EUVIMEDEUVIMED entdecken
Crossref

Affirm: Interactive Mamba with Adaptive Fourier Filters for Long-term Time Series Forecasting

Yuhan Wu, Xiyu Meng, Huajin Hu, Junru Zhang, Yabo Dong, Dongming Lu

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (20) · 21599-21607

DOI: 10.1609/aaai.v39i20.35463 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Yuhan Wu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 26-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In long-term series forecasting (LTSF), it is imperative for models to adeptly discern and distill from historical time series data to forecast future states. Although Transformer-based models excel at capturing long-term dependencies in LTSF, their practical use is limited by issues like computational inefficiency, noise sensitivity, and overfitting on smaller datasets. Therefore, we introduce a novel time series lightweight interactive Mamba with an adaptive Fourier filter model (Affirm). Specifically, (i) we propose an adaptive Fourier filter block. This neural operator employs Fourier analysis to refine feature representation, reduces noise with learnable adaptive thresholds, and captures inter-frequency interactions using global and local semantic adaptive Fourier filters via element-wise multiplication. (ii) A dual interactive Mamba block is introduced to facilitate efficient intra-modal interactions at different granularities, capturing more detailed local features and broad global contextual information, providing a more comprehensive representation for LTSF. Extensive experiments on multiple benchmarks demonstrate that Affirm consistently outperforms existing SOTA methods, offering a superior balance of accuracy and efficiency, making it ideal for various challenging scenarios with noise levels and data sizes.

Zitieren

APA

Wu, Y., Meng, X., Hu, H., Zhang, J., Dong, Y., & Lu, D. (2025). Affirm: Interactive Mamba with Adaptive Fourier Filters for Long-term Time Series Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 39(20), 21599-21607. https://doi.org/10.1609/aaai.v39i20.35463

Vancouver

Wu Y, Meng X, Hu H, Zhang J, Dong Y, Lu D. Affirm: Interactive Mamba with Adaptive Fourier Filters for Long-term Time Series Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(20):21599-21607. doi:10.1609/aaai.v39i20.35463

BibTeX
@article{Wu2025,
  author = {Wu, Yuhan and Meng, Xiyu and Hu, Huajin and Zhang, Junru and Dong, Yabo and Lu, Dongming},
  title = {Affirm: Interactive Mamba with Adaptive Fourier Filters for Long-term Time Series Forecasting},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {20},
  pages = {21599--21607},
  doi = {10.1609/aaai.v39i20.35463}
}
Kostenlos starten →