{"type":"ScholarlyArticle","title":"FEAMOE: Fair, Explainable and Adaptive Mixture of Experts","authors":[{"name":"Shubham Sharma","slug":"shubham-sharma","given":"Shubham","family":"Sharma","affiliation":"The University of Texas at Austin"},{"name":"Jette Henderson","slug":"jette-henderson","given":"Jette","family":"Henderson","affiliation":"TecnoTree"},{"name":"Joydeep Ghosh","slug":"joydeep-ghosh","given":"Joydeep","family":"Ghosh","affiliation":"The University of Texas at Austin"}],"abstract":"Three key properties that are desired of trustworthy machine learning models deployed in high-stakes environments are fairness, explainability, and an ability to account for various kinds of \"drift\". While drifts in model accuracy have been widely investigated, drifts in fairness metrics over time remain largely unexplored. In this paper, we propose FEAMOE, a novel \"mixture-of-experts\" inspired framework aimed at learning fairer, more interpretable models that can also rapidly adjust to drifts in both the accuracy and the fairness of a classifier. We illustrate our framework for three popular fairness measures and demonstrate how drift can be handled with respect to these fairness constraints. Experiments on multiple datasets show that our framework as applied to a mixture of linear experts is able to perform comparably to neural networks in terms of accuracy while producing fairer models. We then use the large-scale HMDA dataset and show that various models trained on HMDA demonstrate drift and FEAMOE can ably handle these drifts with respect to all the considered fairness measures and maintain model accuracy. We also prove that the proposed framework allows for producing fast Shapley value explanations, which makes computationally efficient feature attribution based explanations of model decisions readily available via FEAMOE.","doi":"10.24963/ijcai.2023/55","url":"https://ijcai.org/proceedings/2023/55","pdf":"https://ijcai.org/proceedings/2023/0055.pdf","markdown":"https://ijcai.org/proceedings/2023/55.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/55","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":55,"pages":{"first":492,"last":500},"keywords":["AI Ethics, Trust, Fairness: ETF: Ethical, legal and societal issues","AI Ethics, Trust, Fairness: ETF: Bias","AI Ethics, Trust, Fairness: ETF: Other"],"videos":[],"references":[{"position":1,"raw":"[Aas et al., 2019] Kjersti Aas, Martin Jullum, and Anders Løland. Explaining individual predictions when features are dependent: More accurate approximations to shapley values. arXiv preprint arXiv:1903.10464, 2019.","title":"Explaining individual predictions when features are dependent: More accurate approximations to shapley values","authors":"Kjersti Aas, Martin Jullum, Anders Løland","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Agarwal et al., 2018] Alekh Agarwal, Alina Beygelzimer, Miroslav Dudík, John Langford, and Hanna Wallach. A reductions approach to fair classification. In International Conference on Machine Learning, pages 60-69. PMLR, 2018.","title":"A reductions approach to fair classification","authors":"Alekh Agarwal, Alina Beygelzimer, Miroslav Dudík, John Langford, Hanna Wallach","year":"2018","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Barocas et al., 2019] Solon Barocas, Moritz Hardt, and Arvind Narayanan. Fairness and machine learning. http: //www.fairmlbook.org, 2019. Accessed: 2023-06-05.","title":"Fairness and machine learning","authors":"Solon Barocas, Moritz Hardt, Arvind Narayanan","year":"2019","venue":null,"doi":null,"url":"http://www.fairmlbook.org","internal_url":null},{"position":4,"raw":"[Bechavod et al., 2020] Yahav Bechavod, Christopher Jung, and Steven Z Wu. Metric-free individual fairness in on- line learning. Advances in neural information processing systems, 33:11214-11225, 2020.","title":"Metric-free individual fairness in online learning","authors":"Yahav Bechavod, Christopher Jung, Steven Z Wu","year":"2020","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bellamy