Geometrically Enriched Latent Spaces

Abstract

A common assumption in generative models is that the generator immerses the latent space into a Euclidean ambient space. Instead, we consider the ambient space to be a Riemannian manifold, which allows for encoding domain knowledge through the associated Riemannian metric. Shortest paths can then be defined accordingly in the latent space to both follow the learned manifold and respect the ambient geometry. Through careful design of the ambient metric we can ensure that shortest paths are well-behaved even for deterministic generators that otherwise would exhibit a misleading bias. Experimentally we show that our approach improves interpretability of learned representations both using stochastic and deterministic generators.

References in corpus (11)

• Auto-Encoding Variational Bayes
• Conditional Generative Adversarial Nets
• Deep Residual Learning for Image Recognition
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• Variational Inference with Normalizing Flows
• Density estimation using Real NVP
• Metrics for Probabilistic Geometries
• Fast and Robust Shortest Paths on Manifolds Learned from Data
• Geodesic Clustering in Deep Generative Models
• Learning disconnected manifolds: a no GANs land
• Expected path length on random manifolds