Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Isolating Sources of Disentanglement in the ELBO
Tian Qi Chen, Xuechen Li, Roger Grosse, David Duvenaud
Feb 12, 2018 (modified: Feb 12, 2018)ICLR 2018 Workshop Submissionreaders: everyone
Abstract:We decompose the evidence lower bound (ELBO) to show the existence of a total correlation term between latents. This motivates our beta-TCVAE (Total Correlation Variational Autoencoder), a refinement of the state-of-the-art beta-VAE for learning disentangled representations without supervision. We further propose a principled classifier-free measure of disentanglement called the Mutual Information Gap (MIG). We show a strong relationship between total correlation and disentanglement.
TL;DR:We propose a novel model and metric to learn and evaluate the disentanglement quality of representations.