et al., 2018] Rachel KE Bellamy, Kuntal Dey, Michael Hind, Samuel C Hoffman, Stephanie Houde, Kalapriya Kannan, Pranay Lohia, Jacquelyn Martino, Sameep Mehta, Aleksandra Mojsilovic, et al. Ai fairness 360: An extensible toolkit for detecting, understanding, and mitigating unwanted algorithmic bias. arXiv preprint arXiv:1810.01943, 2018.","title":"Ai fairness 360: An extensible toolkit for detecting, understanding, and mitigating unwanted algorithmic bias","authors":"Rachel Ke Bellamy, Kuntal Dey, Michael Hind, Stephanie Samuel C Hoffman, Kalapriya Houde, Pranay Kannan, Jacquelyn Lohia, Sameep Martino, Aleksandra Mehta, Mojsilovic","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Bhaskaruni et al., 2019] Dheeraj Bhaskaruni, Hui Hu, and Chao Lan. Improving prediction fairness via model en- semble. In 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI), pages 1810-1814. IEEE, 2019.","title":"Improving prediction fairness via model ensemble","authors":"Dheeraj Bhaskaruni, Hui Hu, Chao Lan","year":"2019","venue":"IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI)","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Bhatt et al., 2020] Umang Bhatt, Alice Xiang, Shubham Sharma, Adrian Weller, Ankur Taly, Yunhan Jia, Joydeep Ghosh, Ruchir Puri, José MF Moura, and Peter Eckersley. Explainable machine learning in deployment. In Proceed- ings of the 2020 Conference on Fairness, Accountability, and Transparency, pages 648-657, 2020.","title":"Explainable machine learning in deployment","authors":"Umang Bhatt, Alice Xiang, Shubham Sharma, Adrian Weller, Ankur Taly, Yunhan Jia, Joydeep Ghosh, Ruchir Puri, M F José, Peter Moura, Eckersley","year":"2020","venue":"Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Biswas and Mukherjee, 2020] Arpita Biswas and Suvam Mukherjee. Ensuring fairness under prior probability shifts. arXiv preprint arXiv:2005.03474, 2020.","title":"Ensuring fairness under prior probability shifts","authors":"Arpita Biswas, Suvam Mukherjee","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Bureau, 2020] Consumer Finance Protection Bureau. Hmda dataset. [Online]. Available from: https://www. consumerfinance.gov/data-research/hmda/historic-data, 2020. Accessed 2023-02-05.","title":"Consumer Finance Protection Bureau. Hmda dataset","authors":null,"year":"2020","venue":null,"doi":null,"url":"https://www.consumerfinance.gov/data-research/hmda/historic-data,2020","internal_url":null},{"position":10,"raw":"[Burkart and Huber, 2021] Nadia Burkart and Marco F Huber. A survey on the explainability of supervised machine learn- ing. Journal of Artificial Intelligence Research, 70:245-317, 2021.","title":"A survey on the explainability of supervised machine learning","authors":"Nadia Burkart, Marco F Huber","year":"2021","venue":"Journal of Artificial Intelligence Research","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Butterworth, 2018] Michael Butterworth. The ico and artifi- cial intelligence: The role of fairness in the gdpr framework. Computer Law & Security Review, 34(2):257-268, 2018.","title":"The ico and artificial intelligence: The role of fairness in the gdpr framework","authors":"Michael Butterworth","year":"2018","venue":"Computer Law & Security Review","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Calmon et al., 2017] Flavio Calmon, Dennis Wei, Bhanuki- ran Vinzamuri, Karthikeyan Natesan Ramamurthy, and Kush R Varshney. Optimized pre-processing for discrim- ination prevention. In Advances in Neural Information Processing Systems, pages 3992-4001, 2017.","title":"Optimized pre-processing for discrimination prevention","authors":"Flavio Calmon, Dennis Wei, Bhanukiran Vinzamuri, Karthikeyan Natesan Ramamurthy, Kush R Varshney","year":"2017","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Gama et al., 2014] João Gama, Indrė Žliobaitė, Albert Bifet, Mykola Pechenizkiy, and Abdelhamid Bouchachia. A sur- vey on concept drift adaptation. ACM computing surveys (CSUR), 