Poincaré Wasserstein Autoencoder

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.