{"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/a-deep-generative-model-for-semi-supervised","title":"A Deep Generative Model for Semi-Supervised Classification with Noisy Labels","arxiv_id":"1809.05957","date":"2018-09-16","proceeding":null,"authors":["Maxime Langevin","Edouard Mehlman","Jeffrey Regier","Romain Lopez","Michael. I. Jordan","Nir Yosef"],"abstract":"Class labels are often imperfectly observed, due to mistakes and to genuine\nambiguity among classes. We propose a new semi-supervised deep generative model\nthat explicitly models noisy labels, called the Mislabeled VAE (M-VAE). The\nM-VAE can perform better than existing deep generative models which do not\naccount for label noise. Additionally, the derivation of M-VAE gives new\ntheoretical insights into the popular M1+M2 semi-supervised model.","url_abs":"http://arxiv.org/abs/1809.05957v1","url_pdf":"http://arxiv.org/pdf/1809.05957v1.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":"a-deep-generative-model-for-semi-supervised","repo_url":"https://github.com/maxime1310/fuzzy_labeling_scRNA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}