FaiR-N: Fair and Robust Neural Networks for Structured Data

Fairness in machine learning is crucial when individuals are subject to automated decisions made by models in high-stake domains. Organizations that employ these models may also need to satisfy regulations that promote responsible and ethical A.I. While fairness metrics relying on comparing model error rates across subpopulations have been widely investigated for the detection and mitigation of bias, fairness in terms of the equalized ability to achieve recourse for different protected attribute groups has been relatively unexplored. We present a novel formulation for training neural networks that considers the distance of data points to the decision boundary such that the new objective: (1) reduces the average distance to the decision boundary between two groups for individuals subject to a negative outcome in each group, i.e. the network is more fair with respect to the ability to obtain recourse, and (2) increases the average distance of data points to the boundary to promote adversarial robustness. We demonstrate that training with this loss yields more fair and robust neural networks with similar accuracies to models trained without it. Moreover, we qualitatively motivate and empirically show that reducing recourse disparity across groups also improves fairness measures that rely on error rates. To the best of our knowledge, this is the first time that recourse capabilities across groups are considered to train fairer neural networks, and a relation between error rates based fairness and recourse based fairness is investigated.

[1]  Anca D. Dragan,et al.  The Social Cost of Strategic Classification , 2018, FAT.

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

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

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

[5]  A. K. Taylor,et al.  The Medical Expenditure Panel Survey: a national health information resource. , 1996, Inquiry : a journal of medical care organization, provision and financing.

[6]  Jiliang Tang,et al.  Characterizing the Decision Boundary of Deep Neural Networks , 2019, ArXiv.

[7]  Rachel K. E. Bellamy,et al.  AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias , 2018, ArXiv.

[8]  Toon Calders,et al.  Discrimination Aware Decision Tree Learning , 2010, 2010 IEEE International Conference on Data Mining.

[9]  Kui Ren,et al.  Adversarial Attacks and Defenses in Deep Learning , 2020, Engineering.

[10]  Pascal Frossard,et al.  Imperceptible Adversarial Attacks on Tabular Data , 2019, ArXiv.

[11]  Brian D. Ziebart,et al.  Fair Logistic Regression: An Adversarial Perspective , 2019, ArXiv.

[12]  Yang Liu,et al.  Actionable Recourse in Linear Classification , 2018, FAT.

[13]  Jette Henderson,et al.  CERTIFAI: A Common Framework to Provide Explanations and Analyse the Fairness and Robustness of Black-box Models , 2020, AIES.

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

[15]  Hossein Mobahi,et al.  Large Margin Deep Networks for Classification , 2018, NeurIPS.

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

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

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

[19]  Yunfeng Zhang,et al.  Data Augmentation for Discrimination Prevention and Bias Disambiguation , 2020, AIES.

[20]  Michael Butterworth,et al.  The ICO and artificial intelligence: The role of fairness in the GDPR framework , 2018, Comput. Law Secur. Rev..

[21]  Dianne P. O'Leary,et al.  Investigating Decision Boundaries of Trained Neural Networks , 2019, ArXiv.

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

[23]  Nisheeth K. Vishnoi,et al.  Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees , 2018, FAT.

[24]  Chris Russell,et al.  Counterfactual Explanations Without Opening the Black Box: Automated Decisions and the GDPR , 2017, ArXiv.

[25]  Philipp Hacker,et al.  Teaching fairness to artificial intelligence: Existing and novel strategies against algorithmic discrimination under EU law , 2018, Common Market Law Review.

[26]  Brian D. Ziebart,et al.  Fairness for Robust Log Loss Classification , 2019, AAAI.