Putting Fairness Principles into Practice: Challenges, Metrics, and Improvements

As more researchers have become aware of and passionate about algorithmic fairness, there has been an explosion in papers laying out new metrics, suggesting algorithms to address issues, and calling attention to issues in existing applications of machine learning. This research has greatly expanded our understanding of the concerns and challenges in deploying machine learning, but there has been much less work in seeing how the rubber meets the road. In this paper we provide a case-study on the application of fairness in machine learning research to a production classification system, and offer new insights in how to measure and address algorithmic fairness issues. We discuss open questions in implementing equality of opportunity and describe our fairness metric, conditional equality, that takes into account distributional differences. Further, we provide a new approach to improve on the fairness metric during model training and demonstrate its efficacy in improving performance for a real-world product.

[1]  Alexandra Chouldechova,et al.  A case study of algorithm-assisted decision making in child maltreatment hotline screening decisions , 2018, FAT.

[2]  Katrina Ligett,et al.  Penalizing Unfairness in Binary Classification , 2017 .

[3]  Alexandra Chouldechova,et al.  Fair prediction with disparate impact: A study of bias in recidivism prediction instruments , 2016, Big Data.

[4]  François Laviolette,et al.  Domain-Adversarial Training of Neural Networks , 2015, J. Mach. Learn. Res..

[5]  Esther Rolf,et al.  Delayed Impact of Fair Machine Learning , 2018, ICML.

[6]  François Laviolette,et al.  Domain-Adversarial Neural Networks , 2014, ArXiv.

[7]  Cynthia Dwork,et al.  Fairness Under Composition , 2018, ITCS.

[8]  Toniann Pitassi,et al.  Fairness through awareness , 2011, ITCS '12.

[9]  Zhe Zhao,et al.  Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations , 2017, ArXiv.

[10]  Jun Sakuma,et al.  Fairness-aware Learning through Regularization Approach , 2011, 2011 IEEE 11th International Conference on Data Mining Workshops.

[11]  David Sontag,et al.  Why Is My Classifier Discriminatory? , 2018, NeurIPS.

[12]  Toniann Pitassi,et al.  Learning Fair Representations , 2013, ICML.

[13]  Ankur Taly,et al.  Counterfactual Fairness in Text Classification through Robustness , 2018, AIES.

[14]  Kristian Lum,et al.  Limitations of mitigating judicial bias with machine learning , 2017, Nature Human Behaviour.

[15]  Jon M. Kleinberg,et al.  On Fairness and Calibration , 2017, NIPS.

[16]  Alexandra Chouldechova,et al.  Does mitigating ML's impact disparity require treatment disparity? , 2017, NeurIPS.

[17]  Lucy Vasserman,et al.  Measuring and Mitigating Unintended Bias in Text Classification , 2018, AIES.

[18]  John Langford,et al.  A Reductions Approach to Fair Classification , 2018, ICML.

[19]  Max Welling,et al.  The Variational Fair Autoencoder , 2015, ICLR.

[20]  Miroslav Dudík,et al.  Improving Fairness in Machine Learning Systems: What Do Industry Practitioners Need? , 2018, CHI.

[21]  K. Lum,et al.  To predict and serve? , 2016 .

[22]  Avi Feller,et al.  Algorithmic Decision Making and the Cost of Fairness , 2017, KDD.

[23]  Toon Calders,et al.  Three naive Bayes approaches for discrimination-free classification , 2010, Data Mining and Knowledge Discovery.

[24]  John R. Anderson,et al.  Beyond Globally Optimal: Focused Learning for Improved Recommendations , 2017, WWW.

[25]  Blake Lemoine,et al.  Mitigating Unwanted Biases with Adversarial Learning , 2018, AIES.

[26]  Yaacov Ritov,et al.  On conditional parity as a notion of non-discrimination in machine learning , 2017, ArXiv.

[27]  Amos J. Storkey,et al.  Censoring Representations with an Adversary , 2015, ICLR.

[28]  Maya R. Gupta,et al.  Satisfying Real-world Goals with Dataset Constraints , 2016, NIPS.

[29]  Alexandra Chouldechova,et al.  Does mitigating ML's disparate impact require disparate treatment? , 2017, ArXiv.

[30]  Bernhard Schölkopf,et al.  Avoiding Discrimination through Causal Reasoning , 2017, NIPS.

[31]  Toniann Pitassi,et al.  Learning Adversarially Fair and Transferable Representations , 2018, ICML.

[32]  Guy N. Rothblum,et al.  Calibration for the (Computationally-Identifiable) Masses , 2017, ArXiv.

[33]  George Trigeorgis,et al.  Domain Separation Networks , 2016, NIPS.

[34]  Nathan Srebro,et al.  Equality of Opportunity in Supervised Learning , 2016, NIPS.

[35]  Seth Neel,et al.  Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness , 2017, ICML.

[36]  T. Therneau,et al.  Assessing calibration of prognostic risk scores , 2016, Statistical methods in medical research.

[37]  Krishna P. Gummadi,et al.  Fairness Constraints: Mechanisms for Fair Classification , 2015, AISTATS.

[38]  Jon M. Kleinberg,et al.  Inherent Trade-Offs in the Fair Determination of Risk Scores , 2016, ITCS.