46(4):1-37, 2014.","title":"Albert Bifet, Mykola Pechenizkiy, and Abdelhamid Bouchachia. A survey on concept drift adaptation","authors":"Gama","year":"2014","venue":"ACM computing surveys (CSUR)","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Grgić-Hlača et al., 2017] Nina Grgić-Hlača, Muhammad Bi- lal Zafar, Krishna P Gummadi, and Adrian Weller. On fairness, diversity and randomness in algorithmic decision making. arXiv preprint arXiv:1706.10208, 2017.","title":"On fairness, diversity and randomness in algorithmic decision making","authors":"Nina Grgić-Hlača, Muhammad Bilal Zafar, Krishna P Gummadi, Adrian Weller","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Hacker, 2018] Philipp Hacker. Teaching fairness to artificial intelligence: Existing and novel strategies against algorith- mic discrimination under eu law. Common Market Law Review, 55(4):1143-1185, 2018.","title":"Teaching fairness to artificial intelligence: Existing and novel strategies against algorithmic discrimination under eu law","authors":"Philipp Hacker, Hacker","year":"2018","venue":"Common Market Law Review","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Jacobs et al., 1991] Robert A Jacobs, Michael I Jordan, Steven J Nowlan, and Geoffrey E Hinton. Adaptive mix- tures of local experts. Neural computation, 3(1):79-87, 1991.","title":"Adaptive mixtures of local experts","authors":"Robert A Jacobs, Michael I Jordan, Steven J Nowlan, Geoffrey E Hinton","year":"1991","venue":"Neural computation","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Karimi et al., 2020] Amir-Hossein Karimi, Gilles Barthe, Bernhard Schölkopf, and Isabel Valera. A survey of al- gorithmic recourse: definitions, formulations, solutions, and prospects. arXiv preprint arXiv:2010.04050, 2020.","title":"A survey of algorithmic recourse: definitions, formulations, solutions, and prospects","authors":"Amir-Hossein, Gilles Karimi, Bernhard Barthe, Isabel Schölkopf, Valera","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Kohavi, 1996] Ron Kohavi. Scaling up the accuracy of naive- bayes classifiers: A decision-tree hybrid. In Kdd, vol- ume 96, pages 202-207. Citeseer, 1996.","title":"Scaling up the accuracy of naivebayes classifiers: A decision-tree hybrid","authors":"Ron Kohavi, Kohavi","year":"1996","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Lu et al., 2018] Jie Lu, Anjin Liu, Fan Dong, Feng Gu, Joao Gama, and Guangquan Zhang. Learning under concept drift: A review. IEEE Transactions on Knowledge and Data Engineering, 31(12):2346-2363, 2018.","title":"Learning under concept drift: A review","authors":"Jie Lu, Anjin Liu, Fan Dong, Feng Gu, Joao Gama, Guangquan Zhang","year":"2018","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Lundberg and Lee, 2017a] Scott Lundberg and Su-In Lee. A unified approach to interpreting model predictions. arXiv preprint arXiv:1705.07874, 2017.","title":"A unified approach to interpreting model predictions","authors":"Lee ; Lundberg, Scott Lundberg, Su-In Lee","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Lundberg and Lee, 2017b] Scott M Lundberg and Su-In Lee. A unified approach to interpreting model predictions. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fer- gus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems 30 (NeurIPS 2017), pages 4765-4774.","title":"A unified approach to interpreting model predictions","authors":"Lee ; Lundberg, M Scott, Su-In Lundberg, Lee","year":"2017","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"Curran Associates, Inc., 2017.","title":null,"authors":"Curran Associates, Inc","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Lundberg et al., 2018] Scott M Lundberg, Gabriel G Erion, and Su-In Lee. Consistent individualized feature attribution for tree ensembles. arXiv preprint arXiv:1802.03888, 2018.","title":"Consistent individualized feature attribution for tree ensembles","authors":"Scott M Lundberg, Su-In Gabriel G Erion, Lee","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Madras