{"type":"ScholarlyArticle","title":"SoFaiR: Single Shot Fair Representation Learning","authors":[{"name":"Xavier Gitiaux","slug":"xavier-gitiaux","given":"Xavier","family":"Gitiaux","affiliation":"University"},{"name":"Huzefa Rangwala","slug":"huzefa-rangwala","given":"Huzefa","family":"Rangwala","affiliation":"University"}],"abstract":"To avoid discriminatory uses of their data, organizations can learn to map them into a representation that filters out information related to sensitive  attributes. However, all existing methods in fair representation learning generate a fairness-information trade-off. To achieve different points on the fairness-information plane, one must train different models. In this paper, we first demonstrate that fairness-information trade-offs are fully characterized by rate-distortion trade-offs.  Then, we use this key result and propose SoFaiR, a single shot fair representation learning method that generates with one trained model many points on the fairness-information plane. Besides its computational saving, our single-shot approach is, to the extent of our knowledge, the first fair representation learning method that explains what information is affected by changes in the fairness / distortion properties of the representation. Empirically, we find on three datasets that SoFaiR achieves similar fairness information trade-offs as its multi-shot counterparts.","doi":"10.24963/ijcai.2022/97","url":"https://ijcai.org/proceedings/2022/97","pdf":"https://ijcai.org/proceedings/2022/0097.pdf","markdown":"https://ijcai.org/proceedings/2022/97.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/97","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"AI Ethics, Trust, Fairness","track":"Main Track","number":97,"pages":{"first":687,"last":695},"keywords":["Machine Learning: Representation learning","AI Ethics, Trust, Fairness: Fairness & Diversity","Computer Vision: Bias, Fairness & Privacy","Machine Learning: Autoencoders"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38985194","length_sec":845,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38987051","length_sec":846,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Buolamwini and Gebru, 2018] Joy Buolamwini and Timnit Gebru. Gender shades: Intersectional accuracy dispari- ties in commercial gender classification. In Sorelle A. Friedler and Christo Wilson, editors, Proceedings of the 1st Conference on Fairness, Accountability and Trans- parency, volume 81 of Proceedings of Machine Learning Research, pages 77-91, New York, NY, USA, 23-24 Feb 2018. PMLR.","title":"Joy Buolamwini and Timnit Gebru. Gender shades: Intersectional accuracy disparities in commercial gender classification","authors":"Gebru Buolamwini","year":"2018","venue":"Proceedings of the 1st Conference on Fairness, Accountability and Transparency","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Choi et al., 2019] Yoojin Choi, Mostafa El-Khamy, and Jungwon Lee. Variable rate deep image compression with a conditional autoencoder. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 3146-3154, 2019.","title":"Variable rate deep image compression with a conditional autoencoder","authors":"Yoojin Choi, Mostafa El-Khamy, Jungwon Lee","year":"2019","venue":"Proceedings of the IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chouldechova and Roth, 2018] Alexandra Chouldechova and Aaron Roth. The frontiers of fairness in machine learning. arXiv preprint arXiv:1810.08810, 2018.","title":"The frontiers of fairness in machine learning","authors":"Roth Chouldechova","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cover and Thomas, 2012] Thomas M Cover and Joy A Thomas. Elements of information theory. John Wiley & Sons, 2012.","title":"Elements of information theory","authors":"M Thomas, Joy A Cover, Thomas","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Creager et al., 2019] Elliot Creager, David Madras, Jörn- Henrik Jacobsen, Marissa A Weis, Kevin Swersky, To- niann Pitassi, and Richard Zemel. Flexibly fair repre- sentation learning by disentanglement. arXiv preprint arXiv:1906.02589, 2019.","title":"Flexibly fair representation learning by disentanglement","authors":"Elliot Creager, David Madras, Jörn-Henrik Jacobsen, Marissa A Weis, Kevin Swersky, Toniann Pitassi, Richard Zemel","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cui et al., 2020] Ze Cui, Jing Wang, Bo Bai, Tiansheng Guo, and Yihui Feng. G-vae: A continuously variable rate deep image compression framework. arXiv preprint arXiv:2003.02012, 2020.","title":"G-vae: A continuously variable rate deep image compression framework","authors":"Ze Cui, Jing Wang, Bo Bai, Tiansheng Guo, Yihui Feng","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Edwards and Storkey, 2016] Harrison Edwards and Amos J. Storkey. Censoring representations with an adversary. In Yoshua Bengio and Yann LeCun, editors, 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Pro- ceedings, 2016.","title":"Censoring representations with an adversary","authors":"Harrison Edwards, Amos J Storkey","year":"2016","venue":"4th International Conference on Learning Representations, ICLR 2016","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Gardner et al., 2019] Josh Gardner, Christopher Brooks, and Ryan Baker. Evaluating the fairness of predictive stu- dent models through slicing analysis. In Proceedings of the 9th International Conference on Learning Analytics & Knowledge, pages 225-234. ACM, 2019.","title":"Evaluating the fairness of predictive student models through slicing analysis","authors":"Josh Gardner, Christopher Brooks, Ryan Baker","year":"2019","venue":"Proceedings of the 9th International Conference on Learning Analytics & Knowledge","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Gitiaux and Rangwala, 2021a] Xavier Gitiaux and Huzefa Rangwala. Fair representations by compression. In Pro- ceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 11506-11515, 2021.","title":"Fair representations by compression","authors":"Rangwala