On the Applicability of Machine Learning Fairness Notions

Machine Learning (ML) based predictive systems are increasingly used to support decisions with a critical impact on individuals' lives such as college admission, job hiring, child custody, criminal risk assessment, etc. As a result, fairness emerged as an important requirement to guarantee that ML predictive systems do not discriminate against specific individuals or entire sub-populations, in particular, minorities. Given the inherent subjectivity of viewing the concept of fairness, several notions of fairness have been introduced in the literature. This paper is a survey of fairness notions that, unlike other surveys in the literature, addresses the question of "which notion of fairness is most suited to a given real-world scenario and why?". Our attempt to answer this question consists in (1) identifying the set of fairness-related characteristics of the real-world scenario at hand, (2) analyzing the behavior of each fairness notion, and then (3) fitting these two elements to recommend the most suitable fairness notion in every specific setup. The results are summarized in a decision diagram that can be used by practitioners and policy makers to navigate the relatively large catalogue of ML fairness notions.

[1]  Solon Barocas,et al.  Prediction-Based Decisions and Fairness: A Catalogue of Choices, Assumptions, and Definitions , 2018, 1811.07867.

[2]  Thomas S. Woodson.  Weapons of math destruction , 2018, Journal of Responsible Innovation.

[3]  Michael Luca,et al.  Supplemental Appendix for : Productivity and Selection of Human Capital with Machine Learning , 2016 .

[4]  Suresh Venkatasubramanian,et al.  A comparative study of fairness-enhancing interventions in machine learning , 2018, FAT.

[5]  Luca Oneto,et al.  Fairness in Machine Learning , 2020, INNSBDDL.

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

[7]  Sherita Hill Golden,et al.  Race/Ethnic Difference in Diabetes and Diabetic Complications , 2013, Current Diabetes Reports.

[8]  F Lefford,et al.  A blot on the profession , 1988, British medical journal.

[9]  Krishna P. Gummadi,et al.  Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment , 2016, WWW.

[10]  COMPAS Risk Scales : Demonstrating Accuracy Equity and Predictive Parity Performance of the COMPAS Risk Scales in Broward County , 2016 .

[11]  Harris Mateen.  Weapons of Math Destruction: How Big Data Increases Inequality and Threatens Democracy , 2018 .

[12]  J. Pearl,et al.  Causal Inference in Statistics: A Primer , 2016 .

[13]  Sharad Goel,et al.  The Measure and Mismeasure of Fairness: A Critical Review of Fair Machine Learning , 2018, ArXiv.

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

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

[16]  Matt J. Kusner,et al.  Counterfactual Fairness , 2017, NIPS.

[17]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[18]  W. Cliby,et al.  Skene's gland adenocarcinoma with increased serum level of prostate-specific antigen. , 1994, Gynecologic oncology.

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

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

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

[22]  Pratyush Garg,et al.  Fairness Metrics: A Comparative Analysis , 2020, 2020 IEEE International Conference on Big Data (Big Data).

[23]  K. Crenshaw.  Mapping the margins: intersectionality, identity politics, and violence against women of color , 1991 .

[24]  Andrew D. Selbst,et al.  Big Data's Disparate Impact , 2016 .

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

[26]  Indre Zliobaite,et al.  A survey on measuring indirect discrimination in machine learning , 2015, ArXiv.

[27]  Hannah Lebovits.  Automating Inequality: How High-Tech Tools Profile, Police, and Punish the Poor , 2018, Public Integrity.

[28]  Xi Zhang,et al.  Automated Inference on Criminality using Face Images , 2016, ArXiv.

[29]  John Daniel,et al.  Rankings and Accountability in Higher Education : Uses and Misuses , 2013 .

[30]  Faisal Kamiran,et al.  Quantifying explainable discrimination and removing illegal discrimination in automated decision making , 2012, Knowledge and Information Systems.

[31]  Yongjie Yang,et al.  Fairness in Algorithmic Decision-Making: Applications in Multi-Winner Voting, Machine Learning, and Recommender Systems , 2019, Algorithms.

[32]  Mark Wilson,et al.  Unfair Treatment? The Case of Freedle, the SAT, and the Standardization Approach to Differential Item Functioning , 2010 .

[33]  Julia Rubin,et al.  Fairness Definitions Explained , 2018, 2018 IEEE/ACM International Workshop on Software Fairness (FairWare).

[34]  Gerhard Friedrich,et al.  Recommender Systems - An Introduction , 2010 .

[35]  Jeffrey Bellin.  The Inverse Relationship between the Constitutionality and Effectiveness of New York City 'Stop and Frisk' , 2014 .

[36]  Kristina Lerman,et al.  A Survey on Bias and Fairness in Machine Learning , 2019, ACM Comput. Surv..

[37]  Guy N. Rothblum,et al.  Fairness Through Computationally-Bounded Awareness , 2018, NeurIPS.

[38]  M. Kearns,et al.  Fairness in Criminal Justice Risk Assessments: The State of the Art , 2017, Sociological Methods & Research.

[39]  Afshin Dehghan,et al.  DAGER: Deep Age, Gender and Emotion Recognition Using Convolutional Neural Network , 2017, ArXiv.

[40]  Yuriy Brun,et al.  Fairness testing: testing software for discrimination , 2017, ESEC/SIGSOFT FSE.

[41]  Suresh Venkatasubramanian,et al.  On the (im)possibility of fairness , 2016, ArXiv.