{"publication_status":"published","date_published":"2022-12-22T00:00:00Z","department":[{"_id":"ChLa"}],"abstract":[{"text":"Fairness-aware learning aims at constructing classifiers that not only make accurate predictions, but also do not discriminate against specific groups. It is a fast-growing area of\r\nmachine learning with far-reaching societal impact. However, existing fair learning methods\r\nare vulnerable to accidental or malicious artifacts in the training data, which can cause\r\nthem to unknowingly produce unfair classifiers. In this work we address the problem of\r\nfair learning from unreliable training data in the robust multisource setting, where the\r\navailable training data comes from multiple sources, a fraction of which might not be representative of the true data distribution. We introduce FLEA, a filtering-based algorithm\r\nthat identifies and suppresses those data sources that would have a negative impact on\r\nfairness or accuracy if they were used for training. As such, FLEA is not a replacement of\r\nprior fairness-aware learning methods but rather an augmentation that makes any of them\r\nrobust against unreliable training data. We show the effectiveness of our approach by a\r\ndiverse range of experiments on multiple datasets. Additionally, we prove formally that\r\n–given enough data– FLEA protects the learner against corruptions as long as the fraction of\r\naffected data sources is less than half. Our source code and documentation are available at\r\nhttps://github.com/ISTAustria-CVML/FLEA.","lang":"eng"}],"main_file_link":[{"url":"https://openreview.net/forum?id=XsPopigZXV","open_access":"1"}],"file":[{"date_updated":"2023-02-23T10:30:04Z","file_id":"12673","success":1,"date_created":"2023-02-23T10:30:04Z","file_size":1948063,"relation":"main_file","checksum":"97c8a8470759cab597abb973ca137a3b","content_type":"application/pdf","file_name":"2022_TMLR_Iofinova.pdf","creator":"dernst","access_level":"open_access"}],"license":"https://creativecommons.org/licenses/by/4.0/","type":"journal_article","day":"22","month":"12","article_processing_charge":"No","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"},"date_updated":"2023-02-23T10:30:54Z","quality_controlled":"1","title":"FLEA: Provably robust fair multisource learning from unreliable training data","related_material":{"link":[{"relation":"software","description":"source code","url":"https://github.com/ISTAustria-CVML/FLEA"}]},"status":"public","oa":1,"oa_version":"Published Version","date_created":"2023-02-02T20:29:57Z","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","publisher":"ML Research Press","citation":{"chicago":"Iofinova, Eugenia B, Nikola H Konstantinov, and Christoph Lampert. “FLEA: Provably Robust Fair Multisource Learning from Unreliable Training Data.” <i>Transactions on Machine Learning Research</i>. ML Research Press, 2022.","ista":"Iofinova EB, Konstantinov NH, Lampert C. 2022. FLEA: Provably robust fair multisource learning from unreliable training data. Transactions on Machine Learning Research.","apa":"Iofinova, E. B., Konstantinov, N. H., &#38; Lampert, C. (2022). FLEA: Provably robust fair multisource learning from unreliable training data. <i>Transactions on Machine Learning Research</i>. ML Research Press.","ama":"Iofinova EB, Konstantinov NH, Lampert C. FLEA: Provably robust fair multisource learning from unreliable training data. <i>Transactions on Machine Learning Research</i>. 2022.","short":"E.B. Iofinova, N.H. Konstantinov, C. Lampert, Transactions on Machine Learning Research (2022).","mla":"Iofinova, Eugenia B., et al. “FLEA: Provably Robust Fair Multisource Learning from Unreliable Training Data.” <i>Transactions on Machine Learning Research</i>, ML Research Press, 2022.","ieee":"E. B. Iofinova, N. H. Konstantinov, and C. Lampert, “FLEA: Provably robust fair multisource learning from unreliable training data,” <i>Transactions on Machine Learning Research</i>. ML Research Press, 2022."},"article_type":"original","language":[{"iso":"eng"}],"_id":"12495","has_accepted_license":"1","publication":"Transactions on Machine Learning Research","author":[{"id":"f9a17499-f6e0-11ea-865d-fdf9a3f77117","full_name":"Iofinova, Eugenia B","last_name":"Iofinova","first_name":"Eugenia B","orcid":"0000-0002-7778-3221"},{"last_name":"Konstantinov","first_name":"Nikola H","id":"4B9D76E4-F248-11E8-B48F-1D18A9856A87","full_name":"Konstantinov, Nikola H"},{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Lampert, Christoph","first_name":"Christoph","last_name":"Lampert","orcid":"0000-0001-8622-7887"}],"external_id":{"arxiv":["2106.11732"]},"publication_identifier":{"issn":["2835-8856"]},"acknowledgement":"The authors would like to thank Bernd Prach, Elias Frantar, Alexandra Peste, Mahdi Nikdan, and Peter Súkeník for their helpful feedback. This research was supported by the Scientific Service Units (SSU) of IST Austria through resources provided by Scientific Computing (SciComp). This publication was made possible by an ETH AI Center postdoctoral fellowship granted to Nikola Konstantinov. Eugenia Iofinova was supported in part by the FWF DK VGSCO, grant agreement number W1260-N35. ","file_date_updated":"2023-02-23T10:30:04Z","ddc":["000"],"project":[{"name":"Vienna Graduate School on Computational Optimization","_id":"9B9290DE-BA93-11EA-9121-9846C619BF3A","grant_number":" W1260-N35"}],"year":"2022","acknowledged_ssus":[{"_id":"ScienComp"}]}