Gitiaux","year":"2021","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Gitiaux and Rangwala, 2021b] Xavier Gitiaux and Huzefa Rangwala. Learning smooth and fair representations. In International Conference on Artificial Intelligence and Statistics, pages 253-261. PMLR, 2021.","title":"Learning smooth and fair representations","authors":"Rangwala Gitiaux","year":"2021","venue":"International Conference on Artificial Intelligence and Statistics","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Gupta et al., 2021] Umang Gupta, Aaron Ferber, Bistra Dilkina, and Greg Ver Steeg. Controllable guarantees for fair outcomes via contrastive information estimation. In Proceedings of the AAAI Conference on Artificial Intelli- gence, volume 35, pages 7610-7619, 2021.","title":"Controllable guarantees for fair outcomes via contrastive information estimation","authors":"Umang Gupta, Aaron Ferber, Bistra Dilkina, Greg Ver, Steeg","year":"2021","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Higgins et al., 2016] Irina Higgins, Loic Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick, Shakir Mohamed, and Alexander Lerchner. beta-vae: Learning basic visual concepts with a constrained varia- tional framework. 2016.","title":"beta-vae: Learning basic visual concepts with a constrained variational framework","authors":"Irina Higgins, Loic Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick, Shakir Mohamed, Alexander Lerchner","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Jaiswal et al., 2020] Ayush Jaiswal, Daniel Moyer, Greg Ver Steeg, Wael AbdAlmageed, and Premkumar Natara- jan. Invariant representations through adversarial forget- ting. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 4272-4279, 2020.","title":"Invariant representations through adversarial forgetting","authors":"Ayush Jaiswal, Daniel Moyer, Greg Ver Steeg, Wael Abdalmageed, Premkumar Natarajan","year":"2020","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kostina and Tuncel, 2019] Victoria Kostina and Ertem Tun- cel. Successive refinement of abstract sources. IEEE Transactions on Information Theory, 65(10):6385-6398, 2019.","title":"Victoria Kostina and Ertem Tuncel. Successive refinement of abstract sources","authors":"Tuncel Kostina","year":"2019","venue":"IEEE Transactions on Information Theory","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Madras et al., 2018] David Madras, Elliot Creager, Toniann Pitassi, and Richard Zemel. Learning adversarially fair and transferable representations. In International Con- ference on Machine Learning, pages 3384-3393. PMLR, 2018.","title":"Learning adversarially fair and transferable representations","authors":"David Madras, Elliot Creager, Toniann Pitassi, Richard Zemel","year":"2018","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Moyer et al., 2018] Daniel Moyer, Shuyang Gao, Rob Brekelmans, Aram Galstyan, and Greg Ver Steeg. Invari- ant representations without adversarial training. In Ad- vances in Neural Information Processing Systems, pages 9084-9093, 2018.","title":"Invariant representations without adversarial training","authors":"Daniel Moyer, Shuyang Gao, Rob Brekelmans, Aram Galstyan, Greg Ver, Steeg","year":"2018","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Pfohl et al., 2019] Stephen Pfohl, Ben Marafino, Adrien Coulet, Fatima Rodriguez, Latha Palaniappan, and Nigam H Shah. Creating fair models of atherosclerotic cardiovascular disease risk. In Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, pages 271-278. ACM, 2019.","title":"Creating fair models of atherosclerotic cardiovascular disease risk","authors":"Stephen Pfohl, Ben Marafino, Adrien Coulet, Fatima Rodriguez, Latha Palaniappan, H Nigam, Shah","year":"2019","venue":"Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[ProPublica, 2016] ProPublica. How we analyzed the com- pas recidivism algorithm. ProPublica, 2016.","title":"ProPublica. How we analyzed the compas recidivism algorithm","authors":"Propublica","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Roy and Boddeti, 2019] Proteek Chandan Roy and Vishnu Naresh Boddeti. Mitigating information leakage in image representations: A maximum entropy approach. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2586-2594, 2019.","title":"Proteek Chandan Roy and Vishnu Naresh Boddeti. Mitigating information leakage in image representations: A maximum entropy approach","authors":"Boddeti Roy","year":"2019","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Salimans et al., 2017] Tim Salimans, Andrej Karpathy, Xi Chen, and Diederik P Kingma. Pixelcnn++: Improving the pixelcnn with discretized logistic mixture likelihood and other modifications. arXiv preprint arXiv:1701.05517, 2017.","title":"Pixelcnn++: Improving the pixelcnn with discretized logistic mixture likelihood and other modifications","authors":"Tim Salimans, Andrej Karpathy, Xi Chen, Diederik P Kingma","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Theis et al., 2017] Lucas Theis, Wenzhe Shi, Andrew Cun- ningham, and Ferenc Huszár. Lossy image compres- sion with compressive autoencoders. arXiv preprint arXiv:1703.00395, 2017.","title":"Lossy image compression with compressive autoencoders","authors":"Lucas Theis, Wenzhe Shi, Andrew Cunningham, Ferenc Huszár","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Tishby, 1999] N Tishby. The information bottleneck method. In Proc. 37th Annual Allerton Conference on Communications, Control and Computing, 1999, pages 368-377, 1999.","title":"The information bottleneck method","authors":"Tishby","year":"1999","venue":"Proc. 37th Annual Allerton Conference on Communications, Control and Computing","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Zemel et al., 2013] Rich Zemel, Yu Wu, Kevin Swersky, Toni Pitassi, and Cynthia Dwork. Learning fair representa- tions. In International Conference on Machine Learning, pages 325-333, 2013.","title":"Learning fair representations","authors":"Rich Zemel, Yu Wu, Kevin Swersky, Toni Pitassi, Cynthia Dwork","year":"2013","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}