Multi-source heterogeneous unsupervised domain adaptation via fuzzy-relation neural networks

Liu, F; Zhang, G; Lu, J

Multi-source heterogeneous unsupervised domain adaptation via fuzzy-relation neural networks

Liu, F

Zhang, G

Lu, J

Permalink

Publisher:: Institute of Electrical and Electronics Engineers
Publication Type:: Journal Article
Citation:: IEEE Transactions on Fuzzy Systems, 2021, 29, (11), pp. 3308-3322
Issue Date:: 2021

Closed Access

	Filename	Description	Size
	Multisource_Heterogeneous_Unsupervised_Domain_Adaptation_via_Fuzzy_Relation_Neural_Networks.pdf	Published version	3.4 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Liu, F https://orcid.org/0000-0002-5005-9129
dc.contributor.author	Zhang, G https://orcid.org/0000-0003-3960-0583
dc.contributor.author	Lu, J https://orcid.org/0000-0003-0690-4732
dc.date.accessioned	2022-05-16T07:01:41Z
dc.date.available	2022-05-16T07:01:41Z
dc.date.issued	2021
dc.identifier.citation	IEEE Transactions on Fuzzy Systems, 2021, 29, (11), pp. 3308-3322
dc.identifier.issn	1063-6706
dc.identifier.issn	1941-0034
dc.identifier.uri	http://hdl.handle.net/10453/157427
dc.description.abstract	In unsupervised domain adaptation (UDA), a classifier for a target domain is trained with labeled source data and unlabeled target data. Existing UDA methods assume that the source data come from the same source domain (i.e., single-source scenario) or from multiple source domains, whose feature spaces have the same dimension ( homogeneous ) but different distributions (i.e., multihomogeneous-source scenario). However, in the real world, for a specific target domain, we probably have multiple different-dimension ( heterogeneous ) source domains, which do not satisfy the assumption of existing UDA methods. To remove this assumption and move forward to a realistic UDA problem, this article presents a shared-fuzzy-equivalence-relation neural network (SFERNN) for addressing the multisource heterogeneous UDA problem. The SFERNN is a five-layer neural network containing c source branches and one target branch. The network structure of the SFERNN is first confirmed by a novel fuzzy relation called multisource shared fuzzy equivalence relation. Then, we optimize parameters of the SFERNN via minimizing cross-entropy loss on c source branches and the distributional discrepancy between each source branch and the target branch. Experiments distributed across eight real-world datasets are conducted to validate the SFERNN. This testing regime demonstrates that the SFERNN outperforms the existing single-source heterogeneous UDA methods, especially when the target domain contains few data.
dc.language	English
dc.publisher	Institute of Electrical and Electronics Engineers
dc.relation	http://purl.org/au-research/grants/arc/DP170101632
dc.relation	http://purl.org/au-research/grants/arc/FL190100149
dc.relation.ispartof	IEEE Transactions on Fuzzy Systems
dc.relation.isbasedon	10.1109/tfuzz.2020.3018191
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0102 Applied Mathematics, 0801 Artificial Intelligence and Image Processing, 0906 Electrical and Electronic Engineering
dc.subject.classification	Artificial Intelligence & Image Processing
dc.title	Multi-source heterogeneous unsupervised domain adaptation via fuzzy-relation neural networks
dc.type	Journal Article
utslib.citation.volume	29
utslib.for	0102 Applied Mathematics
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0906 Electrical and Electronic Engineering
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2022-05-16T07:01:37Z
pubs.issue	11
pubs.publication-status	Published
pubs.volume	29
utslib.citation.issue	11

Abstract:

In unsupervised domain adaptation (UDA), a classifier for a target domain is trained with labeled source data and unlabeled target data. Existing UDA methods assume that the source data come from the same source domain (i.e., single-source scenario) or from multiple source domains, whose feature spaces have the same dimension ( homogeneous ) but different distributions (i.e., multihomogeneous-source scenario). However, in the real world, for a specific target domain, we probably have multiple different-dimension ( heterogeneous ) source domains, which do not satisfy the assumption of existing UDA methods. To remove this assumption and move forward to a realistic UDA problem, this article presents a shared-fuzzy-equivalence-relation neural network (SFERNN) for addressing the multisource heterogeneous UDA problem. The SFERNN is a five-layer neural network containing c source branches and one target branch. The network structure of the SFERNN is first confirmed by a novel fuzzy relation called multisource shared fuzzy equivalence relation. Then, we optimize parameters of the SFERNN via minimizing cross-entropy loss on c source branches and the distributional discrepancy between each source branch and the target branch. Experiments distributed across eight real-world datasets are conducted to validate the SFERNN. This testing regime demonstrates that the SFERNN outperforms the existing single-source heterogeneous UDA methods, especially when the target domain contains few data.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/157427