et al., 2017] David Madras, Toniann Pitassi, and Richard Zemel. Predict responsibly: improving fair- ness and accuracy by learning to defer. arXiv preprint arXiv:1711.06664, 2017.","title":"Predict responsibly: improving fairness and accuracy by learning to defer","authors":"David Madras, Toniann Pitassi, Richard Zemel","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Masoudnia and Ebrahimpour, 2014] Saeed Masoudnia and Reza Ebrahimpour. Mixture of experts: a literature survey. Artificial Intelligence Review, 42(2):275-293, 2014.","title":"Mixture of experts: a literature survey","authors":"Saeed Masoudnia, Reza Ebrahimpour","year":"2014","venue":"Artificial Intelligence Review","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Mehrabi et al., 2019] Ninareh Mehrabi, Fred Morstatter, Nripsuta Saxena, Kristina Lerman, and Aram Galstyan. A survey on bias and fairness in machine learning. arXiv preprint arXiv:1908.09635, 2019.","title":"A survey on bias and fairness in machine learning","authors":"Mehrabi","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Molnar, 2019] Christoph Molnar. Interpretable machine learning. https://christophm.github.io/ interpretable-ml-book/, 2019. Accessed: 2023-06- 05.","title":"Interpretable machine learning","authors":"Christoph Molnar, Molnar","year":"2019","venue":null,"doi":null,"url":"https://christophm.github.io/interpretable-ml-book/","internal_url":null},{"position":28,"raw":"Nejdl, ] Wolfgang Nejdl. Farf: A fair and adaptive random forests classifier. In Advances in Knowledge Discovery and Data Mining: 25th Pacific-Asia Conference, PAKDD 2021, Virtual Event, May 11-14, 2021, Proceedings, Part II, page 245. Springer Nature.","title":"Farf: A fair and adaptive random forests classifier","authors":"] Nejdl, Wolfgang Nejdl","year":"2021","venue":"Advances in Knowledge Discovery and Data Mining: 25th Pacific-Asia Conference, PAKDD 2021, Virtual Event","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Ntoutsi et al., 2020] Eirini Ntoutsi, Pavlos Fafalios, Ujwal Gadiraju, Vasileios Iosifidis, Wolfgang Nejdl, Maria-Esther Vidal, Salvatore Ruggieri, Franco Turini, Symeon Pa- padopoulos, Emmanouil Krasanakis, et al. Bias in data- driven artificial intelligence systems-an introductory sur- vey. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 10(3):e1356, 2020.","title":"Bias in datadriven artificial intelligence systems-an introductory survey","authors":"Eirini Ntoutsi, Pavlos Fafalios, Ujwal Gadiraju, Vasileios Iosifidis, Wolfgang Nejdl, Maria-Esther Vidal, Salvatore Ruggieri, Franco Turini, Symeon Papadopoulos, Emmanouil Krasanakis","year":"2020","venue":"Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[ProPublica, 2016] ProPublica. Compas dataset. [Online]. Available from: https://www.propublica.org/datastore/ dataset/compas-recidivism-risk-score-data-and-analysis, 2016. Accessed: 2023-02-05.","title":"ProPublica. Compas dataset","authors":"Propublica","year":"2016","venue":null,"doi":null,"url":"https://www.propublica.org/datastore/dataset/compas-recidivism-risk-score-data-and-analysis,2016","internal_url":null},{"position":31,"raw":"[Riquelme et al., 2021] Carlos Riquelme, Joan Puigcerver, Basil Mustafa, Maxim Neumann, Rodolphe Jenatton, An- dré Susano Pinto, Daniel Keysers, and Neil Houlsby. Scal- ing vision with sparse mixture of experts. arXiv preprint arXiv:2106.05974, 2021.","title":"Scaling vision with sparse mixture of experts","authors":"Carlos Riquelme, Joan Puigcerver, Basil Mustafa, Maxim Neumann, Rodolphe Jenatton, André Susano Pinto, Daniel Keysers, Neil Houlsby","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Robins, 1995] Anthony Robins. Catastrophic forgetting, re- hearsal and pseudorehearsal. Connection Science, 7(2):123- 146, 1995.","title":"Catastrophic forgetting, rehearsal and pseudorehearsal","authors":"Anthony Robins","year":"1995","venue":"Connection Science","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Shapley, 1953] Lloyd S Shapley. A value for n-person games. In Contributions to the Theory of Games II, pages 307-317. 