Deep Transfer Learning Method Based on Automatic Domain Alignment and Moment Matching

Jingui Zhang, Chuangji Meng, Cunlu Xu, Jingyong Ma and Wei Su
Additional contact information
Jingui Zhang: School of Information Science and Engineering, Lanzhou University, 222 Tianshui South Road, Lanzhou 730000, China
Chuangji Meng: School of Information Science and Engineering, Lanzhou University, 222 Tianshui South Road, Lanzhou 730000, China
Cunlu Xu: School of Information Science and Engineering, Lanzhou University, 222 Tianshui South Road, Lanzhou 730000, China
Jingyong Ma: College of Pastoral Agriculture Science and Technology, Lanzhou University, Lanzhou 730020, China
Wei Su: School of Information Science and Engineering, Lanzhou University, 222 Tianshui South Road, Lanzhou 730000, China

Mathematics, 2022, vol. 10, issue 14, 1-14

Abstract: Domain discrepancy is a key research problem in the field of deep domain adaptation. Two main strategies are used to reduce the discrepancy: the parametric method and the nonparametric method. Both methods have achieved good results in practical applications. However, research on whether the combination of the two can further reduce domain discrepancy has not been conducted. Therefore, in this paper, a deep transfer learning method based on automatic domain alignment and moment matching (DA-MM) is proposed. First, an automatic domain alignment layer is embedded in the front of each domain-specific layer of a neural network structure to preliminarily align the source and target domains. Then, a moment matching measure (such as MMD distance) is added between every domain-specific layer to map the source and target domain features output by the alignment layer to a common reproduced Hilbert space. The results of an extensive experimental analysis over several public benchmarks show that DA-MM can reduce the distribution discrepancy between the two domains and improve the domain adaptation performance.

Keywords: deep transfer learning; domain adaptation; automatic domain alignment; maximum mean discrepancy (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/10/14/2531/pdf (application/pdf)
https://www.mdpi.com/2227-7390/10/14/2531/ (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:10:y:2022:i:14:p:2531-:d:867886

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 ().