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

An Identifiable Double VAE For Disentangled Representations

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.
Document type :
Preprints, Working Papers, ...
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03344922
Contributor : Centre De Documentation Eurecom Connect in order to contact the contributor
Submitted on : Wednesday, September 15, 2021 - 11:50:13 AM
Last modification on : Thursday, September 16, 2021 - 3:40:44 AM

Links full text

Identifiers

  • HAL Id : hal-03344922, version 1
  • ARXIV : 2010.09360

Collections

Citation

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

Share

Metrics

Record views

8