FeGAN
Rachid Guerraoui, Arsany Guirguis, Anne-Marie Kermarrec, Erwan Le Merrer
Abstract
Existing approaches to distribute Generative Adversarial Networks (GANs) either (i) fail to scale for they typically put the two components of a GAN (the generator and the discriminator) on different machines, inducing significant communication overhead, or (ii) they face GAN training specific issues, exacerbated by distribution.
Topics & Concepts
DiscriminatorComputer scienceGenerator (circuit theory)Overhead (engineering)Generative grammarAdversarial systemFace (sociological concept)Scale (ratio)Distributed computingArtificial intelligenceComputer networkTelecommunicationsProgramming languagePower (physics)Social scienceDetectorQuantum mechanicsPhysicsSociologyAdversarial Robustness in Machine LearningDigital Media Forensic DetectionGenerative Adversarial Networks and Image Synthesis