InfoCatVAE: Representation Learning with Categorical Variational Autoencoders
Machine Learning
2018-06-26 v2 Machine Learning
Abstract
This paper describes InfoCatVAE, an extension of the variational autoencoder that enables unsupervised disentangled representation learning. InfoCatVAE uses multimodal distributions for the prior and the inference network and then maximizes the evidence lower bound objective (ELBO). We connect the new ELBO derived for our model with a natural soft clustering objective which explains the robustness of our approach. We then adapt the InfoGANs method to our setting in order to maximize the mutual information between the categorical code and the generated inputs and obtain an improved model.
Cite
@article{arxiv.1806.08240,
title = {InfoCatVAE: Representation Learning with Categorical Variational Autoencoders},
author = {Edouard Pineau and Marc Lelarge},
journal= {arXiv preprint arXiv:1806.08240},
year = {2018}
}
Comments
9 pages, 3 appendix, 5 figures. arXiv admin note: text overlap with arXiv:1606.03657 by other authors