Conditional Learning of Fair Representations

We propose a novel algorithm for learning fair representations that can simultaneously mitigate two notions of disparity among different demographic subgroups. Two key components underpinning the design of our algorithm are balanced error rate and conditional alignment of representations. We show how these two components contribute to ensuring accuracy parity and equalized false-positive and false-negative rates across groups without impacting demographic parity. Furthermore, we also demonstrate both in theory and on two real-world experiments that the proposed algorithm leads to a better utility-fairness trade-off on balanced datasets compared with existing algorithms on learning fair representations.

[1]  Shai Ben-David,et al.  On the difficulty of approximately maximizing agreements , 2000, J. Comput. Syst. Sci..

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[18]  Elad Eban,et al.  Scalable Learning of Non-Decomposable Objectives , 2016, AISTATS.

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

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

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

[22]  Constantinos Daskalakis,et al.  The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimization , 2018, NeurIPS.

[23]  Alexandra Chouldechova,et al.  The Frontiers of Fairness in Machine Learning , 2018, ArXiv.

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

[25]  Aditya Krishna Menon,et al.  The cost of fairness in binary classification , 2018, FAT.

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

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

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

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

[30]  Toniann Pitassi,et al.  Flexibly Fair Representation Learning by Disentanglement , 2019, ICML.

[31]  Geoffrey J. Gordon,et al.  Inherent Tradeoffs in Learning Fair Representations , 2019, NeurIPS.

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

[33]  Yixin Wang,et al.  Equal Opportunity and Affirmative Action via Counterfactual Predictions , 2019, ArXiv.

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

[35]  Zoubin Ghahramani,et al.  One-Network Adversarial Fairness , 2019, AAAI.

[36]  Silvia Chiappa,et al.  Wasserstein Fair Classification , 2019, UAI.

[37]  Edward H. Kennedy,et al.  Counterfactual risk assessments, evaluation, and fairness , 2019, FAT*.