Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/151222
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLi, Yangen_US
dc.contributor.authorPan, Quanen_US
dc.contributor.authorWang, Suhangen_US
dc.contributor.authorPeng, Haiyunen_US
dc.contributor.authorYang, Taoen_US
dc.contributor.authorCambria, Eriken_US
dc.date.accessioned2021-06-09T07:10:13Z-
dc.date.available2021-06-09T07:10:13Z-
dc.date.issued2019-
dc.identifier.citationLi, Y., Pan, Q., Wang, S., Peng, H., Yang, T. & Cambria, E. (2019). Disentangled variational auto-encoder for semi-supervised learning. Information Sciences, 482, 73-85. https://dx.doi.org/10.1016/j.ins.2018.12.057en_US
dc.identifier.issn0020-0255en_US
dc.identifier.other0000-0002-3030-1280-
dc.identifier.urihttps://hdl.handle.net/10356/151222-
dc.description.abstractSemi-supervised learning is attracting increasing attention due to the fact that datasets of many domains lack enough labeled data. Variational Auto-Encoder (VAE), in particular, has demonstrated the benefits of semi-supervised learning. The majority of existing semi-supervised VAEs utilize a classifier to exploit label information, where the parameters of the classifier are introduced to the VAE. Given the limited labeled data, learning the parameters for the classifiers may not be an optimal solution for exploiting label information. Therefore, in this paper, we develop a novel approach for semi-supervised VAE without classifier. Specifically, we propose a new model called Semi-supervised Disentangled VAE (SDVAE), which encodes the input data into disentangled representation and non-interpretable representation, then the category information is directly utilized to regularize the disentangled representation via the equality constraint. To further enhance the feature learning ability of the proposed VAE, we incorporate reinforcement learning to relieve the lack of data. The dynamic framework is capable of dealing with both image and text data with its corresponding encoder and decoder networks. Extensive experiments on image and text datasets demonstrate the effectiveness of the proposed framework.en_US
dc.language.isoenen_US
dc.relation.ispartofInformation Sciencesen_US
dc.rights© 2019 Elsevier Inc. All rights reserved.en_US
dc.subjectEngineering::Computer science and engineeringen_US
dc.titleDisentangled variational auto-encoder for semi-supervised learningen_US
dc.typeJournal Articleen
dc.contributor.schoolSchool of Computer Science and Engineeringen_US
dc.identifier.doi10.1016/j.ins.2018.12.057-
dc.identifier.scopus2-s2.0-85059744324-
dc.identifier.volume482en_US
dc.identifier.spage73en_US
dc.identifier.epage85en_US
dc.subject.keywordsSemi-supervised Learningen_US
dc.subject.keywordsVariational Auto-encoderen_US
item.grantfulltextnone-
item.fulltextNo Fulltext-
Appears in Collections:SCSE Journal Articles

Page view(s)

47
Updated on Oct 18, 2021

Google ScholarTM

Check

Altmetric


Plumx

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