Informative GANs via Structured Regularization of Optimal Transport

12/04/2019
by   Pierre Bréchet, et al.
0

We tackle the challenge of disentangled representation learning in generative adversarial networks (GANs) from the perspective of regularized optimal transport (OT). Specifically, a smoothed OT loss gives rise to an implicit transportation plan between the latent space and the data space. Based on this theoretical observation, we exploit a structured regularization on the transportation plan to encourage a prescribed latent subspace to be informative. This yields the formulation of a novel informative OT-based GAN. By convex duality, we obtain the equivalent view that this leads to perturbed ground costs favoring sparsity in the informative latent dimensions. Practically, we devise a stable training algorithm for the proposed informative GAN. Our experiments support the hypothesis that such regularizations effectively yield the discovery of disentangled and interpretable latent representations. Our work showcases potential power of a regularized OT framework in the context of generative modeling through its access to the transport plan. Further challenges are addressed in this line.

READ FULL TEXT

page 2

page 8

page 9

research
07/09/2019

k-GANs: Ensemble of Generative Models with Semi-Discrete Optimal Transport

Generative adversarial networks (GANs) are the state of the art in gener...
research
10/26/2018

Scalable Unbalanced Optimal Transport using Generative Adversarial Networks

Generative adversarial networks (GANs) are an expressive class of neural...
research
07/29/2020

Generalization Properties of Optimal Transport GANs with Latent Distribution Learning

The Generative Adversarial Networks (GAN) framework is a well-establishe...
research
09/30/2022

Sparsity-Constrained Optimal Transport

Regularized optimal transport (OT) is now increasingly used as a loss or...
research
02/10/2020

Regularized Optimal Transport is Ground Cost Adversarial

Regularizing Wasserstein distances has proved to be the key in the recen...
research
04/25/2023

Latent Traversals in Generative Models as Potential Flows

Despite the significant recent progress in deep generative models, the u...
research
07/11/2020

Representation Learning via Adversarially-Contrastive Optimal Transport

In this paper, we study the problem of learning compact (low-dimensional...

Please sign up or login with your details

Forgot password? Click here to reset