{"type":"ScholarlyArticle","title":"SF-PATE: Scalable, Fair, and Private Aggregation of Teacher Ensembles","authors":[{"name":"Cuong Tran","slug":"cuong-tran","given":"Cuong","family":"Tran","affiliation":"Syracuse University"},{"name":"Keyu Zhu","slug":"keyu-zhu","given":"Keyu","family":"Zhu","affiliation":"Georgia Institute of Technology"},{"name":"Ferdinando Fioretto","slug":"ferdinando-fioretto","given":"Ferdinando","family":"Fioretto","affiliation":"University of Virginia"},{"name":"Pascal Van Hentenryck","slug":"pascal-van-hentenryck","given":"Pascal","family":"Van Hentenryck","affiliation":"Georgia Institute of Technology"}],"abstract":"A critical concern in data-driven processes is to build models whose outcomes do not discriminate against some protected groups. In learning tasks, knowledge of the group attributes is essential to ensure non-discrimination, but in practice, these attributes may not be available due to legal and ethical requirements. To address this challenge, this paper studies a model that protects the privacy of individuals’ sensitive information while also allowing it to learn non-discriminatory predictors.\r\nA key feature of the proposed model is to enable the use of off-the-shelves and non-private fair models to create a privacy-preserving and fair model. The paper analyzes the relation between accuracy, privacy, and fairness, and assesses the benefits of the proposed models on several prediction tasks. In particular, this proposal allows both scalable and accurate training of private and fair models for very large neural networks.","doi":"10.24963/ijcai.2023/56","url":"https://ijcai.org/proceedings/2023/56","pdf":"https://ijcai.org/proceedings/2023/0056.pdf","markdown":"https://ijcai.org/proceedings/2023/56.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/56","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"AI Ethics, Trust, Fairness","track":"Main Track","number":56,"pages":{"first":501,"last":509},"keywords":["AI Ethics, Trust, Fairness: ETF: Trustworthy AI","Machine Learning: ML: Multi-task and transfer learning","Data Mining: DM: Privacy-preserving data mining"],"videos":[],"references":[{"position":1,"raw":"[Abadi et al., 2016] Martin Abadi, Andy Chu, Ian Goodfel- low, H. Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang. Deep learning with differential privacy. In Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, 2016.","title":"Deep learning with differential privacy","authors":"Martin Abadi, Andy Chu, Ian Goodfellow, H Brendan Mcmahan, Ilya Mironov, Kunal Talwar, Li Zhang","year":"2016","venue":"Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Agarwal et al., 2018] Alekh Agarwal, Alina Beygelzimer, Miroslav Dudik, John Langford, and Hanna Wallach. A reductions approach to fair classification. In ICML, 2018.","title":"A reductions approach to fair classification","authors":"Alekh Agarwal, Alina Beygelzimer, Miroslav Dudik, John Langford, Hanna Wallach","year":"2018","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bagdasaryan et al., 2019] Eugene Bagdasaryan, Omid Poursaeed, and Vitaly Shmatikov. Differential privacy has disparate impact on model accuracy. In Proceedings of Advances in Neural Information Processing Systems (NIPS), 2019.","title":"Differential privacy has disparate impact on model accuracy","authors":"Eugene Bagdasaryan, Omid Poursaeed, Vitaly Shmatikov","year":"2019","venue":"Proceedings of Advances in Neural Information Processing Systems (NIPS)","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Blake, 1998] Catherine Blake. Uci repository of ma- chine learning databases. http://www.ics.uci.edu/ ∼ mlearn/ MLRepository.html, 1998. Accessed: 2023-01-30.","title":"Catherine Blake. Uci repository of machine learning databases","authors":"Blake","year":"1998","venue":null,"doi":null,"url":"http://www.ics.uci.edu/∼mlearn/MLRepository.html","internal_url":null},{"position":5,"raw":"[Bradbury et al., 2018] James Bradbury, Roy Frostig, Peter Hawkins, Matthew James Johnson, Chris Leary, Dougal Maclaurin, George Necula, Adam Paszke, Jake Vander- Plas, Skye Wanderman-Milne, and Qiao Zhang. JAX: composable transformations of Python+NumPy programs. http://github.com/google/jax, 2018. Accessed: 2023-01- 30.","title":"JAX: composable transformations of Python+NumPy programs","authors":"James Bradbury, Roy Frostig, Peter Hawkins, Matthew James Johnson, Chris Leary, Dougal Maclaurin, George Necula, Adam Paszke, Jake Vander-Plas, Skye Wanderman-Milne, Qiao Zhang","year":"2023","venue":null,"doi":null,"url":"http://github.com/google/jax,2018","internal_url":null},{"position":6,"raw":"[Chaudhuri et al., 2011] Kamalika Chaudhuri, Claire Mon- teleoni, and Anand D. Sarwate. Differentially private em- pirical risk minimization. Journal of Machine Learning Research, 2011.","title":"Differentially private empirical risk minimization","authors":"Kamalika Chaudhuri, Claire Monteleoni, Anand D Sarwate","year":"2011","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Du