{"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/radialgan-leveraging-multiple-datasets-to","title":"RadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networks","arxiv_id":"1802.06403","date":"2018-02-18","proceeding":"ICML 2018 7","authors":["Jinsung Yoon","James Jordon","Mihaela van der Schaar"],"abstract":"Training complex machine learning models for prediction often requires a\nlarge amount of data that is not always readily available. Leveraging these\nexternal datasets from related but different sources is therefore an important\ntask if good predictive models are to be built for deployment in settings where\ndata can be rare. In this paper we propose a novel approach to the problem in\nwhich we use multiple GAN architectures to learn to translate from one dataset\nto another, thereby allowing us to effectively enlarge the target dataset, and\ntherefore learn better predictive models than if we simply used the target\ndataset. We show the utility of such an approach, demonstrating that our method\nimproves the prediction performance on the target domain over using just the\ntarget dataset and also show that our framework outperforms several other\nbenchmarks on a collection of real-world medical datasets.","url_abs":"http://arxiv.org/abs/1802.06403v2","url_pdf":"http://arxiv.org/pdf/1802.06403v2.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":"radialgan-leveraging-multiple-datasets-to","repo_url":"https://github.com/vanderschaarlab/mlforhealthlabpub/tree/main/alg/RadialGAN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null},{"paper_slug":"radialgan-leveraging-multiple-datasets-to","repo_url":"https://github.com/sandhyat/kmfchimerice_schmatch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.06403","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}