SOTAVerified

Understanding disentangling in β-VAE

2018-04-10Code Available1· sign in to hype

Christopher P. Burgess, Irina Higgins, Arka Pal, Loic Matthey, Nick Watters, Guillaume Desjardins, Alexander Lerchner

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

We present new intuitions and theoretical assessments of the emergence of disentangled representation in variational autoencoders. Taking a rate-distortion theory perspective, we show the circumstances under which representations aligned with the underlying generative factors of variation of data emerge when optimising the modified ELBO bound in -VAE, as training progresses. From these insights, we propose a modification to the training regime of -VAE, that progressively increases the information capacity of the latent code during training. This modification facilitates the robust learning of disentangled representations in -VAE, without the previous trade-off in reconstruction accuracy.

Reproductions