et al., 2021] Mengnan Du, Subhabrata Mukherjee, Guanchu Wang, Ruixiang Tang, Ahmed Awadallah, and Xia Hu. Fairness via representation neutralization. Advances in Neural Information Processing Systems, 34:12091-12103, 2021.","title":"Fairness via representation neutralization","authors":"Du","year":"2021","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Dwork et al., 2006] Cynthia Dwork, Frank McSherry, Kobbi Nissim, and Adam Smith. Calibrating noise to sensitivity in private data analysis. In Proceedings of Theory of Cryptography Conference, pages 265-284, 2006.","title":"Calibrating noise to sensitivity in private data analysis","authors":"Dwork","year":"2006","venue":"Proceedings of Theory of Cryptography Conference","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Ekstrand et al., 2018] Michael D Ekstrand, Rezvan Joshaghani, and Hoda Mehrpouyan. Privacy for all: Ensuring fair and equitable privacy protections. In ACM FAccT, pages 35-47, 2018.","title":"Privacy for all: Ensuring fair and equitable privacy protections","authors":"Rezvan Michael D Ekstrand, Hoda Joshaghani, Mehrpouyan","year":"2018","venue":"ACM FAccT","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Fioretto et al., 2020] Ferdinando Fioretto, Pascal Van Hen- tenryck, Terrence W. K. Mak, Cuong Tran, Federico Baldo, and Michele Lombardi. Lagrangian duality for constrained deep learning. In Machine Learning and Knowledge Discovery in Databases. European Confer- ence, ECML PKDD 2020, volume 12461 of Lecture Notes in Computer Science, pages 118-135, 2020.","title":"Lagrangian duality for constrained deep learning","authors":"Ferdinando Fioretto, Pascal Van Hentenryck, Terrence W K Mak, Cuong Tran, Federico Baldo, Michele Lombardi","year":"2020","venue":"Machine Learning and Knowledge Discovery in Databases. European Conference, ECML PKDD 2020","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Fioretto et al., 2022] Ferdinando Fioretto, Cuong Tran, Pas- cal Van Hentenryck, and Keyu Zhu. Differential privacy and fairness in decisions and learning tasks: A survey. In In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), pages 5470-5477, 2022.","title":"Differential privacy and fairness in decisions and learning tasks: A survey","authors":"Ferdinando Fioretto, Cuong Tran, Pascal Van Hentenryck, Keyu Zhu","year":"2022","venue":"Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI)","doi":null,"url":null,"internal_url":"/proceedings/2022/766"},{"position":12,"raw":"[Hwang et al., 2020] Sunhee Hwang, Sungho Park, Do- hyung Kim, Mirae Do, and Hyeran Byun. Fairfacegan: Fairness-aware facial image-to-image translation. In 31st British Machine Vision Conference 2020, BMVC 2020, 2020.","title":"Fairfacegan: Fairness-aware facial image-to-image translation","authors":"Sunhee Hwang, Sungho Park, Dohyung Kim, Mirae Do, Hyeran Byun","year":"2020","venue":"31st British Machine Vision Conference 2020","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Jagielski et al., 2019] Matthew Jagielski, Michael Kearns, Jieming Mao, Alina Oprea, Aaron Roth, Saeed Sharifi- Malvajerdi, and Jonathan Ullman. Differentially private fair learning. In ICML, pages 3000-3008, 2019.","title":"Differentially private fair learning","authors":"Matthew Jagielski, Michael Kearns, Jieming Mao, Alina Oprea, Aaron Roth, Saeed Sharifi-Malvajerdi, Jonathan Ullman","year":"2019","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kim et al., 2022] Dongha Kim, Kunwoong Kim, Insung Kong, Ilsang Ohn, and Yongdai Kim. Learning fair rep- resentation with a parametric integral probability metric. arXiv preprint arXiv:2202.02943, 2022.","title":"Learning fair representation with a parametric integral probability metric","authors":"Kim","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Mozannar et al., 2020] Hussein Mozannar, Mesrob Ohan- nessian, and Nathan Srebro. Fair learning with private de- mographic data. In ICML, pages 7066-7075, 2020.","title":"Hussein Mozannar, Mesrob Ohannessian, and Nathan Srebro. Fair learning with private demographic data","authors":"Mozannar","year":"2020","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Papernot et al., 2018] Nicolas Papernot, Shuang Song, Ilya Mironov, Ananth Raghunathan, Kunal Talwar, and Úlfar Erlingsson. Scalable private learning with pate. arXiv preprint arXiv:1802.08908, 2018.","title":"Scalable private learning with pate","authors":"Nicolas Papernot, Shuang Song, Ilya Mironov, Kunal Ananth Raghunathan, Úlfar Talwar, Erlingsson","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Pujol et al., 2020] David Pujol, Ryan McKenna, Satya Kup- pam, Michael Hay, Ashwin Machanavajjhala, and Gerome Miklau. Fair decision making using privacy-protected data. In ACM FAccT, pages 189-199, 2020.","title":"Fair decision making using privacy-protected data","authors":"David Pujol, Ryan Mckenna, Satya Kuppam, Michael Hay, Ashwin Machanavajjhala, Gerome Miklau","year":"2020","venue":"ACM FAccT","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Shui