Learning fair predictors with Sensitive Subspace Robustness

We consider an approach to training machine learning systems that are fair in the sense that their performance is invariant under certain perturbations to the features. For example, the performance of a resume screening system should be invariant under changes to the name of the applicant or switching the gender pronouns. We connect this intuitive notion of algorithmic fairness to individual fairness and study how to certify ML algorithms as algorithmically fair. We also demonstrate the effectiveness of our approach on three machine learning tasks that are susceptible to gender and racial biases.

[1]  Peng Sun,et al.  A Robust Optimization Perspective on Stochastic Programming , 2007, Oper. Res..

[2]  Adam Tauman Kalai,et al.  Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings , 2016, NIPS.

[3]  Daniel Kuhn,et al.  Distributionally Robust Logistic Regression , 2015, NIPS.

[4]  Shin Ishii,et al.  Distributional Smoothing with Virtual Adversarial Training , 2015, ICLR 2016.

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

[6]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[7]  Hal Daumé,et al.  Deep Unordered Composition Rivals Syntactic Methods for Text Classification , 2015, ACL.

[8]  Yuekai Sun,et al.  Debiasing representations by removing unwanted variation due to protected attributes , 2018, ArXiv.

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

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

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

[12]  Jaeho Lee,et al.  Minimax Statistical Learning with Wasserstein distances , 2017, NeurIPS.

[13]  Karthyek R. A. Murthy,et al.  Quantifying Distributional Model Risk Via Optimal Transport , 2016, Math. Oper. Res..

[14]  Tommi S. Jaakkola,et al.  A causal framework for explaining the predictions of black-box sequence-to-sequence models , 2017, EMNLP.

[15]  David A. Wagner,et al.  Towards Evaluating the Robustness of Neural Networks , 2016, 2017 IEEE Symposium on Security and Privacy (SP).

[16]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[17]  Samy Bengio,et al.  Adversarial Machine Learning at Scale , 2016, ICLR.

[18]  Saeed Ghadimi,et al.  Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming , 2013, SIAM J. Optim..

[19]  Nathan Srebro,et al.  Learning Non-Discriminatory Predictors , 2017, COLT.

[20]  Alexandra Chouldechova,et al.  Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting , 2019, FAT.

[21]  Yinyu Ye,et al.  Distributionally Robust Optimization Under Moment Uncertainty with Application to Data-Driven Problems , 2010, Oper. Res..

[22]  Seth Neel,et al.  Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness , 2017, ICML.

[23]  Alexander Shapiro,et al.  Stochastic Approximation approach to Stochastic Programming , 2013 .

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

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

[26]  Anja De Waegenaere,et al.  Robust Solutions of Optimization Problems Affected by Uncertain Probabilities , 2011, Manag. Sci..

[27]  John Duchi,et al.  Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach , 2016, Math. Oper. Res..

[28]  John C. Duchi,et al.  Certifying Some Distributional Robustness with Principled Adversarial Training , 2017, ICLR.

[29]  Christopher Jung,et al.  Online Learning with an Unknown Fairness Metric , 2018, NeurIPS.

[30]  Shai Ben-David,et al.  Empirical Risk Minimization under Fairness Constraints , 2018, NeurIPS.

[31]  Ananthram Swami,et al.  The Limitations of Deep Learning in Adversarial Settings , 2015, 2016 IEEE European Symposium on Security and Privacy (EuroS&P).

[32]  Timnit Gebru,et al.  Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification , 2018, FAT.

[33]  Percy Liang,et al.  Fairness Without Demographics in Repeated Loss Minimization , 2018, ICML.

[34]  Bing Liu,et al.  Mining and summarizing customer reviews , 2004, KDD.

[35]  Barbara Lindemann Schlei,et al.  Employment Discrimination Law , 1976 .

[36]  Katrina Ligett,et al.  Penalizing Unfairness in Binary Classification , 2017 .

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

[38]  Arvind Narayanan,et al.  Semantics derived automatically from language corpora contain human-like biases , 2016, Science.

[39]  M. KarthyekRajhaaA.,et al.  Robust Wasserstein profile inference and applications to machine learning , 2019, J. Appl. Probab..

[40]  Suresh Venkatasubramanian,et al.  On the (im)possibility of fairness , 2016, ArXiv.

[41]  Alexandra Chouldechova,et al.  What’s in a Name? Reducing Bias in Bios without Access to Protected Attributes , 2019, NAACL.

[42]  Christina Ilvento,et al.  Metric Learning for Individual Fairness , 2019, FORC.

[43]  Adam Tauman Kalai,et al.  What are the Biases in My Word Embedding? , 2018, AIES.

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

[45]  Aleksander Madry,et al.  Towards Deep Learning Models Resistant to Adversarial Attacks , 2017, ICLR.

[46]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[47]  Melvyn Sim,et al.  Distributionally Robust Optimization and Its Tractable Approximations , 2010, Oper. Res..

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

[49]  Christopher Jung,et al.  Eliciting and Enforcing Subjective Individual Fairness , 2019, ArXiv.

[50]  John C. Duchi,et al.  Variance-based Regularization with Convex Objectives , 2016, NIPS.

[51]  Henry Lam,et al.  Quantifying uncertainty in sample average approximation , 2015, 2015 Winter Simulation Conference (WSC).

[52]  Joan Bruna,et al.  Intriguing properties of neural networks , 2013, ICLR.

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

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

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

[56]  Daniel Kuhn,et al.  Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations , 2015, Mathematical Programming.

[57]  John C. Duchi,et al.  Stochastic Gradient Methods for Distributionally Robust Optimization with f-divergences , 2016, NIPS.