{"type":"ScholarlyArticle","title":"FNNC: Achieving Fairness through Neural Networks","authors":[{"name":"Manisha Padala","slug":"manisha-padala","given":"Manisha","family":"Padala","affiliation":"International Institute of Information and Technology , Hyderabad"},{"name":"Sujit Gujar","slug":"sujit-gujar","given":"Sujit","family":"Gujar","affiliation":"International Institute of Information and Technology , Hyderabad"}],"abstract":"In classification models, fairness can be ensured by solving a constrained optimization problem. We focus on fairness constraints like Disparate Impact, Demographic Parity, and Equalized Odds, which are non-decomposable and non-convex. Researchers define convex surrogates of the constraints and then apply convex optimization frameworks to obtain fair classifiers. Surrogates serve as an upper bound to the actual constraints, and convexifying fairness constraints is challenging.\r\n\r\nWe propose a neural network-based framework, \\emph{FNNC}, to achieve fairness while maintaining high accuracy in classification. The above fairness constraints are included in the loss using Lagrangian multipliers. We prove bounds on generalization errors for the constrained losses which asymptotically go to zero. The network is optimized using two-step mini-batch stochastic gradient descent. Our experiments show that FNNC performs as good as the state of the art, if not better.  The experimental evidence supplements our theoretical guarantees. In summary, we have an automated solution to achieve fairness in classification, which is easily extendable to many fairness constraints.","doi":"10.24963/ijcai.2020/315","url":"https://ijcai.org/proceedings/2020/315","pdf":"https://ijcai.org/proceedings/2020/0315.pdf","markdown":"https://ijcai.org/proceedings/2020/315.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/315","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":315,"pages":{"first":2277,"last":2283},"keywords":["Trust, Fairness, Bias: General","Machine Learning: Deep Learning","Machine Learning: Classification"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24762/file_24762.m3u8","length_sec":299,"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 Jennifer Dy and Andreas Krause, editors, Proceedings of the 35th Inter- national Conference on Machine Learning, volume 80 of Proceedings of Machine Learning Research, pages 60-69, Stockholmsmässan, Stockholm Sweden, 10-15 Jul 2018. PMLR. Barocas and Selbst, 2016] Solon Barocas and Andrew D Selbst. Big data's disparate impact. Cal. L. Rev., 104:671, 2016.","title":"Solon Barocas and Andrew D Selbst. Big data's disparate impact","authors":"Alekh Agarwal, Alina Beygelzimer, Miroslav Dudik, John Langford, Hanna Wallach","year":"2016","venue":"Proceedings of the 35th International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bechavod and Ligett, 2017] Yahav Bechavod and Katrina Ligett. Learning fair classifiers: A regularization-inspired approach. CoRR, abs/1707.00044, 2017.","title":"Yahav Bechavod and Katrina Ligett. Learning fair classifiers: A regularization-inspired approach","authors":"Ligett Bechavod","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Berk et al., 2018] Richard Berk, Hoda Heidari, Shahin Jab- bari, Michael Kearns, and Aaron Roth. Fairness in crim- inal justice risk assessments: The state of the art. Soci- ological Methods & Research, page 0049124118782533, 2018.","title":"Fairness in criminal justice risk assessments: The state of the art","authors":"Richard Berk, Hoda Heidari, Shahin Jabbari, Michael Kearns, Aaron Roth","year":"2018","venue":"Sociological Methods & Research","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Beutel et al., 2017] Alex Beutel, Jilin Chen, Zhe Zhao, and Ed Huai hsin Chi. Data decisions and theoretical impli- cations when adversarially learning fair representations. CoRR, abs/1707.00075, 2017.","title":"Data decisions and theoretical implications when adversarially learning fair representations","authors":"Alex Beutel, Jilin Chen, Zhe Zhao, Ed Huai Hsin, Chi","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bilal Zafar et al., 2015] M. Bilal Zafar, I. Valera, M. Gomez Rodriguez, and K. P. Gummadi. Fairness