Isolating Sources of Disentanglement in Variational Autoencoders

Part of Advances in Neural Information Processing Systems 31 (NeurIPS 2018)

Bibtex Metadata Paper Reviews Supplemental

Authors

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

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 the beta-TCVAE (Total Correlation Variational Autoencoder) algorithm, a refinement and plug-in replacement of the beta-VAE 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 model is trained using our framework.