EUVIMEDEUVIMED entdecken
Crossref

HMformer: Unleashing Transformer’s Potential for Time Series Forecasting via Hierarchical Multi-Scale Modeling

Renjun Huang, Han Xiao, Bingqing Li, Baili Zhang, Jianhua Lyu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (26) · 22012-22020

DOI: 10.1609/aaai.v40i26.39355 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Renjun Huang und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Time series forecasting plays a critical role across a wide range of domains. Recently, an increasing number of Transformer-based forecasting models have emerged, achieving remarkably competitive performance. However, real-world time series data often exhibit complex multi-scale periodicities, which are not well-suited for modeling by the original Transformer architecture originally developed for NLP tasks. To address this limitation, we propose the Hierarchical Multi-scale Time Series Transformer (HMformer), employing a novel and sophisticated framework specifically designed for multi-scale time series forecasting. Specifically, HMformer incorporates a hierarchical cross-scale mixing mechanism that progressively aggregates temporal information from fine to coarse granularities, a scale-adaptive feature expansion design enhancing the extraction of high-level temporal semantics, and a multi-branch complementary prediction strategy for effectively integrating diverse temporal patterns. Collectively, these components enable HMformer to capture intricate, multi-scale temporal dynamics while retaining the Transformer’s inherent strength in modeling long-range dependencies. Extensive experiments conducted on multiple real-world benchmark datasets—encompassing both long-term and short-term forecasting tasks—demonstrate that HMformer achieves state-of-the-art performance.

Zitieren

APA

Huang, R., Xiao, H., Li, B., Zhang, B., & Lyu, J. (2026). HMformer: Unleashing Transformer’s Potential for Time Series Forecasting via Hierarchical Multi-Scale Modeling. Proceedings of the AAAI Conference on Artificial Intelligence, 40(26), 22012-22020. https://doi.org/10.1609/aaai.v40i26.39355

Vancouver

Huang R, Xiao H, Li B, Zhang B, Lyu J. HMformer: Unleashing Transformer’s Potential for Time Series Forecasting via Hierarchical Multi-Scale Modeling. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(26):22012-22020. doi:10.1609/aaai.v40i26.39355

BibTeX
@article{Huang2026,
  author = {Huang, Renjun and Xiao, Han and Li, Bingqing and Zhang, Baili and Lyu, Jianhua},
  title = {HMformer: Unleashing Transformer’s Potential for Time Series Forecasting via Hierarchical Multi-Scale Modeling},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {26},
  pages = {22012--22020},
  doi = {10.1609/aaai.v40i26.39355}
}
Kostenlos starten →