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 flexible 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.
@article{arxiv.2302.04362,
title = {Disentangling Learning Representations with Density Estimation},
author = {Eric Yeats and Frank Liu and Hai Li},
journal= {arXiv preprint arXiv:2302.04362},
year = {2023}
}
Comments
Accepted to ICLR 2023; Code available: https://github.com/ericyeats/gcae-disentanglement