Please use this identifier to cite or link to this item:
Title: Subdomain adaptation with manifolds discrepancy alignment
Authors: Wei, Pengfei
Ke, Yiping
Qu, Xinghua
Leong, Tze-Yun
Keywords: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Issue Date: 2021
Source: Wei, P., Ke, Y., Qu, X. & Leong, T. (2021). Subdomain adaptation with manifolds discrepancy alignment. IEEE Transactions On Cybernetics, 1-11.
Project: SDSC-2020-004 
Journal: IEEE Transactions on Cybernetics 
Abstract: Reducing domain divergence is a key step in transfer learning. Existing works focus on the minimization of global domain divergence. However, two domains may consist of several shared subdomains, and differ from each other in each subdomain. In this paper, we take the local divergence of subdomains into account in transfer. Specifically, we propose to use low-dimensional manifold to represent subdomain, and align the local data distribution discrepancy in each manifold across domains. A Manifold Maximum Mean Discrepancy (M3D) is developed to measure the local distribution discrepancy in each manifold. We then propose a general framework, called Transfer with Manifolds Discrepancy Alignment (TMDA), to couple the discovery of data manifolds with the minimization of M3D. We instantiate TMDA in the subspace learning case considering both the linear and nonlinear mappings. We also instantiate TMDA in the deep learning framework. Experimental studies show that TMDA is a promising method for various transfer learning tasks.
ISSN: 2168-2267
DOI: 10.1109/TCYB.2021.3071244
Schools: School of Computer Science and Engineering 
Rights: © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at:
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Journal Articles

Files in This Item:
File Description SizeFormat 
Subdomain Adaptation with Manifolds - IEEE Cybernetics 2021.pdf4.88 MBAdobe PDFThumbnail

Citations 20

Updated on May 22, 2024

Web of ScienceTM
Citations 20

Updated on Oct 22, 2023

Page view(s)

Updated on May 24, 2024

Download(s) 50

Updated on May 24, 2024

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.