{"intvolume":"        23","volume":23,"year":"2022","acknowledgement":"The authors thank Eugenia Iofinova and Bernd Prach for providing feedback on early versions of this paper. This publication was made possible by an ETH AI Center postdoctoral fellowship to Nikola Konstantinov.","file_date_updated":"2022-07-12T15:08:28Z","keyword":["Fairness","robustness","data poisoning","trustworthy machine learning","PAC learning"],"ddc":["004"],"has_accepted_license":"1","publication":"Journal of Machine Learning Research","author":[{"last_name":"Konstantinov","first_name":"Nikola H","full_name":"Konstantinov, Nikola H","id":"4B9D76E4-F248-11E8-B48F-1D18A9856A87"},{"orcid":"0000-0002-4561-241X","full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","first_name":"Christoph","last_name":"Lampert"}],"page":"1-60","external_id":{"arxiv":["2102.06004"]},"publication_identifier":{"eissn":["1533-7928"],"issn":["1532-4435"]},"citation":{"chicago":"Konstantinov, Nikola H, and Christoph Lampert. “Fairness-Aware PAC Learning from Corrupted Data.” <i>Journal of Machine Learning Research</i>. ML Research Press, 2022.","apa":"Konstantinov, N. H., &#38; Lampert, C. (2022). Fairness-aware PAC learning from corrupted data. <i>Journal of Machine Learning Research</i>. ML Research Press.","ista":"Konstantinov NH, Lampert C. 2022. Fairness-aware PAC learning from corrupted data. Journal of Machine Learning Research. 23, 1–60.","ama":"Konstantinov NH, Lampert C. Fairness-aware PAC learning from corrupted data. <i>Journal of Machine Learning Research</i>. 2022;23:1-60.","short":"N.H. Konstantinov, C. Lampert, Journal of Machine Learning Research 23 (2022) 1–60.","mla":"Konstantinov, Nikola H., and Christoph Lampert. “Fairness-Aware PAC Learning from Corrupted Data.” <i>Journal of Machine Learning Research</i>, vol. 23, ML Research Press, 2022, pp. 1–60.","ieee":"N. H. Konstantinov and C. Lampert, “Fairness-aware PAC learning from corrupted data,” <i>Journal of Machine Learning Research</i>, vol. 23. ML Research Press, pp. 1–60, 2022."},"article_type":"original","_id":"10802","language":[{"iso":"eng"}],"oa_version":"Published Version","oa":1,"date_created":"2022-02-28T14:05:42Z","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","publisher":"ML Research Press","scopus_import":"1","quality_controlled":"1","title":"Fairness-aware PAC learning from corrupted data","status":"public","related_material":{"record":[{"relation":"dissertation_contains","id":"10799","status":"public"},{"id":"13241","relation":"shorter_version","status":"public"}]},"type":"journal_article","file":[{"checksum":"9cac897b54a0ddf3a553a2c33e88cfda","relation":"main_file","content_type":"application/pdf","creator":"kschuh","access_level":"open_access","file_name":"2022_JournalMachineLearningResearch_Konstantinov.pdf","date_updated":"2022-07-12T15:08:28Z","success":1,"file_id":"11570","date_created":"2022-07-12T15:08:28Z","file_size":551862}],"day":"01","article_processing_charge":"No","month":"05","date_updated":"2023-09-26T10:44:37Z","tmp":{"image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","short":"CC BY (4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode"},"publication_status":"published","date_published":"2022-05-01T00:00:00Z","department":[{"_id":"ChLa"}],"abstract":[{"text":"Addressing fairness concerns about machine learning models is a crucial step towards their long-term adoption in real-world automated systems. While many approaches have been developed for training fair models from data, little is known about the robustness of these methods to data corruption. In this work we consider fairness-aware learning under worst-case data manipulations. We show that an adversary can in some situations force any learner to return an overly biased classifier, regardless of the sample size and with or without degrading\r\naccuracy, and that the strength of the excess bias increases for learning problems with underrepresented protected groups in the data. We also prove that our hardness results are tight up to constant factors. To this end, we study two natural learning algorithms that optimize for both accuracy and fairness and show that these algorithms enjoy guarantees that are order-optimal in terms of the corruption ratio and the protected groups frequencies in the large data\r\nlimit.","lang":"eng"}]}