et al., 2022] Changjian Shui, Qi Chen, Jiaqi Li, Boyu Wang, and Christian Gagné. Fair representation learn- ing through implicit path alignment. In Proceedings of the 39th International Conference on Machine Learning, 2022.","title":"Fair representation learning through implicit path alignment","authors":"Changjian Shui, Qi Chen, Jiaqi Li, Boyu Wang, Christian Gagné","year":"2022","venue":"Proceedings of the 39th International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Subramani et al., 2021] Pranav Subramani, Nicholas Vadi- velu, and Gautam Kamath. Enabling fast differentially private sgd via just-in-time compilation and vectoriza- tion. Advances in Neural Information Processing Systems, 34:26409-26421, 2021.","title":"Enabling fast differentially private sgd via just-in-time compilation and vectorization","authors":"Pranav Subramani, Nicholas Vadivelu, Gautam Kamath","year":"2021","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Tran and Fioretto, 2023] Cuong Tran and Ferdinando Fioretto. A fairness analysis on private aggregation of teacher ensembles. In International Joint Conference on Artificial Intelligence (IJCAI), page TBD, 2023.","title":"A fairness analysis on private aggregation of teacher ensembles","authors":"Tran, Fioretto ;, Cuong Tran, Ferdinando Fioretto","year":"2023","venue":"International Joint Conference on Artificial Intelligence (IJCAI)","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Tran et al., 2021a] Cuong Tran, My Dinh, and Ferdinando Fioretto. Differentially private empirical risk minimization under the fairness lens. In Advances in Neural Information Processing Systems (NeurIPS), volume 34, pages 27555- 27565.","title":"Differentially private empirical risk minimization under the fairness lens","authors":"Tran","year":"2021","venue":"Advances in Neural Information Processing Systems (NeurIPS)","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"Curran Associates, Inc., 2021.","title":null,"authors":"Curran Associates, Inc","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Tran et al., 2021b] Cuong Tran, Ferdinando Fioretto, and Pascal Van Hentenryck. Differentially private and fair deep learning: A lagrangian dual approach. In Proceed- ings of the AAAI Conference on Artificial Intelligence, vol- ume 35, pages 9932-9939, 2021.","title":"Differentially private and fair deep learning: A lagrangian dual approach","authors":"Tran","year":"2021","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Tran et al., 2021c] Cuong Tran, Ferdinando Fioretto, Pascal Van Hentenryck, and Zhiyan Yao. Decision making with differential privacy under the fairness lens. In Interna- tional Joint Conference on Artificial Intelligence (IJCAI), pages 560-566, 2021.","title":"Decision making with differential privacy under the fairness lens","authors":"Tran","year":"2021","venue":"International Joint Conference on Artificial Intelligence (IJCAI)","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Tran et al., 2022] Cuong Tran, Keyu Zhu, Ferdinando Fioretto, and Pascal Van Hentenryck. SF-PATE: Scalable, Fair, and Private Aggregation of Teacher Ensembles. arXiv preprint arXiv:2204.05157, 2022.","title":"SF-PATE: Scalable, Fair, and Private Aggregation of Teacher Ensembles","authors":"Cuong Tran, Keyu Zhu, Ferdinando Fioretto, Pascal Van Hentenryck","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Uniyal et al., 2021] Archit Uniyal, Rakshit Naidu, Sasikanth Kotti, Sahib Singh, Patrik Joslin Kenfack, Fatemehsadat Mireshghallah, and Andrew Trask. Dp-sgd vs pate: Which has less disparate impact on model accuracy? arXiv, 2106.12576, 2021.","title":"Dp-sgd vs pate: Which has less disparate impact on model accuracy?","authors":"Archit Uniyal, Rakshit Naidu, Sasikanth Kotti, Sahib Singh, Patrik Joslin Kenfack, Fatemehsadat Mireshghallah, Andrew Trask","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Xu et al., 2019] Depeng Xu, Shuhan Yuan, and Xintao Wu. Achieving differential privacy and fairness in logistic re- gression. In Proceedings of the 26th International Confer- ence on World Wide Web (WWW), 2019.","title":"Achieving differential privacy and fairness in logistic regression","authors":"Xu","year":"2019","venue":"Proceedings of the 26th International Conference on World Wide Web (WWW)","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Yousefpour et al., 2021] Ashkan Yousefpour, Igor Shilov, Alexandre Sablayrolles, Davide Testuggine, Karthik Prasad, Mani Malek, John Nguyen, Sayan Ghosh, Akash Bharadwaj, Jessica Zhao, Graham Cormode, and Ilya Mironov. Opacus: User-friendly differential privacy li- brary in PyTorch. arXiv preprint arXiv:2109.12298, 2021.","title":"Opacus: User-friendly differential privacy library in PyTorch","authors":"Ashkan Yousefpour, Igor Shilov, Alexandre Sablayrolles, Davide Testuggine, Karthik Prasad, Mani Malek, John Nguyen, Sayan Ghosh, Akash Bharadwaj, Jessica Zhao, Graham Cormode, Ilya Mironov","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}