# Hyperprior Induced Unsupervised Disentanglement of Latent Representations

arXiv: https://arxiv.org/abs/1809.04497 · HTML: https://mlsanity.com/paper/1809.04497/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Sep 2018.

## Built on by (most cited first, 6 of 6)

- [Symmetry-Based Representations for Artificial and Biological General Intelligence](https://mlsanity.com/paper/2203.09250/) (2022)
- [On Incorporating Inductive Biases into VAEs](https://mlsanity.com/paper/2106.13746/) (2021)
- [SKILL-IL: Disentangling Skill and Knowledge in Multitask Imitation Learning](https://mlsanity.com/paper/2205.03130/) (2022)
- [HAVANA: Hierarchical and Variation-Normalized Autoencoder for Person Re-identification](https://mlsanity.com/paper/2101.02568/) (2021)
- [Autoencoded sparse Bayesian in-IRT factorization, calibration, and amortized inference for the Work Disability Functional Assessment Battery](https://mlsanity.com/paper/2210.10952/) (2022)
- [3DLatNav: Navigating Generative Latent Spaces for Semantic-Aware 3D Object Manipulation](https://mlsanity.com/paper/2211.09770/) (2022)

## Abstract (arXiv)

We address the problem of unsupervised disentanglement of latent representations learnt via deep generative models. In contrast to current approaches that operate on the evidence lower bound (ELBO), we argue that statistical independence in the latent space of VAEs can be enforced in a principled hierarchical Bayesian manner. To this effect, we augment the standard VAE with an inverse-Wishart (IW) prior on the covariance matrix of the latent code. By tuning the IW parameters, we are able to encourage (or discourage) independence in the learnt latent dimensions. Extensive experimental results on a range of datasets (2DShapes, 3DChairs, 3DFaces and CelebA) show our approach to outperform the β-VAE and is competitive with the state-of-the-art FactorVAE. Our approach achieves significantly better disentanglement and reconstruction on a new dataset (CorrelatedEllipses) which introduces correlations between the factors of variation.