Path-Specific Counterfactual Fairness

We consider the problem of learning fair decision systems in complex scenarios in which a sensitive attribute might affect the decision along both fair and unfair pathways. We introduce a causal approach to disregard effects along unfair pathways that simplifies and generalizes previous literature. Our method corrects observations adversely affected by the sensitive attribute, and uses these to form a decision. This avoids disregarding fair information, and does not require an often intractable computation of the path-specific effect. We leverage recent developments in deep learning and approximate inference to achieve a solution that is widely applicable to complex, non-linear scenarios.

[1]  Ilya Shpitser,et al.  Counterfactual Graphical Models for Longitudinal Mediation Analysis With Unobserved Confounding , 2012, Cogn. Sci..

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

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

[4]  Silvia Chiappa,et al.  Explicit-Duration Markov Switching Models , 2014, Found. Trends Mach. Learn..

[5]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

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

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

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

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

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

[11]  Bernhard Schölkopf,et al.  A Kernel Two-Sample Test , 2012, J. Mach. Learn. Res..

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

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

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

[15]  J. Pearl.  Causality: Models, Reasoning and Inference , 2000 .

[16]  A. Dawid.  FUNDAMENTALS OF STATISTICAL CAUSALITY , 2007 .

[17]  Bernhard Schölkopf,et al.  Elements of Causal Inference: Foundations and Learning Algorithms , 2017 .

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

[19]  Cynthia Rudin,et al.  Interpretable classification models for recidivism prediction , 2015, 1503.07810.

[20]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[21]  M. Hoffman,et al.  Discretion in Hiring , 2015 .

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

[23]  J. Pearl.  The Causal Mediation Formula—A Guide to the Assessment of Pathways and Mechanisms , 2012, Prevention Science.

[24]  Lu Zhang,et al.  Anti-discrimination learning: a causal modeling-based framework , 2017, International Journal of Data Science and Analytics.

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

[26]  Daan Wierstra,et al.  Stochastic Backpropagation and Approximate Inference in Deep Generative Models , 2014, ICML.

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

[28]  Judea Pearl,et al.  Direct and Indirect Effects , 2001, UAI.

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

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

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

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

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

[34]  Kush R. Varshney,et al.  Optimized Pre-Processing for Discrimination Prevention , 2017, NIPS.