# Disentanglement with Hyperspherical Latent Spaces using Diffusion Variational Autoencoders

arXiv: https://arxiv.org/abs/2003.08996 · HTML: https://mlsanity.com/paper/2003.08996/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Mar 2020.

## Built on by (most cited first, 1 of 1)

- [Semi-Supervised Manifold Learning with Complexity Decoupled Chart Autoencoders](https://mlsanity.com/paper/2208.10570/) (2022)

## Abstract (arXiv)

A disentangled representation of a data set should be capable of recovering the underlying factors that generated it. One question that arises is whether using Euclidean space for latent variable models can produce a disentangled representation when the underlying generating factors have a certain geometrical structure. Take for example the images of a car seen from different angles. The angle has a periodic structure but a 1-dimensional representation would fail to capture this topology. How can we address this problem? The submissions presented for the first stage of the NeurIPS2019 Disentanglement Challenge consist of a Diffusion Variational Autoencoder (DeltaVAE) with a hyperspherical latent space which can, for example, recover periodic true factors. The training of the DeltaVAE is enhanced by incorporating a modified version of the Evidence Lower Bound (ELBO) for tailoring the encoding capacity of the posterior approximate.