GCVAE: Generalized-Controllable Variational AutoEncoder - Mines Saint-Étienne
Pré-Publication, Document De Travail Année : 2022

GCVAE: Generalized-Controllable Variational AutoEncoder

Résumé

Variational autoencoders (VAEs) have recently been used for unsupervised disentanglement learning of complex density distributions. Numerous variants exist to encourage disentanglement in latent space while improving reconstruction. However, none have simultaneously managed the trade-off between attaining extremely low reconstruction error and a high disentanglement score. We present a generalized framework to handle this challenge under constrained optimization and demonstrate that it outperforms state-of-the-art existing models as regards disentanglement while balancing reconstruction. We introduce three controllable Lagrangian hyperparameters to control reconstruction loss, KL divergence loss and correlation measure. We prove that maximizing information in the reconstruction network is equivalent to information maximization during amortized inference under reasonable assumptions and constraint relaxation.
Fichier principal
Vignette du fichier
2206.04225.pdf (1.1 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

emse-03712594 , version 1 (04-07-2022)

Identifiants

  • HAL Id : emse-03712594 , version 1

Citer

Kenneth Ezukwoke, Anis Hoayek, Mireille Batton-Hubert, Xavier Boucher. GCVAE: Generalized-Controllable Variational AutoEncoder. 2022. ⟨emse-03712594⟩
217 Consultations
87 Téléchargements

Partager

More