EUVIMEDEUVIMED entdecken
Crossref

Generalizing to New Dynamical Systems via Frequency Domain Adaptation

Tiexin Qin, Hong Yan, Haoliang Li

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-10 · 47 (10) · 9352-9359

DOI: 10.1109/tpami.2025.3581941 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-10. Verfasst von Tiexin Qin und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: Hong Kong Innovation and Technology Commission, Institute of Digital Medicine, City University of Hong Kong, Hong Kong Research Grants Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Learning the underlying dynamics from data with deep neural networks has shown remarkable potential in modeling various complex physical dynamics. However, current approaches are constrained in their ability to make reliable predictions in a specific domain and struggle with generalizing to unseen systems that are governed by the same general dynamics but differ in environmental characteristics. In this work, we formulate a parameter-efficient method, Fourier Neural Simulator for Dynamical Adaptation (FNSDA), that can readily generalize to new dynamics via adaptation in the Fourier space. Specifically, FNSDA identifies the shareable dynamics based on the known environments using an automatic partition in Fourier modes and learns to adjust the modes specific for each new environment by conditioning on low-dimensional latent systematic parameters for efficient generalization. We evaluate our approach on four representative families of dynamic systems, and the results show that FNSDA can achieve superior or competitive generalization performance compared to existing methods with a significantly reduced parameter cost. Our code is available at https://github.com/WonderSeven/FNSDA.

Förderung

  • Hong Kong Innovation and Technology Commission
  • Institute of Digital Medicine, City University of Hong Kong
  • Hong Kong Research Grants Council
  • City University of Hong Kong
  • Sichuan Science and Technology Fund

Zitieren

APA

Qin, T., Yan, H., & Li, H. (2025). Generalizing to New Dynamical Systems via Frequency Domain Adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(10), 9352-9359. https://doi.org/10.1109/tpami.2025.3581941

Vancouver

Qin T, Yan H, Li H. Generalizing to New Dynamical Systems via Frequency Domain Adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(10):9352-9359. doi:10.1109/tpami.2025.3581941

BibTeX
@article{Qin2025,
  author = {Qin, Tiexin and Yan, Hong and Li, Haoliang},
  title = {Generalizing to New Dynamical Systems via Frequency Domain Adaptation},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {10},
  pages = {9352--9359},
  doi = {10.1109/tpami.2025.3581941}
}
Kostenlos starten →