{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/md-gan-multi-discriminator-generative","title":"MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets","arxiv_id":"1811.03850","date":"2018-11-09","proceeding":null,"authors":["Corentin Hardy","Erwan Le Merrer","Bruno Sericola"],"abstract":"A recent technical breakthrough in the domain of machine learning is the\ndiscovery and the multiple applications of Generative Adversarial Networks\n(GANs). Those generative models are computationally demanding, as a GAN is\ncomposed of two deep neural networks, and because it trains on large datasets.\nA GAN is generally trained on a single server.\n  In this paper, we address the problem of distributing GANs so that they are\nable to train over datasets that are spread on multiple workers. MD-GAN is\nexposed as the first solution for this problem: we propose a novel learning\nprocedure for GANs so that they fit this distributed setup. We then compare the\nperformance of MD-GAN to an adapted version of Federated Learning to GANs,\nusing the MNIST and CIFAR10 datasets. MD-GAN exhibits a reduction by a factor\nof two of the learning complexity on each worker node, while providing better\nperformances than federated learning on both datasets. We finally discuss the\npractical implications of distributing GANs.","url_abs":"http://arxiv.org/abs/1811.03850v2","url_pdf":"http://arxiv.org/pdf/1811.03850v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"md-gan-multi-discriminator-generative","repo_url":"https://github.com/KhanJr/Generative-Adversarial-Networks-COMPUTER-VISION","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"md-gan-multi-discriminator-generative","repo_url":"https://github.com/SACHIN92012/Implementation-of-GAN-in-distributed-networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"md-gan-multi-discriminator-generative","repo_url":"https://github.com/bbondd/DistributedGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.03850","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}