1953.","title":"A value for n-person games","authors":"S Lloyd, Shapley","year":"1953","venue":"Contributions to the Theory of Games II","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Sharma et al., 2020a] Shubham Sharma, Alan H Gee, David Paydarfar, and Joydeep Ghosh. Fair-n: Fair and ro- bust neural networks for structured data. arXiv preprint arXiv:2010.06113, 2020.","title":"Fair-n: Fair and robust neural networks for structured data","authors":"Sharma","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Sharma et al., 2020b] Shubham Sharma, Yunfeng Zhang, Jesús M Ríos Aliaga, Djallel Bouneffouf, Vinod Muthusamy, and Kush R Varshney. Data augmentation for discrimination prevention and bias disambiguation. In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, pages 358-364, 2020.","title":"Data augmentation for discrimination prevention and bias disambiguation","authors":"Sharma","year":"2020","venue":"Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Slack et al., 2020] Dylan Slack, Sorelle A Friedler, and Emile Givental. Fairness warnings and fair-maml: learn- ing fairly with minimal data. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, pages 200-209, 2020.","title":"Fairness warnings and fair-maml: learning fairly with minimal data","authors":"Slack","year":"2020","venue":"Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Stanley, 2003] Kenneth O Stanley. Learning concept drift with a committee of decision trees. Informe técnico: UT-AI- TR-03-302, Department of Computer Sciences, University of Texas at Austin, USA, 2003.","title":"Learning concept drift with a committee of decision trees","authors":"O Kenneth, Stanley","year":"2003","venue":null,"doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Sundararajan et al., 2017] Mukund Sundararajan, Ankur Taly, and Qiqi Yan. Axiomatic attribution for deep net- works. In Proceedings of the 34th International Confer- ence on Machine Learning-Volume 70 (ICML 2017), pages 3319-3328. Journal of Machine Learning Research, 2017.","title":"Axiomatic attribution for deep networks","authors":"Mukund Sundararajan, Ankur Taly, Qiqi Yan","year":"2017","venue":"Proceedings of the 34th International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Yuksel et al., 2012] Seniha Esen Yuksel, Joseph N Wilson, and Paul D Gader. Twenty years of mixture of experts. IEEE transactions on neural networks and learning sys- tems, 23(8):1177-1193, 2012.","title":"Twenty years of mixture of experts","authors":"Yuksel","year":"2012","venue":"IEEE transactions on neural networks and learning systems","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Zhang and Ntoutsi, 2019] Wenbin Zhang and Eirini Ntoutsi. Faht: an adaptive fairness-aware decision tree classifier. arXiv preprint arXiv:1907.07237, 2019.","title":"Faht: an adaptive fairness-aware decision tree classifier","authors":"Ntoutsi Zhang, Wenbin Zhang, Eirini Ntoutsi","year":"2019","venue":null,"doi":null,"url":null,"internal_url":"/proceedings/2019/205"},{"position":41,"raw":"[Zhang et al., 2018] Brian Hu Zhang, Blake Lemoine, and Margaret Mitchell. Mitigating unwanted biases with ad- versarial learning. In Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society, pages 335-340. ACM, 2018.","title":"Mitigating unwanted biases with adversarial learning","authors":"Brian Hu Zhang, Blake Lemoine, Margaret Mitchell","year":"2018","venue":"Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Zhang et al., 2021] Wenbin Zhang, Albert Bifet, Xiangliang Zhang, Jeremy C Weiss, and Wolfgang Nejdl. Farf: A fair and adaptive random forests classifier. In Pacific-Asia Conference on Knowledge Discovery and Data Mining, pages 245-256. Springer, 2021.","title":"Farf: A fair and adaptive random forests classifier","authors":"Wenbin Zhang, Albert Bifet, Xiangliang Zhang, Jeremy C Weiss, Wolfgang Nejdl","year":"2021","venue":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}