An Identifiable Double VAE For Disentangled Representations - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year : 2021

An Identifiable Double VAE For Disentangled Representations

Maurizio Filippone
  • Function : Author
  • PersonId : 1021042
Pietro Michiardi
  • Function : Author
  • PersonId : 1084771

Abstract

A large part of the literature on learning disentangled representations focuses on variational autoencoders (VAE). Recent developments demonstrate that disentanglement cannot be obtained in a fully unsupervised setting without inductive biases on models and data. However, Khemakhem et al., AISTATS, 2020 suggest that employing a particular form of factorized prior, conditionally dependent on auxiliary variables complementing input observations, can be one such bias, resulting in an identifiable model with guarantees on disentanglement. Working along this line, we propose a novel VAE-based generative model with theoretical guarantees on identifiability. We obtain our conditional prior over the latents by learning an optimal representation, which imposes an additional strength on their regularization. We also extend our method to semi-supervised settings. Experimental results indicate superior performance with respect to state-of-the-art approaches, according to several established metrics proposed in the literature on disentanglement.

Dates and versions

hal-03344922 , version 1 (15-09-2021)

Identifiers

Cite

Graziano Mita, Maurizio Filippone, Pietro Michiardi. An Identifiable Double VAE For Disentangled Representations. 2021. ⟨hal-03344922⟩
18 View
0 Download

Altmetric

Share

Gmail Facebook X LinkedIn More