Variational graph autoencoders for multiview canonical correlation analysis - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Signal Processing Année : 2021

Variational graph autoencoders for multiview canonical correlation analysis

Résumé

We present a novel approach for multiview canonical correlation analysis based on a variational graph neural network model. We propose a nonlinear model which takes into account the available graph-based geometric constraints while being scalable to large-scale datasets with multiple views. This model combines the probabilistic interpretation of CCA with an autoencoder architecture based on graph convolutional neural network layers. Experiments with the proposed method are conducted on classification, clustering, and recommendation tasks on real datasets. The algorithm is competitive with state-of-the-art multiview representation learning techniques, in addition to being scalable and robust to instances with missing views.
Fichier principal
Vignette du fichier
GPCCAv3.pdf (3.45 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03436007 , version 1 (19-11-2021)

Identifiants

Citer

Yacouba Kaloga, Pierre Borgnat, Sundeep Prabhakar Chepuri, Patrice Abry, Amaury Habrard, et al.. Variational graph autoencoders for multiview canonical correlation analysis. Signal Processing, 2021, 188, pp.108182. ⟨10.1016/j.sigpro.2021.108182⟩. ⟨hal-03436007⟩
24 Consultations
81 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More