Constraints: Mechanisms for Fair Classification. ArXiv e-prints, July 2015.","title":"Fairness Constraints: Mechanisms for Fair Classification","authors":"M Zafar, I Valera, M Gomez Rodriguez, K P Gummadi","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Calders and Verwer, 2010] Toon Calders and Sicco Ver- wer. Three naive bayes approaches for discrimination-free classification. Data Mining and Knowledge Discovery, 21:277-292, 2010.","title":"Toon Calders and Sicco Verwer. Three naive bayes approaches for discrimination-free classification","authors":"Verwer Calders","year":"2010","venue":"Data Mining and Knowledge Discovery","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Chouldechova, 2017] Alexandra Chouldechova. Fair pre- diction with disparate impact: A study of bias in recidi- vism prediction instruments. Big data, 5 2:153-163, 2017.","title":"Alexandra Chouldechova. Fair prediction with disparate impact: A study of bias in recidivism prediction instruments","authors":"Chouldechova","year":"2017","venue":"Big data","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Dütting et al., 2017] Paul Dütting, Zhe Feng, Harikrishna Narasimhan, David C Parkes, and Sai Srivatsa Ravin- dranath. Optimal auctions through deep learning. arXiv preprint arXiv:1706.03459, 2017.","title":"Optimal auctions through deep learning","authors":"Paul Dütting, Zhe Feng, Harikrishna Narasimhan, David C Parkes, Sai Srivatsa Ravindranath","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Dwork et al., 2012] Cynthia Dwork, Moritz Hardt, Toniann Pitassi, Omer Reingold, and Richard Zemel. Fairness through awareness. In Proceedings of the 3rd Innovations in Theoretical Computer Science Conference, ITCS '12, pages 214-226, New York, NY, USA, 2012. ACM.","title":"Fairness through awareness","authors":"Cynthia Dwork, Moritz Hardt, Toniann Pitassi, Omer Reingold, Richard Zemel","year":"2012","venue":"Proceedings of the 3rd Innovations in Theoretical Computer Science Conference, ITCS '12","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Eban et al., 2016] Elad ET Eban, Mariano Schain, Alan Mackey, Ariel Gordon, Rif A Saurous, and Gal Elidan. Scalable learning of non-decomposable objectives. arXiv preprint arXiv:1608.04802, 2016.","title":"Scalable learning of non-decomposable objectives","authors":"Mariano Elad Et Eban, Alan Schain, Ariel Mackey, Rif A Gordon, Gal Saurous, Elidan","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Edwards and Storkey, 2016] Harrison Edwards and Amos Storkey. Censoring representations with an adversary. In International Conference in Learning Representations (ICLR2016), 2 2016.","title":"Censoring representations with an adversary","authors":"Storkey Edwards, Harrison Edwards, Amos Storkey","year":"2016","venue":"International Conference in Learning Representations","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Feldman et al., 2015] Michael Feldman, Sorelle A. Friedler, John Moeller, Carlos Scheidegger, and Suresh Venkatasubramanian. Certifying and removing disparate impact. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '15, pages 259-268, New York, NY, USA, 2015. ACM.","title":"Certifying and removing disparate impact","authors":"Michael Feldman, Sorelle A Friedler, John Moeller, Carlos Scheidegger, Suresh Venkatasubramanian","year":"2015","venue":"Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '15","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Hardt et al., 2016] Moritz Hardt, Eric Price, and Nathan Srebro. Equality of opportunity in supervised learning. In NIPS, 2016.","title":"Equality of opportunity in supervised learning","authors":"Moritz Hardt, Eric Price, Nathan Srebro","year":"2016","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kamiran and Calders, 2009] F. Kamiran and T. Calders. Classifying without discriminating. In 2009 2nd Interna- tional Conference on Computer, Control and Communica- tion, pages 1-6, Feb 2009.","title":"Classifying without discriminating","authors":"F Kamiran, T Calders","year":"2009","venue":"2009 2nd International Conference on Computer, Control and Communication","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kamishima et