Poincaré Wasserstein Autoencoder

Ivan Ovinnikov

TL;DR: Wasserstein Autoencoder with hyperbolic latent space

Abstract:

This work presents the Poincaré Wasserstein Autoencoder, a reformulation of
the recently proposed Wasserstein autoencoder framework on a non-Euclidean
manifold, the Poincaré ball model of the hyperbolic space H n . By assuming the
latent space to be hyperbolic, we can use its intrinsic hierarchy to impose structure
on the learned latent space representations. We show that for datasets with latent
hierarchies, we can recover the structure in a low-dimensional latent space. We
also demonstrate the model in the visual domain to analyze some of its properties
and show competitive results on a graph link prediction task.

Code: https://github.com/io-papercode/pwa

Keywords: Variational inference, hyperbolic geometry, hierarchical latent space, representation learning