EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

KALFormer: Knowledge-augmented attention learning for long-term time series forecasting with transformer

Xing Dong, Qianwei Yang, Wenbo Cheng, Yun Zhang iD

PLOS One · 2026

DOI: 10.1371/journal.pone.0338052 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2026. Verfasst von Xing Dong und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Basic Medical Sciences, Guizhou University of Traditional Chinese Medicine, Guiyang, China. Hauptthemen laut MEDLINE: Attention, Machine Learning. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guiyang University of Traditional Chinese Medicine, Guizhou University of Traditional Chinese Medicine, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Time series forecasting remains a fundamental yet challenging task due to its inherent non-linear dynamics, inter-variable dependencies, and long-term temporal correlations. Existing approaches often struggle to jointly capture local temporal continuity and global contextual relationships, particularly under complex external influences. To overcome these limitations, we propose KALFormer, a knowledge-augmented attention learning transformer framework that integrates sequential modeling with external information fusion. KALFormer enhances spatiotemporal representation and contextual reasoning by integrating Long Short-Term Memory (LSTM) encoders, Transformer-based self-attention mechanisms, and knowledge-aware modules. Extensive experiments on six public benchmark datasets demonstrate that KALFormer achieves an average improvement of 8.4% in MSE and MAE compared with representative baseline models, highlighting its robustness, interpretability, and reliability for long-term time series forecasting. The source code is available at https://github.com/dxpython/KALFormer .

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AttentionMachine LearningForecastingHumansAlgorithmsTime FactorsLong Short Term Memory

Autor:innen und Institutionen

  • School of Basic Medical Sciences, Guizhou University of Traditional Chinese Medicine, Guiyang, China.
  • National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China.
  • School of Information Engineering, Guizhou University of Traditional Chinese Medicine, Guiyang, China.

ORCID-Profile: Yun Zhang

Förderung

  • Guiyang University of Traditional Chinese Medicine
  • Guizhou University of Traditional Chinese Medicine
  • National Natural Science Foundation of China

Zitieren

APA

Dong, X., Yang, Q., Cheng, W., & Zhang, Y. (2026). KALFormer: Knowledge-augmented attention learning for long-term time series forecasting with transformer. PLOS One. https://doi.org/10.1371/journal.pone.0338052

Vancouver

Dong X, Yang Q, Cheng W, Zhang Y. KALFormer: Knowledge-augmented attention learning for long-term time series forecasting with transformer. PLOS One. 2026. doi:10.1371/journal.pone.0338052

BibTeX
@article{Dong2026,
  author = {Dong, Xing and Yang, Qianwei and Cheng, Wenbo and Zhang, Yun},
  title = {KALFormer: Knowledge-augmented attention learning for long-term time series forecasting with transformer},
  journal = {PLOS One},
  year = {2026},
  doi = {10.1371/journal.pone.0338052}
}
Kostenlos starten →