Biconditional Generative Adversarial Networks for Multiview Learning with Missing Views - Archive ouverte HAL
Conference Papers Year : 2020

Biconditional Generative Adversarial Networks for Multiview Learning with Missing Views

Abstract

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.
Fichier principal
Vignette du fichier
CondGAN.pdf (188.92 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03178193 , version 1 (23-03-2021)

Identifiers

Cite

Anastasiia Doinychko, Massih-Reza Amini. Biconditional Generative Adversarial Networks for Multiview Learning with Missing Views. 2020 European Conference on Information Retrieval, Apr 2020, Lisbon (on line), Portugal. ⟨10.1007/978-3-030-45439-5_53⟩. ⟨hal-03178193⟩
51 View
74 Download

Altmetric

Share

More