Rethinking the Roles of Time and Frequency Domains Before Tackling Time Series UDA

Fang-Yi Su, Ching Chieh Tsao, Jung-Hsien Chiang

Keywords: unsupervised domain adaptation, time-series domain adaptation, TSUDA

Abstract: In time-series unsupervised domain adaptation (UDA), the adaptation between temporal and frequency domain features has been relatively underexplored. To address this gap, we conduct a comprehensive series of experiments to revisit the roles of these domains in source-free UDA (SFUDA), a branch of the UDA task. Our findings reveal that the temporal domain contains more diverse features, offering higher discriminability, while the frequency domain is more domain-invariant, providing better transferability. Combining the strengths of both domains, we propose TidalFlow, a SFUDA framework that synergistically integrates temporal and frequency domain features. TidalFlow enhances feature extraction and captures subtle, class-specific features without relying on traditional alignment strategies. By utilizing simple hyperparameter adjustments and using frequency embeddings from the source domain as reference points for domain adaptation, TidalFlow achieves nearly a 10\% improvement across five benchmark datasets in time-series UDA. This research highlights the unique strengths of both domains and marks a paradigm shift in SFUDA methods, showcasing TidalFlow’s robust performance in real-world applications. Code is available at the anonymous link: \textcolor{magenta}{\url{https://anonymous.4open.science/r/TidalFlow-42B0/}}.

Primary Area: other topics in machine learning (i.e., none of the above)

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 5596