English

Preventing posterior collapse in variational autoencoders for text generation via decoder regularization

Machine Learning 2021-10-29 v1 Computation and Language

Abstract

Variational autoencoders trained to minimize the reconstruction error are sensitive to the posterior collapse problem, that is the proposal posterior distribution is always equal to the prior. We propose a novel regularization method based on fraternal dropout to prevent posterior collapse. We evaluate our approach using several metrics and observe improvements in all the tested configurations.

Cite

@article{arxiv.2110.14945,
  title  = {Preventing posterior collapse in variational autoencoders for text generation via decoder regularization},
  author = {Alban Petit and Caio Corro},
  journal= {arXiv preprint arXiv:2110.14945},
  year   = {2021}
}

Comments

Accepted at NeurIPS 2021 Workshop DGMs Applications

R2 v1 2026-06-24T07:15:25.597Z