Cargando…

Biconditional Generative Adversarial Networks for Multiview Learning with Missing Views

In this paper, we present a conditional GAN with two generators and a common discriminator for multiview learning problems where observations have two views, but one of them may be missing for some of the training samples. This is for example the case for multilingual collections where documents are...

Descripción completa

Detalles Bibliográficos
Autores principales: Doinychko, Anastasiia, Amini, Massih-Reza
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7148219/
http://dx.doi.org/10.1007/978-3-030-45439-5_53
_version_ 1783520546317664256
author Doinychko, Anastasiia
Amini, Massih-Reza
author_facet Doinychko, Anastasiia
Amini, Massih-Reza
author_sort Doinychko, Anastasiia
collection PubMed
description In this paper, we present a conditional GAN with two generators and a common discriminator for multiview learning problems where observations have two views, but one of them may be missing for some of the training samples. This is for example the case for multilingual collections where documents are not available in all languages. Some studies tackled this problem by assuming the existence of view generation functions to approximately complete the missing views; for example Machine Translation to translate documents into the missing languages. These functions generally require an external resource to be set and their quality has a direct impact on the performance of the learned multiview classifier over the completed training set. Our proposed approach addresses this problem by jointly learning the missing views and the multiview classifier using a tripartite game with two generators and a discriminator. Each of the generators is associated to one of the views and tries to fool the discriminator by generating the other missing view conditionally on the corresponding observed view. The discriminator then tries to identify if for an observation, one of its views is completed by one of the generators or if both views are completed along with its class. Our results on a subset of Reuters RCV1/RCV2 collections show that the discriminator achieves significant classification performance; and that the generators learn the missing views with high quality without the need of any consequent external resource.
format Online
Article
Text
id pubmed-7148219
institution National Center for Biotechnology Information
language English
publishDate 2020
record_format MEDLINE/PubMed
spelling pubmed-71482192020-04-13 Biconditional Generative Adversarial Networks for Multiview Learning with Missing Views Doinychko, Anastasiia Amini, Massih-Reza Advances in Information Retrieval Article In this paper, we present a conditional GAN with two generators and a common discriminator for multiview learning problems where observations have two views, but one of them may be missing for some of the training samples. This is for example the case for multilingual collections where documents are not available in all languages. Some studies tackled this problem by assuming the existence of view generation functions to approximately complete the missing views; for example Machine Translation to translate documents into the missing languages. These functions generally require an external resource to be set and their quality has a direct impact on the performance of the learned multiview classifier over the completed training set. Our proposed approach addresses this problem by jointly learning the missing views and the multiview classifier using a tripartite game with two generators and a discriminator. Each of the generators is associated to one of the views and tries to fool the discriminator by generating the other missing view conditionally on the corresponding observed view. The discriminator then tries to identify if for an observation, one of its views is completed by one of the generators or if both views are completed along with its class. Our results on a subset of Reuters RCV1/RCV2 collections show that the discriminator achieves significant classification performance; and that the generators learn the missing views with high quality without the need of any consequent external resource. 2020-03-17 /pmc/articles/PMC7148219/ http://dx.doi.org/10.1007/978-3-030-45439-5_53 Text en © Springer Nature Switzerland AG 2020 This article is made available via the PMC Open Access Subset for unrestricted research re-use and secondary analysis in any form or by any means with acknowledgement of the original source. These permissions are granted for the duration of the World Health Organization (WHO) declaration of COVID-19 as a global pandemic.
spellingShingle Article
Doinychko, Anastasiia
Amini, Massih-Reza
Biconditional Generative Adversarial Networks for Multiview Learning with Missing Views
title Biconditional Generative Adversarial Networks for Multiview Learning with Missing Views
title_full Biconditional Generative Adversarial Networks for Multiview Learning with Missing Views
title_fullStr Biconditional Generative Adversarial Networks for Multiview Learning with Missing Views
title_full_unstemmed Biconditional Generative Adversarial Networks for Multiview Learning with Missing Views
title_short Biconditional Generative Adversarial Networks for Multiview Learning with Missing Views
title_sort biconditional generative adversarial networks for multiview learning with missing views
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7148219/
http://dx.doi.org/10.1007/978-3-030-45439-5_53
work_keys_str_mv AT doinychkoanastasiia biconditionalgenerativeadversarialnetworksformultiviewlearningwithmissingviews
AT aminimassihreza biconditionalgenerativeadversarialnetworksformultiviewlearningwithmissingviews