Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

GCVAE: Generalized-Controllable Variational AutoEncoder

Abstract : 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.
Document type :
Preprints, Working Papers, ...
Complete list of metadata
Contributor : Florent Breuil Connect in order to contact the contributor
Submitted on : Monday, July 4, 2022 - 9:19:53 AM
Last modification on : Friday, August 5, 2022 - 10:51:52 AM


Files produced by the author(s)


  • HAL Id : emse-03712594, version 1


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



Record views


Files downloads