Fairness in Algorithmic Decision Making: An Excursion Through the Lens of Causality

As virtually all aspects of our lives are increasingly impacted by algorithmic decision making systems, it is incumbent upon us as a society to ensure such systems do not become instruments of unfair discrimination on the basis of gender, race, ethnicity, religion, etc. We consider the problem of determining whether the decisions made by such systems are discriminatory, through the lens of causal models. We introduce two definitions of group fairness grounded in causality: fair on average causal effect (FACE), and fair on average causal effect on the treated (FACT). We use the Rubin-Neyman potential outcomes framework for the analysis of cause-effect relationships to robustly estimate FACE and FACT. We demonstrate the effectiveness of our proposed approach on synthetic data. Our analyses of two real-world data sets, the Adult income data set from the UCI repository (with gender as the protected attribute), and the NYC Stop and Frisk data set (with race as the protected attribute), show that the evidence of discrimination obtained by FACE and FACT, or lack thereof, is often in agreement with the findings from other studies. We further show that FACT, being somewhat more nuanced compared to FACE, can yield findings of discrimination that differ from those obtained using FACE.

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

[2]  Carlos Eduardo Scheidegger,et al.  Certifying and Removing Disparate Impact , 2014, KDD.

[3]  Judea Pearl,et al.  Causal Inference , 2010 .

[4]  Solon Barocas,et al.  Big Data, Data Science, and Civil Rights , 2017, ArXiv.

[5]  Elizabeth A Stuart,et al.  Matching methods for causal inference: A review and a look forward. , 2010, Statistical science : a review journal of the Institute of Mathematical Statistics.

[6]  Luke Keele,et al.  An overview of rbounds: An R package for Rosenbaum bounds sensitivity analysis with matched data. , 2010 .

[7]  P. Holland.  Statistics and Causal Inference , 1985 .

[8]  D. Rubin,et al.  Constructing a Control Group Using Multivariate Matched Sampling Methods That Incorporate the Propensity Score , 1985 .

[9]  Jiuyong Li,et al.  Discrimination detection by causal effect estimation , 2017, 2017 IEEE International Conference on Big Data (Big Data).

[10]  Silvia Chiappa,et al.  Path-Specific Counterfactual Fairness , 2018, AAAI.

[11]  T. VanderWeele,et al.  On the causal interpretation of race in regressions adjusting for confounding and mediating variables. , 2014, Epidemiology.

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

[13]  Gary King,et al.  Misunderstandings between experimentalists and observationalists about causal inference , 2008 .

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

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

[16]  Illtyd Trethowan.  Causality , 1938 .

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

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

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

[20]  Toon Calders,et al.  Classifying without discriminating , 2009, 2009 2nd International Conference on Computer, Control and Communication.

[21]  Lu Zhang,et al.  A Causal Framework for Discovering and Removing Direct and Indirect Discrimination , 2016, IJCAI.

[22]  Toniann Pitassi,et al.  Fairness through Causal Awareness: Learning Causal Latent-Variable Models for Biased Data , 2018, FAT.

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

[24]  D. Rubin,et al.  The central role of the propensity score in observational studies for causal effects , 1983 .

[25]  Ilya Shpitser,et al.  Fair Inference on Outcomes , 2017, AAAI.

[26]  Matt J. Kusner,et al.  Causal Reasoning for Algorithmic Fairness , 2018, ArXiv.

[27]  Matt J. Kusner,et al.  When Worlds Collide: Integrating Different Counterfactual Assumptions in Fairness , 2017, NIPS.

[28]  D. Rubin,et al.  Causal Inference for Statistics, Social, and Biomedical Sciences: A General Method for Estimating Sampling Variances for Standard Estimators for Average Causal Effects , 2015 .

[29]  Salvatore Ruggieri,et al.  A multidisciplinary survey on discrimination analysis , 2013, The Knowledge Engineering Review.

[30]  Lu Zhang,et al.  Situation Testing-Based Discrimination Discovery: A Causal Inference Approach , 2016, IJCAI.

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

[32]  Matt J. Kusner,et al.  Causal Interventions for Fairness , 2018, ArXiv.

[33]  Gary King,et al.  MatchIt: Nonparametric Preprocessing for Parametric Causal Inference , 2011 .

[34]  Krishna P. Gummadi,et al.  The Case for Process Fairness in Learning: Feature Selection for Fair Decision Making , 2016 .

[35]  Francesco Bonchi,et al.  Exposing the probabilistic causal structure of discrimination , 2015, International Journal of Data Science and Analytics.

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

[37]  D. Rubin.  Estimating causal effects of treatments in randomized and nonrandomized studies. , 1974 .

[38]  Elizabeth A. Stuart,et al.  An Introduction to Sensitivity Analysis for Unobserved Confounding in Nonexperimental Prevention Research , 2013, Prevention Science.

[39]  P. Rosenbaum.  A Characterization of Optimal Designs for Observational Studies , 1991 .

[40]  Joichi Ito,et al.  Interventions over Predictions: Reframing the Ethical Debate for Actuarial Risk Assessment , 2017, FAT.

[41]  I NICOLETTI,et al.  The Planning of Experiments , 1936, Rivista di clinica pediatrica.

[42]  J. Robins,et al.  Marginal Structural Models and Causal Inference in Epidemiology , 2000, Epidemiology.

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

[44]  Ronald B. Geskus,et al.  ipw: An R Package for Inverse Probability Weighting , 2011 .

[45]  Kristian Lum,et al.  An algorithm for removing sensitive information: Application to race-independent recidivism prediction , 2017, The Annals of Applied Statistics.

[46]  D. V. Lindley,et al.  Randomization Analysis of Experimental Data: The Fisher Randomization Test Comment , 1980 .

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

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

[49]  Ron Kohavi,et al.  Scaling Up the Accuracy of Naive-Bayes Classifiers: A Decision-Tree Hybrid , 1996, KDD.

[50]  Donald B. Rubin,et al.  Bayesian Inference for Causal Effects: The Role of Randomization , 1978 .

[51]  D. Rubin,et al.  Causal Inference for Statistics, Social, and Biomedical Sciences: An Introduction , 2016 .

[52]  Paul R. Rosenbaum,et al.  Sensitivity Analysis in Observational Studies , 2005 .

[53]  J. Pearl.  3. The Foundations of Causal Inference , 2010 .

[54]  Elias Bareinboim,et al.  Fairness in Decision-Making - The Causal Explanation Formula , 2018, AAAI.

[55]  E. Stuart,et al.  Misunderstandings among Experimentalists and Observationalists about Causal Inference , 2007 .

[56]  J. Pearl.  On the Interpretation of do ( x ) , 2019 .

[57]  Jun Sakuma,et al.  Fairness-Aware Classifier with Prejudice Remover Regularizer , 2012, ECML/PKDD.

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

[59]  Judea Pearl.  On the Interpretation of do(x)do(x) , 2019, Journal of Causal Inference.

[60]  D. Rubin.  Using Propensity Scores to Help Design Observational Studies: Application to the Tobacco Litigation , 2001, Health Services and Outcomes Research Methodology.

[61]  Toon Calders,et al.  Building Classifiers with Independency Constraints , 2009, 2009 IEEE International Conference on Data Mining Workshops.