Learning Deep-Latent Hierarchies by Stacking Wasserstein Autoencoders

TL;DR

This paper introduces a novel training method for deep-latent hierarchical generative models using Optimal Transport, overcoming limitations of Variational Autoencoders and enhancing sample quality and interpretability.

Contribution

It presents a new approach to training deep-latent hierarchies with Optimal Transport, avoiding complex inference and latent collapse issues common in VAEs.

Findings

Enables full utilization of deep-latent hierarchies

Produces higher quality, more interpretable samples

Avoids latent variable collapse in generative models

Abstract

Probabilistic models with hierarchical-latent-variable structures provide state-of-the-art results amongst non-autoregressive, unsupervised density-based models. However, the most common approach to training such models based on Variational Autoencoders (VAEs) often fails to leverage deep-latent hierarchies; successful approaches require complex inference and optimisation schemes. Optimal Transport is an alternative, non-likelihood-based framework for training generative models with appealing theoretical properties, in principle allowing easier training convergence between distributions. In this work we propose a novel approach to training models with deep-latent hierarchies based on Optimal Transport, without the need for highly bespoke models and inference networks. We show that our method enables the generative model to fully leverage its deep-latent hierarchy, avoiding the well known "latent variable collapse" issue of VAEs; therefore, providing qualitatively better sample generations as well as more interpretable latent representation than the original Wasserstein Autoencoder with Maximum Mean Discrepancy divergence.