Oral
in
Workshop: Deep Generative Models and Downstream Applications
Preventing posterior collapse in variational autoencoders for text generation via decoder regularization
Alban Petit · Caio Corro
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.
Chat is not available.