{"type":"ScholarlyArticle","title":"Fairness-Aware Neural Rényi Minimization for Continuous Features","authors":[{"name":"Vincent Grari","slug":"vincent-grari","given":"Vincent","family":"Grari","affiliation":"Sorbonne Université , LIP6/CNRS , Paris , France; AXA , REV Research , Paris , France"},{"name":"Sylvain Lamprier","slug":"sylvain-lamprier","given":"Sylvain","family":"Lamprier","affiliation":"Sorbonne Université , LIP6/CNRS , Paris , France"},{"name":"Marcin Detyniecki","slug":"marcin-detyniecki","given":"Marcin","family":"Detyniecki","affiliation":"AXA , REV Research , Paris , France; Polish Academy of Science , IBS PAN , Warsaw , Poland"}],"abstract":"The past few years have seen a dramatic rise of academic and societal interest in fair machine learning. While plenty of fair algorithms have been proposed recently to tackle this challenge for discrete variables, only a few ideas exist for continuous ones. The objective in this paper is to ensure some independence level between the outputs of regression models and any given continuous sensitive variables. For this purpose, we use the Hirschfeld-Gebelein-Rényi (HGR) maximal correlation coefficient as a fairness metric. We propose to minimize the HGR coefficient directly with an adversarial neural network architecture. The idea is to predict the output Y while minimizing the ability of an adversarial neural network to find the estimated transformations which are required to predict the HGR coefficient. We empirically assess and compare our approach and demonstrate significant improvements on previously presented work in the field.","doi":"10.24963/ijcai.2020/313","url":"https://ijcai.org/proceedings/2020/313","pdf":"https://ijcai.org/proceedings/2020/0313.pdf","markdown":"https://ijcai.org/proceedings/2020/313.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/313","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Machine Learning","track":"Main track","number":313,"pages":{"first":2262,"last":2268},"keywords":["Trust, Fairness, Bias: General","Machine Learning: Deep Learning","Machine Learning: Adversarial Machine Learning"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/25055/file_25055.m3u8","length_sec":294,"provider":"hls"}],"references":[{"position":1,"raw":"[Agarwal et al., 2018] Alekh Agarwal, Alina Beygelzimer, Miroslav Dudik, John Langford, and Hanna Wallach. A re- ductions approach to fair classification. In ICML'18, pages 60-69, 2018.","title":"A reductions approach to fair classification","authors":"Alekh Agarwal, Alina Beygelzimer, Miroslav Dudik, John Langford, Hanna Wallach","year":"2018","venue":"ICML'18","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Angwin et al., 2016] Julia Angwin, Jeff Larson, Surya Mattu, and Lauren Kirchner. Machine bias. ProPublica, May 23, 2016.","title":"Machine bias","authors":"Julia Angwin, Jeff Larson, Surya Mattu, Lauren Kirchner","year":"2016","venue":"ProPublica","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Baharlouei et al., 2019] Sina Baharlouei, Maher Nouiehed, and Meisam Razaviyayn. Rényi fair inference. CoRR, abs/1906.12005, 2019.","title":"Sina Baharlouei, Maher Nouiehed, and Meisam Razaviyayn. Rényi fair inference","authors":"Baharlouei","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Belghazi et al., 2018] Mohamed Ishmael Belghazi, Aristide Baratin, Sai Rajeswar, Sherjil Ozair, Yoshua Bengio, Aaron Courville, and R Devon Hjelm. Mine: Mutual in- formation neural estimation, 2018.","title":"Mine: Mutual information neural estimation","authors":"Mohamed Ishmael Belghazi, Aristide Baratin, Sai Rajeswar, Sherjil Ozair, Yoshua Bengio, Aaron Courville, Devon Hjelm","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bellamy et al., 2018] Rachel K. E. Bellamy, Kuntal Dey, Michael Hind, et al. AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Un- wanted Algorithmic Bias. 2018.","title":"AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias","authors":"K E Rachel, Kuntal Bellamy, Michael Dey, Hind","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Bolukbasi et al., 2016] Tolga Bolukbasi, Kai-Wei Chang, James Zou, Venkatesh Saligrama, and Adam Kalai. Man is to computer programmer as woman is to homemaker? debiasing word embeddings. In NIPS, 2016, pages 4349- 4357, 2016.","title":"Man is to computer programmer as woman is to homemaker? debiasing word embeddings","authors":"Tolga Bolukbasi, Kai-Wei Chang, James Zou, Venkatesh Saligrama, Adam Kalai","year":"2016","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Chen