# β-VAEs can retain label information even at high compression

arXiv: https://arxiv.org/abs/1812.02682 · HTML: https://mlsanity.com/paper/1812.02682/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Dec 2018.

## Built on by (most cited first, 2 of 2)

- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [Disentangled Representation Learning Using (β-)VAE and GAN](https://mlsanity.com/paper/2208.04549/) (2022)

## Abstract (arXiv)

In this paper, we investigate the degree to which the encoding of a β-VAE captures label information across multiple architectures on Binary Static MNIST and Omniglot. Even though they are trained in a completely unsupervised manner, we demonstrate that a β-VAE can retain a large amount of label information, even when asked to learn a highly compressed representation.