MeTa Learning-Based Optimization of Unsupervised Domain Adaptation Deep Networks

Hsiau-Wen Lin (), Trang-Thi Ho, Ching-Ting Tu (), Hwei-Jen Lin () and Chen-Hsiang Yu
Additional contact information
Hsiau-Wen Lin: Department of Information Management, Chihlee University of Technology, Taipei 220305, Taiwan
Trang-Thi Ho: Department of Computer Science and Information Engineering, Tamkang University, Taipei 251301, Taiwan
Ching-Ting Tu: Department of Applied Mathematics, National Chung Hsing University, Taichung 402202, Taiwan
Hwei-Jen Lin: Department of Computer Science and Information Engineering, Tamkang University, Taipei 251301, Taiwan
Chen-Hsiang Yu: Multidisciplinary Graduate Engineering, College of Engineering, Northeastern University, Boston, MA 02115, USA

Mathematics, 2025, vol. 13, issue 2, 1-23

Abstract: This paper introduces a novel unsupervised domain adaptation (UDA) method, MeTa Discriminative Class-Wise MMD (MCWMMD), which combines meta-learning with a Class-Wise Maximum Mean Discrepancy (MMD) approach to enhance domain adaptation. Traditional MMD methods align overall distributions but struggle with class-wise alignment, reducing feature distinguishability. MCWMMD incorporates a meta-module to dynamically learn a deep kernel for MMD, improving alignment accuracy and model adaptability. This meta-learning technique enhances the model’s ability to generalize across tasks by ensuring domain-invariant and class-discriminative feature representations. Despite the complexity of the method, including the need for meta-module training, it presents a significant advancement in UDA. Future work will explore scalability in diverse real-world scenarios and further optimize the meta-learning framework. MCWMMD offers a promising solution to the persistent challenge of domain adaptation, paving the way for more adaptable and generalizable deep learning models.

Keywords: unsupervised domain adaptation; maximum mean discrepancy (MMD); discriminative class-wise MMD (DCWMMD); meta-learning; deep kernel; feature distributions; domain shift; transfer learning (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/2/226/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/2/226/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:2:p:226-:d:1564626

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().