{"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-robust-ensemble-approach-to-learn-from","title":"A Robust Ensemble Approach to Learn From Positive and Unlabeled Data Using SVM Base Models","arxiv_id":"1402.3144","date":"2014-02-13","proceeding":null,"authors":["Marc Claesen","Frank De Smet","Johan A. K. Suykens","Bart De Moor"],"abstract":"We present a novel approach to learn binary classifiers when only positive\nand unlabeled instances are available (PU learning). This problem is routinely\ncast as a supervised task with label noise in the negative set. We use an\nensemble of SVM models trained on bootstrap resamples of the training data for\nincreased robustness against label noise. The approach can be considered in a\nbagging framework which provides an intuitive explanation for its mechanics in\na semi-supervised setting. We compared our method to state-of-the-art\napproaches in simulations using multiple public benchmark data sets. The\nincluded benchmark comprises three settings with increasing label noise: (i)\nfully supervised, (ii) PU learning and (iii) PU learning with false positives.\nOur approach shows a marginal improvement over existing methods in the second\nsetting and a significant improvement in the third.","url_abs":"http://arxiv.org/abs/1402.3144v2","url_pdf":"http://arxiv.org/pdf/1402.3144v2.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-robust-ensemble-approach-to-learn-from","repo_url":"https://github.com/claesenm/resvm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[{"method_slug":"svm","method_name":"SVM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}