EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

iTransformer-FFC: A Frequency-Aware Transformer Framework for Multi-Scale Time Series Forecasting

Yongli Tang, Zhongqi Cai

Electronics · 10.06.2025 · 14 (12) · 2378

DOI: 10.3390/electronics14122378 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 10.06.2025. Verfasst von Yongli Tang und 1 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Key Scientific and Technological Research Project of Henan Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Capturing complex temporal dependencies across multiple scales remains a fundamental challenge in time series forecasting. Transformer-based models have achieved impressive performance on sequence tasks, but vanilla designs often struggle to integrate information from both local fluctuations and global trends, especially in non-stationary sequences. We propose iTransformer-FFC, a novel forecasting framework that addresses these issues through frequency-domain analysis and multi-scale feature fusion. In particular, iTransformer-FFC introduces a Fast Fourier Convolution (FFC) module to transform time series data into the frequency domain, isolating dominant periodic components and attenuating noise before attention is applied. A hierarchical feature fusion mechanism that integrates features extracted at multiple temporal resolutions then jointly models global and local temporal patterns, while a factorized self-attention architecture reduces the quadratic complexity of standard Transformers, improving efficiency while maintaining accuracy. Together, these innovations enable more effective long-range dependency modeling and adaptability to regime shifts in the data. Extensive experiments on five public benchmark datasets demonstrate that iTransformer-FFC consistently outperforms state-of-the-art models, including the vanilla Transformer, an earlier iTransformer variant, and PatchTST. Notably, our model achieves on average an 8.73% lower MSE and 6.95% lower MAE than the best performing baseline, confirming its superior predictive accuracy and generalization in multi-scale time series forecasting through its innovative integration of frequency-domain analysis, hierarchical feature fusion, and factorized attention mechanisms.

Förderung

  • National Natural Science Foundation of China
  • Key Scientific and Technological Research Project of Henan Province

Zitieren

APA

Tang, Y., & Cai, Z. (2025). iTransformer-FFC: A Frequency-Aware Transformer Framework for Multi-Scale Time Series Forecasting. Electronics, 14(12), 2378. https://doi.org/10.3390/electronics14122378

Vancouver

Tang Y, Cai Z. iTransformer-FFC: A Frequency-Aware Transformer Framework for Multi-Scale Time Series Forecasting. Electronics. 2025;14(12):2378. doi:10.3390/electronics14122378

BibTeX
@article{Tang2025,
  author = {Tang, Yongli and Cai, Zhongqi},
  title = {iTransformer-FFC: A Frequency-Aware Transformer Framework for Multi-Scale Time Series Forecasting},
  journal = {Electronics},
  year = {2025},
  volume = {14},
  number = {12},
  pages = {2378},
  doi = {10.3390/electronics14122378}
}
Kostenlos starten →