et al., 2019] Jiahao Chen, Nathan Kallus, Xiaojie Mao, Geoffry Svacha, and Madeleine Udell. Fairness un- der unawareness: Assessing disparity when protected class is unobserved. In FAT* 2019, 2019, pages 339-348. ACM, 2019.","title":"Fairness under unawareness: Assessing disparity when protected class is unobserved","authors":"Jiahao Chen, Nathan Kallus, Xiaojie Mao, Geoffry Svacha, Madeleine Udell","year":"2019","venue":"FAT* 2019","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Donini et al., 2017] M. Donini, S. Ben-David, M. Pontil, and J. Shawe-Taylor. An efficient method to impose fair- ness in linear models. In NIPS Workshop on Prioritising Online Content, 2017.","title":"An efficient method to impose fairness in linear models","authors":"M Donini, S Ben-David, M Pontil, J Shawe-Taylor","year":"2017","venue":"NIPS Workshop on Prioritising Online Content","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[du Pin Calmon et al., 2017] Flávio du Pin Calmon, Den- nis Wei, Karthikeyan Natesan Ramamurthy, and Kush R. Varshney. Optimized data pre-processing for discrimina- tion prevention. CoRR, abs/1704.03354, 2017.","title":"Optimized data pre-processing for discrimination prevention","authors":"Du Pin Calmon","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Dua and Graff, 2017] Dheeru Dua and Casey Graff. UCI machine learning repository. http://archive.ics.uci.edu/ml, 2017.","title":"Dheeru Dua and Casey Graff. UCI machine learning repository","authors":"Graff Dua","year":"2017","venue":null,"doi":null,"url":"http://archive.ics.uci.edu/ml,2017","internal_url":null},{"position":11,"raw":"[Goodfellow et al., 2014] Ian Goodfellow, Jean Pouget- Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Gen- erative adversarial nets. In NIPS'14, pages 2672-2680. 2014.","title":"Generative adversarial nets","authors":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio","year":"2014","venue":"NIPS'14","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Gretton et al., 2005] Arthur Gretton, Ralf Herbrich, Alexander Smola, Olivier Bousquet, and Bernhard Schölkopf. Kernel methods for measuring independence. J. Mach. Learn. Res., 6:2075-2129, December 2005.","title":"Kernel methods for measuring independence","authors":"Arthur Gretton, Ralf Herbrich, Alexander Smola, Olivier Bousquet, Bernhard Schölkopf","year":"2005","venue":"J. Mach. Learn. Res","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Hardoon and Shawe-Taylor, 2009] David R Hardoon and John Shawe-Taylor. Convergence analysis of kernel canonical correlation analysis: theory and practice. Ma- chine learning, 74(1):23-38, 2009.","title":"Convergence analysis of kernel canonical correlation analysis: theory and practice","authors":"John David R Hardoon, Shawe-Taylor","year":"2009","venue":"Machine learning","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Hardt et al., 2016] Moritz Hardt, Eric Price, and Nati Sre- bro. Equality of opportunity in supervised learning. In NIPS'16, pages 3315-3323, 2016.","title":"Equality of opportunity in supervised learning","authors":"Hardt","year":"2016","venue":"NIPS'16","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kamiran and Calders, 2012] Faisal Kamiran and Toon Calders. Data preprocessing techniques for classification without discrimination. Knowledge and Information Systems, 33(1):1-33, Oct 2012.","title":"Faisal Kamiran and Toon Calders. Data preprocessing techniques for classification without discrimination","authors":"Calders Kamiran","year":"2012","venue":"Knowledge and Information Systems","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Kamishima et al., 2011] Toshihiro Kamishima, Shotaro Akaho, and Jun Sakuma. Fairness-aware learning through regularization approach. In ICDM'11 Workshops, pages 643-650. IEEE, 2011.","title":"Fairness-aware learning through regularization approach","authors":"Toshihiro Kamishima, Shotaro Akaho, Jun Sakuma","year":"2011","venue":"ICDM'11 Workshops","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Lambrecht and E. Tucker, 2016] Anja Lambrecht and Catherine E. Tucker. Algorithmic Bias? An Empirical Study into Apparent Gender-Based Discrimination in the Display of STEM Career Ads. SSRN Electronic Journal, 2016.","title":"Algorithmic Bias? An Empirical Study into Apparent Gender-Based Discrimination in the Display of STEM Career Ads","authors":"E Lambrecht, Anja Tucker, Catherine E Lambrecht, Tucker","year":"2016","venue":"SSRN