Towards Threshold Invariant Fair Classification

Effective machine learning models can automatically learn useful information from a large quantity of data and provide decisions in a high accuracy. These models may, however, lead to unfair predictions in certain sense among the population groups of interest, where the grouping is based on such sensitive attributes as race and gender. Various fairness definitions, such as demographic parity and equalized odds, were proposed in prior art to ensure that decisions guided by the machine learning models are equitable. Unfortunately, the "fair" model trained with these fairness definitions is threshold sensitive, i.e., the condition of fairness may no longer hold true when tuning the decision threshold. This paper introduces the notion of threshold invariant fairness, which enforces equitable performances across different groups independent of the decision threshold. To achieve this goal, this paper proposes to equalize the risk distributions among the groups via two approximation methods. Experimental results demonstrate that the proposed methodology is effective to alleviate the threshold sensitivity in machine learning models designed to achieve fairness.

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

[2]  Christopher T. Lowenkamp,et al.  False Positives, False Negatives, and False Analyses: A Rejoinder to "Machine Bias: There's Software Used across the Country to Predict Future Criminals. and It's Biased against Blacks" , 2016 .

[3]  Hany Farid,et al.  The accuracy, fairness, and limits of predicting recidivism , 2018, Science Advances.

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

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

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

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

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

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

[10]  G. Wahba,et al.  Some results on Tchebycheffian spline functions , 1971 .

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

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

[13]  Toon Calders,et al.  Data preprocessing techniques for classification without discrimination , 2011, Knowledge and Information Systems.

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

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

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

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

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

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

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

[21]  Yoram Singer,et al.  Pegasos: primal estimated sub-gradient solver for SVM , 2011, Math. Program..