{"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/generating-multi-categorical-samples-with","title":"Generating Multi-Categorical Samples with Generative Adversarial Networks","arxiv_id":"1807.01202","date":"2018-07-03","proceeding":null,"authors":["Ramiro Camino","Christian Hammerschmidt","Radu State"],"abstract":"We propose a method to train generative adversarial networks on mutivariate\nfeature vectors representing multiple categorical values. In contrast to the\ncontinuous domain, where GAN-based methods have delivered considerable results,\nGANs struggle to perform equally well on discrete data. We propose and compare\nseveral architectures based on multiple (Gumbel) softmax output layers taking\ninto account the structure of the data. We evaluate the performance of our\narchitecture on datasets with different sparsity, number of features, ranges of\ncategorical values, and dependencies among the features. Our proposed\narchitecture and method outperforms existing models.","url_abs":"http://arxiv.org/abs/1807.01202v2","url_pdf":"http://arxiv.org/pdf/1807.01202v2.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":"generating-multi-categorical-samples-with","repo_url":"https://github.com/rcamino/multi-categorical-gans","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"generating-multi-categorical-samples-with","repo_url":"https://github.com/ydataai/ydata-synthetic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}