Electronic Journal","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[López-Paz et al., 2013] David López-Paz, Philipp Hennig, and Bernhard Schölkopf. The randomized dependence co- efficient. In NIPS 2013, pages 1-9, 2013.","title":"The randomized dependence coefficient","authors":"David López-Paz, Philipp Hennig, Bernhard Schölkopf","year":"2013","venue":"NIPS 2013","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Louppe et al., 2017] Gilles Louppe, Michael Kagan, and Kyle Cranmer. Learning to pivot with adversarial net- works. In NIPS 2017, pages 981-990, 2017.","title":"Learning to pivot with adversarial networks","authors":"Gilles Louppe, Michael Kagan, Kyle Cranmer","year":"2017","venue":"NIPS 2017","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Mary et al., 2019] Jeremie Mary, Clément Calauzènes, and Noureddine El Karoui. Fairness-aware learning for contin- uous attributes and treatments. In ICML'19, pages 4382- 4391, Long Beach, California, USA, 09-15 Jun 2019.","title":"Fairness-aware learning for continuous attributes and treatments","authors":"Jeremie Mary, Clément Calauzènes, Noureddine El Karoui","year":"2019","venue":"ICML'19","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Pedreschi et al., 2008] Dino Pedreschi, Salvatore Ruggieri, and Franco Turini. Discrimination-aware data mining. In KDD'08, page 560, 2008.","title":"Discrimination-aware data mining","authors":"Dino Pedreschi, Salvatore Ruggieri, Franco Turini","year":"2008","venue":"KDD'08","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Póczos et al., 2012] Barnabás Póczos, Zoubin Ghahramani, and Jeff Schneider. Copula-based kernel dependency mea- sures. In ICML'12, pages 1635-1642, 2012.","title":"Copula-based kernel dependency measures","authors":"Barnabás Póczos, Zoubin Ghahramani, Jeff Schneider","year":"2012","venue":"ICML'12","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Rényi, 1959] Alfréd Rényi. On measures of dependence. Acta mathematica hungarica, 10(3-4):441-451, 1959.","title":"Alfréd Rényi. On measures of dependence","authors":"Rényi","year":"1959","venue":"Acta mathematica hungarica","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Székely et al., 2009] Gábor J Székely, Maria L Rizzo, et al. Brownian distance covariance. The annals of applied statistics, 3(4):1236-1265, 2009.","title":"Brownian distance covariance","authors":"J Gábor, Maria L Székely, Rizzo","year":"2009","venue":"The annals of applied statistics","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Wadsworth et al., 2018] Christina Wadsworth, Francesca Vera, and Chris Piech. Achieving fairness through ad- versarial learning: an application to recidivism prediction. CoRR, abs/1807.00199, 2018.","title":"Achieving fairness through adversarial learning: an application to recidivism prediction","authors":"Christina Wadsworth, Francesca Vera, Chris Piech","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Witsenhausen, 1975] Hans S Witsenhausen. On sequences of pairs of dependent random variables. SIAM Journal on Applied Mathematics, 28(1):100-113, 1975.","title":"On sequences of pairs of dependent random variables","authors":"Hans S Witsenhausen","year":"1975","venue":"SIAM Journal on Applied Mathematics","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zafar et al., 2017] Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez Rogriguez, and Krishna P. Gummadi. Fair- ness Constraints: Mechanisms for Fair Classification. In AISTATS'17, pages 962-970, 2017.","title":"Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez Rogriguez, and Krishna P. Gummadi. Fairness Constraints: Mechanisms for Fair Classification","authors":"Zafar","year":"2017","venue":"AISTATS'17","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zemel et al., 2013] Rich Zemel, Yu Wu, Kevin Swersky, Toni Pitassi, and Cynthia Dwork. Learning fair represen- tations. In ICML'13, pages 325-333, 2013.","title":"Learning fair representations","authors":"Rich Zemel, Yu Wu, Kevin Swersky, Toni Pitassi, Cynthia Dwork","year":"2013","venue":"ICML'13","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zhang et al., 2018] Brian Hu Zhang, Blake Lemoine, and Margaret Mitchell. Mitigating unwanted biases with ad- versarial learning. In AIES '18, pages 335-340, 2018.","title":"Mitigating unwanted biases with adversarial learning","authors":"Brian Hu Zhang, Blake Lemoine, Margaret Mitchell","year":"2018","venue":"AIES '","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}