Geometry of Deep Generative Models for Disentangled Representations

by   Ankita Shukla, et al.
Arizona State University
IIIT Delhi

Deep generative models like variational autoencoders approximate the intrinsic geometry of high dimensional data manifolds by learning low-dimensional latent-space variables and an embedding function. The geometric properties of these latent spaces has been studied under the lens of Riemannian geometry; via analysis of the non-linearity of the generator function. In new developments, deep generative models have been used for learning semantically meaningful `disentangled' representations; that capture task relevant attributes while being invariant to other attributes. In this work, we explore the geometry of popular generative models for disentangled representation learning. We use several metrics to compare the properties of latent spaces of disentangled representation models in terms of class separability and curvature of the latent-space. The results we obtain establish that the class distinguishable features in the disentangled latent space exhibits higher curvature as opposed to a variational autoencoder. We evaluate and compare the geometry of three such models with variational autoencoder on two different datasets. Further, our results show that distances and interpolation in the latent space are significantly improved with Riemannian metrics derived from the curvature of the space. We expect these results will have implications on understanding how deep-networks can be made more robust, generalizable, as well as interpretable.


page 6

page 7


The Riemannian Geometry of Deep Generative Models

Deep generative models learn a mapping from a low dimensional latent spa...

Latent Space Oddity: on the Curvature of Deep Generative Models

Deep generative models provide a systematic way to learn nonlinear data ...

Geodesic Clustering in Deep Generative Models

Deep generative models are tremendously successful in learning low-dimen...

VTAE: Variational Transformer Autoencoder with Manifolds Learning

Deep generative models have demonstrated successful applications in lear...

Latent Translation: Crossing Modalities by Bridging Generative Models

End-to-end optimization has achieved state-of-the-art performance on man...

On Explicit Curvature Regularization in Deep Generative Models

We propose a family of curvature-based regularization terms for deep gen...

Mario Plays on a Manifold: Generating Functional Content in Latent Space through Differential Geometry

Deep generative models can automatically create content of diverse types...

Please sign up or login with your details

Forgot password? Click here to reset