al., 2011] T. Kamishima, S. Akaho, and J. Sakuma. Fairness-aware learning through regularization approach. In 2011 IEEE 11th International Conference on Data Mining Workshops, pages 643-650, Dec 2011.","title":"Fairness-aware learning through regularization approach","authors":"T Kamishima, S Akaho, J Sakuma","year":"2011","venue":"IEEE 11th International Conference on Data Mining Workshops","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Louizos et al., 2015] Christos Louizos, Kevin Swersky, Yu- jia Li, Max Welling, and Richard S. Zemel. The variational fair autoencoder. CoRR, abs/1511.00830, 2015.","title":"The variational fair autoencoder","authors":"Christos Louizos, Kevin Swersky, Yujia Li, Max Welling, Richard S Zemel","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Madras et al., 2018] David Madras, Elliot Creager, Toniann Pitassi, and Richard S. Zemel. Learning adversarially fair and transferable representations. In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, July 10-15, 2018, pages 3381-3390, 2018.","title":"Learning adversarially fair and transferable representations","authors":"David Madras, Elliot Creager, Toniann Pitassi, Richard S Zemel","year":"2018","venue":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Manisha and Gujar, 2018] P. Manisha and Sujit Gujar. A neural network framework for fair classifier. CoRR, abs/1811.00247, 2018.","title":"A neural network framework for fair classifier","authors":"P Manisha, Sujit Gujar","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Narasimhan, 2018] Harikrishna Narasimhan. Learning with complex loss functions and constraints. In International Conference on Artificial Intelligence and Statistics, AIS- TATS 2018, 9-11 April 2018, Playa Blanca, Lanzarote, Canary Islands, Spain, pages 1646-1654, 2018.","title":"Learning with complex loss functions and constraints","authors":"Harikrishna Narasimhan","year":"2018","venue":"International Conference on Artificial Intelligence and Statistics, AIS-TATS 2018","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Pleiss et al., 2017] Geoff Pleiss, Manish Raghavan, Felix Wu, Jon Kleinberg, and Kilian Q Weinberger. On fairness and calibration. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Sys- tems 30, pages 5680-5689.","title":"On fairness and calibration","authors":"Geoff Pleiss, Manish Raghavan, Felix Wu, Jon Kleinberg, Kilian Q Weinberger","year":null,"venue":"Advances in Neural Information Processing Systems 30","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"Curran Associates, Inc., 2017.","title":null,"authors":"Curran Associates, Inc","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Shalev-Shwartz and Ben-David, 2014] Shai Shalev- Shwartz and Shai Ben-David. Rademacher Complexities, page 325-336. Cambridge University Press, 2014.","title":"Rademacher Complexities","authors":"Shai Shalev, -Shwartz, Shai Ben-David","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wu et al., 2018] Yongkai Wu, Lu Zhang, and Xintao Wu. Fairness-aware classification: Criterion, convexity, and bounds. CoRR, abs/1809.04737, 2018.","title":"Fairness-aware classification: Criterion, convexity, and bounds","authors":"Yongkai Wu, Lu Zhang, Xintao Wu","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Zemel et al., 2013] Rich Zemel, Yu Wu, Kevin Swersky, Toni Pitassi, and Cynthia Dwork. Learning fair repre- sentations. In Sanjoy Dasgupta and David McAllester, editors, Proceedings of the 30th International Conference on Machine Learning, volume 28 of Proceedings of Ma- chine Learning Research, pages 325-333, Atlanta, Geor- gia, USA, 17-19 Jun 2013. PMLR.","title":"Learning fair representations","authors":"Rich Zemel, Yu Wu, Kevin Swersky, Toni Pitassi, Cynthia Dwork","year":"2013","venue":"Proceedings of the 30th International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zhang et al., 2018] Brian Hu Zhang, Blake Lemoine, and Margaret Mitchell. Mitigating unwanted biases with ad- versarial learning. CoRR, abs/1801.07593, 2018.","title":"Mitigating unwanted biases with adversarial learning","authors":"Brian Hu Zhang, Blake Lemoine, Margaret Mitchell","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}