SOTAVerified

Isolating Sources of Disentanglement in Variational Autoencoders

2018-02-14NeurIPS 2018Code Available1· sign in to hype

Ricky T. Q. Chen, Xuechen Li, Roger Grosse, David Duvenaud

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

We decompose the evidence lower bound to show the existence of a term measuring the total correlation between latent variables. We use this to motivate our -TCVAE (Total Correlation Variational Autoencoder), a refinement of the state-of-the-art -VAE objective for learning disentangled representations, requiring no additional hyperparameters during training. We further propose a principled classifier-free measure of disentanglement called the mutual information gap (MIG). We perform extensive quantitative and qualitative experiments, in both restricted and non-restricted settings, and show a strong relation between total correlation and disentanglement, when the latent variables model is trained using our framework.

Tasks

Reproductions