VMI-VAE: Variational Mutual Information Maximization Framework for VAE With Discrete and Continuous Priors
From MaRDI portal
Publication:6341609
arXiv2005.13953MaRDI QIDQ6341609
Author name not available (Why is that?)
Publication date: 28 May 2020
Abstract: Variational Autoencoder is a scalable method for learning latent variable models of complex data. It employs a clear objective that can be easily optimized. However, it does not explicitly measure the quality of learned representations. We propose a Variational Mutual Information Maximization Framework for VAE to address this issue. It provides an objective that maximizes the mutual information between latent codes and observations. The objective acts as a regularizer that forces VAE to not ignore the latent code and allows one to select particular components of it to be most informative with respect to the observations. On top of that, the proposed framework provides a way to evaluate mutual information between latent codes and observations for a fixed VAE model.
Has companion code repository: https://github.com/aserdega/VMI-VAE
This page was built for publication: VMI-VAE: Variational Mutual Information Maximization Framework for VAE With Discrete and Continuous Priors
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6341609)
