{"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/improving-missing-data-imputation-with-deep","title":"Improving Missing Data Imputation with Deep Generative Models","arxiv_id":"1902.10666","date":"2019-02-27","proceeding":null,"authors":["Ramiro D. Camino","Christian A. Hammerschmidt","Radu State"],"abstract":"Datasets with missing values are very common on industry applications, and\nthey can have a negative impact on machine learning models. Recent studies\nintroduced solutions to the problem of imputing missing values based on deep\ngenerative models. Previous experiments with Generative Adversarial Networks\nand Variational Autoencoders showed interesting results in this domain, but it\nis not clear which method is preferable for different use cases. The goal of\nthis work is twofold: we present a comparison between missing data imputation\nsolutions based on deep generative models, and we propose improvements over\nthose methodologies. We run our experiments using known real life datasets with\ndifferent characteristics, removing values at random and reconstructing them\nwith several imputation techniques. Our results show that the presence or\nabsence of categorical variables can alter the selection of the best model, and\nthat some models are more stable than others after similar runs with different\nrandom number generator seeds.","url_abs":"http://arxiv.org/abs/1902.10666v1","url_pdf":"http://arxiv.org/pdf/1902.10666v1.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":"improving-missing-data-imputation-with-deep","repo_url":"https://github.com/rcamino/multi-categorical-gans","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"imputation","task_name":"Imputation"},{"task_slug":"missing-values","task_name":"Missing Values"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.10666","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}