecasting

Ziyu Zhou, Yiming Huang, Yanyun Wang, Yuankai Wu, James Kwok, Yuxuan Liang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (34) · 29115-29123

DOI: 10.1609/aaai.v40i34.40149 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Ziyu Zhou und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Irregular multivariate time series (IMTS), characterized by uneven sampling and inter-variate asynchrony, fuel many forecasting applications yet remain challenging to model efficiently. Canonical Pre-Alignment (CPA) has been widely adopted in IMTS modeling by padding zeros at every global timestamp, thereby alleviating inter-variate asynchrony and unifying the series length, but its dense zero-padding inflates the pre-aligned series length, especially when numerous variates are present, causing prohibitive compute overhead. Recent graph-based models with patching strategies sidestep CPA, but their local message passing struggles to capture global inter-variate correlations. Therefore, we posit that CPA should be retained, with the pre-aligned series properly handled by the model, enabling it to outperform state-of-the-art graph-based baselines that sidestep CPA. Technically, we propose KAFNet, a compact architecture grounded in CPA for IMTS forecasting that couples (1) a Pre-Convolution module for sequence smoothing and sparsity mitigation, (2) a Temporal Kernel Aggregation module for learnable compression and modeling of intra-series irregularity, and (3) Frequency Linear Attention blocks for low-cost inter-series correlation modeling in the frequency domain. Experiments on multiple IMTS datasets show that KAFNet achieves state-of-the-art forecasting performance, with a 7.2× parameter reduction and an 8.4× training–inference acceleration.

Zitieren

APA

Zhou, Z., Huang, Y., Wang, Y., Wu, Y., Kwok, J., & Liang, Y. (2026). Revitalizing Canonical Pre-Alignment for Irregular Multivariate Time Series Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 40(34), 29115-29123. https://doi.org/10.1609/aaai.v40i34.40149

Vancouver

Zhou Z, Huang Y, Wang Y, Wu Y, Kwok J, Liang Y. Revitalizing Canonical Pre-Alignment for Irregular Multivariate Time Series Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(34):29115-29123. doi:10.1609/aaai.v40i34.40149

BibTeX
@article{Zhou2026,
  author = {Zhou, Ziyu and Huang, Yiming and Wang, Yanyun and Wu, Yuankai and Kwok, James and Liang, Yuxuan},
  title = {Revitalizing Canonical Pre-Alignment for Irregular Multivariate Time Series Forecasting},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {34},
  pages = {29115--29123},
  doi = {10.1609/aaai.v40i34.40149}
}
Kostenlos starten →