Skip to yearly menu bar Skip to main content


In-Person Poster presentation / poster accept

Disentangling Learning Representations with Density Estimation

Eric Yeats · Frank Liu · Hai Li

MH1-2-3-4 #80

Keywords: [ disentanglement ] [ representation learning ] [ density estimation ] [ autoencoder ] [ Deep Learning and representational learning ]


Abstract:

Disentangled learning representations have promising utility in many applications, but they currently suffer from serious reliability issues. We present Gaussian Channel Autoencoder (GCAE), a method which achieves reliable disentanglement via scalable non-parametric density estimation of the latent space. GCAE avoids the curse of dimensionality of density estimation by disentangling subsets of its latent space with the Dual Total Correlation (DTC) metric, thereby representing its high-dimensional latent joint distribution as a collection of many low-dimensional conditional distributions. In our experiments, GCAE achieves highly competitive and reliable disentanglement scores compared with state-of-the-art baselines.

Chat is not available.