Skip to yearly menu bar Skip to main content


Unifying GANs and Score-Based Diffusion as Generative Particle Models

Jean-Yves Franceschi · Mike Gartrell · Ludovic Dos Santos · Thibaut Issenhuth · Emmanuel de B├ęzenac · Mickael Chen · Alain Rakotomamonjy

Great Hall & Hall B1+B2 (level 1) #521
[ ] [ Project Page ]
[ Paper [ Slides [ Poster [ OpenReview
Wed 13 Dec 8:45 a.m. PST — 10:45 a.m. PST


Particle-based deep generative models, such as gradient flows and score-based diffusion models, have recently gained traction thanks to their striking performance. Their principle of displacing particle distributions using differential equations is conventionally seen as opposed to the previously widespread generative adversarial networks (GANs), which involve training a pushforward generator network. In this paper we challenge this interpretation, and propose a novel framework that unifies particle and adversarial generative models by framing generator training as a generalization of particle models. This suggests that a generator is an optional addition to any such generative model. Consequently, integrating a generator into a score-based diffusion model and training a GAN without a generator naturally emerge from our framework. We empirically test the viability of these original models as proofs of concepts of potential applications of our framework.

Chat is not available.