{"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/identifying-mislabeled-data-using-the-area","title":"Identifying Mislabeled Data using the Area Under the Margin Ranking","arxiv_id":"2001.10528","date":"2020-01-28","proceeding":"NeurIPS 2020 12","authors":["Geoff Pleiss","Tianyi Zhang","Ethan R. Elenberg","Kilian Q. Weinberger"],"abstract":"Not all data in a typical training set help with generalization; some samples can be overly ambiguous or outrightly mislabeled. This paper introduces a new method to identify such samples and mitigate their impact when training neural networks. At the heart of our algorithm is the Area Under the Margin (AUM) statistic, which exploits differences in the training dynamics of clean and mislabeled samples. A simple procedure - adding an extra class populated with purposefully mislabeled threshold samples - learns a AUM upper bound that isolates mislabeled data. This approach consistently improves upon prior work on synthetic and real-world datasets. On the WebVision50 classification task our method removes 17% of training data, yielding a 1.6% (absolute) improvement in test error. On CIFAR100 removing 13% of the data leads to a 1.2% drop in error.","url_abs":"https://arxiv.org/abs/2001.10528v4","url_pdf":"https://arxiv.org/pdf/2001.10528v4.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":"identifying-mislabeled-data-using-the-area","repo_url":"https://github.com/asappresearch/aum","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"identifying-mislabeled-data-using-the-area","repo_url":"https://github.com/AlexKubiesa/area-under-the-margin-ranking","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"identifying-mislabeled-data-using-the-area","repo_url":"https://github.com/Manuscrit/Area-Under-the-Margin-Ranking","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2001.10528","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.10528"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AlexKubiesa/area-under-the-margin-ranking","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/asappresearch/aum","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Manuscrit/Area-Under-the-Margin-Ranking","reach":null}],"summary":{"ran":3,"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"repositories":1},"listed":{"samples":3,"ran":3,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"5332cc63be8cc094","entry":"AUM","repo":"AlexKubiesa/area-under-the-margin-ranking","repo_kind":"listed","path":"aum_ranking.py","file_url":"https://github.com/AlexKubiesa/area-under-the-margin-ranking/blob/HEAD/aum_ranking.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5332cc63be8cc094"}},{"code_sha256_prefix":"4f73ae08cdd6cc71","entry":"AreaUnderTheMarginRanking","repo":"Manuscrit/Area-Under-the-Margin-Ranking","repo_kind":"listed","path":"area_under_margin.py","file_url":"https://github.com/Manuscrit/Area-Under-the-Margin-Ranking/blob/HEAD/area_under_margin.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4f73ae08cdd6cc71"}},{"code_sha256_prefix":"093952b4cc1de7a8","entry":"ConstantTargetDataset","repo":"Manuscrit/Area-Under-the-Margin-Ranking","repo_kind":"listed","path":"area_under_margin.py","file_url":"https://github.com/Manuscrit/Area-Under-the-Margin-Ranking/blob/HEAD/area_under_margin.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"093952b4cc1de7a8"}},{"code_sha256_prefix":"6c8e3288a92eec18","entry":"AUMCalculator","repo":"asappresearch/aum","repo_kind":"official","path":"aum/aum.py","file_url":"https://github.com/asappresearch/aum/blob/HEAD/aum/aum.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6c8e3288a92eec18"}},{"code_sha256_prefix":"40d9bc8a5455b81a","entry":"AUMRecord","repo":"asappresearch/aum","repo_kind":"official","path":"aum/aum.py","file_url":"https://github.com/asappresearch/aum/blob/HEAD/aum/aum.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"40d9bc8a5455b81a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}