Unsupervised multi-source domain adaptation with no observable source data.

Given trained models from multiple source domains, how can we predict the labels of unlabeled data in a target domain? Unsupervised multi-source domain adaptation (UMDA) aims for predicting the labels of unlabeled target data by transferring the knowledge of multiple source domains. UMDA is a crucia...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hyunsik Jeon, Seongmin Lee, U Kang
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/23a4fccc91304804b1a1b90f9f7b92e7
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:23a4fccc91304804b1a1b90f9f7b92e7
record_format	dspace
spelling	oai:doaj.org-article:23a4fccc91304804b1a1b90f9f7b92e72021-12-02T20:05:07ZUnsupervised multi-source domain adaptation with no observable source data.1932-620310.1371/journal.pone.0253415https://doaj.org/article/23a4fccc91304804b1a1b90f9f7b92e72021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0253415https://doaj.org/toc/1932-6203Given trained models from multiple source domains, how can we predict the labels of unlabeled data in a target domain? Unsupervised multi-source domain adaptation (UMDA) aims for predicting the labels of unlabeled target data by transferring the knowledge of multiple source domains. UMDA is a crucial problem in many real-world scenarios where no labeled target data are available. Previous approaches in UMDA assume that data are observable over all domains. However, source data are not easily accessible due to privacy or confidentiality issues in a lot of practical scenarios, although classifiers learned in source domains are readily available. In this work, we target data-free UMDA where source data are not observable at all, a novel problem that has not been studied before despite being very realistic and crucial. To solve data-free UMDA, we propose DEMS (Data-free Exploitation of Multiple Sources), a novel architecture that adapts target data to source domains without exploiting any source data, and estimates the target labels by exploiting pre-trained source classifiers. Extensive experiments for data-free UMDA on real-world datasets show that DEMS provides the state-of-the-art accuracy which is up to 27.5% point higher than that of the best baseline.Hyunsik JeonSeongmin LeeU KangPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 7, p e0253415 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Hyunsik Jeon Seongmin Lee U Kang Unsupervised multi-source domain adaptation with no observable source data.
description	Given trained models from multiple source domains, how can we predict the labels of unlabeled data in a target domain? Unsupervised multi-source domain adaptation (UMDA) aims for predicting the labels of unlabeled target data by transferring the knowledge of multiple source domains. UMDA is a crucial problem in many real-world scenarios where no labeled target data are available. Previous approaches in UMDA assume that data are observable over all domains. However, source data are not easily accessible due to privacy or confidentiality issues in a lot of practical scenarios, although classifiers learned in source domains are readily available. In this work, we target data-free UMDA where source data are not observable at all, a novel problem that has not been studied before despite being very realistic and crucial. To solve data-free UMDA, we propose DEMS (Data-free Exploitation of Multiple Sources), a novel architecture that adapts target data to source domains without exploiting any source data, and estimates the target labels by exploiting pre-trained source classifiers. Extensive experiments for data-free UMDA on real-world datasets show that DEMS provides the state-of-the-art accuracy which is up to 27.5% point higher than that of the best baseline.
format	article
author	Hyunsik Jeon Seongmin Lee U Kang
author_facet	Hyunsik Jeon Seongmin Lee U Kang
author_sort	Hyunsik Jeon
title	Unsupervised multi-source domain adaptation with no observable source data.
title_short	Unsupervised multi-source domain adaptation with no observable source data.
title_full	Unsupervised multi-source domain adaptation with no observable source data.
title_fullStr	Unsupervised multi-source domain adaptation with no observable source data.
title_full_unstemmed	Unsupervised multi-source domain adaptation with no observable source data.
title_sort	unsupervised multi-source domain adaptation with no observable source data.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/23a4fccc91304804b1a1b90f9f7b92e7
work_keys_str_mv	AT hyunsikjeon unsupervisedmultisourcedomainadaptationwithnoobservablesourcedata AT seongminlee unsupervisedmultisourcedomainadaptationwithnoobservablesourcedata AT ukang unsupervisedmultisourcedomainadaptationwithnoobservablesourcedata
_version_	1718375469721583616

Unsupervised multi-source domain adaptation with no observable source data.

Ejemplares similares