Poincaré Wasserstein Autoencoder
This work addresses the need for hierarchical latent representations in machine learning, though it is incremental as it adapts an existing framework to a non-Euclidean space.
The authors tackled the problem of learning structured latent representations by reformulating the Wasserstein autoencoder framework on the hyperbolic Poincaré ball manifold, demonstrating competitive results on a graph link prediction task.
This work presents a reformulation of the recently proposed Wasserstein autoencoder framework on a non-Euclidean manifold, the Poincaré ball model of the hyperbolic space. By assuming the latent space to be hyperbolic, we can use its intrinsic hierarchy to impose structure on the learned latent space representations. We demonstrate the model in the visual domain to analyze some of its properties and show competitive results on a graph link prediction task.