Disentangling Learning Representations with Density Estimation
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.
Cite
Text
Yeats et al. "Disentangling Learning Representations with Density Estimation." International Conference on Learning Representations, 2023.Markdown
[Yeats et al. "Disentangling Learning Representations with Density Estimation." International Conference on Learning Representations, 2023.](https://mlanthology.org/iclr/2023/yeats2023iclr-disentangling/)BibTeX
@inproceedings{yeats2023iclr-disentangling,
title = {{Disentangling Learning Representations with Density Estimation}},
author = {Yeats, Eric and Liu, Frank Y and Li, Hai},
booktitle = {International Conference on Learning Representations},
year = {2023},
url = {https://mlanthology.org/iclr/2023/yeats2023iclr-disentangling/}
}