Empirical Risk Minimization under Fairness Constraints

Abstract

We address the problem of algorithmic fairness: ensuring that sensitive variables do not unfairly influence the outcome of a classifier. We present an approach based on empirical risk minimization, which incorporates a fairness constraint into the learning problem. It encourages the conditional risk of the learned classifier to be approximately constant with respect to the sensitive variable. We derive both risk and fairness bounds that support the statistical consistency of our approach. We specify our approach to kernel methods and observe that the fairness requirement implies an orthogonality constraint which can be easily added to these methods. We further observe that for linear models the constraint translates into a simple data preprocessing step. Experiments indicate that the method is empirically effective and performs favorably against state-of-the-art approaches.

References in corpus (14)

• Equality of Opportunity in Supervised Learning
• Counterfactual Fairness
• Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness
• Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations
• On Fairness and Calibration
• A Convex Framework for Fair Regression
• Learning Non-Discriminatory Predictors
• From Parity to Preference-based Notions of Fairness in Classification
• A Reductions Approach to Fair Classification
• A Note on the PAC Bayesian Theorem
• On the relation between accuracy and fairness in binary classification
• Penalizing Unfairness in Binary Classification
• A statistical framework for fair predictive algorithms
• Iterative Orthogonal Feature Projection for Diagnosing Bias in Black-Box Models

Cited by in corpus (19)

• Identifying and Correcting Label Bias in Machine Learning
• A Reductions Approach to Fair Classification
• POTs: Protective Optimization Technologies
• Fairness for Robust Log Loss Classification
• Amazon SageMaker Clarify: Machine Learning Bias Detection and Explainability in the Cloud
• A General Framework for Fair Regression
• Wasserstein Fair Classification
• Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML
• Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraints
• Achieving Model Fairness in Vertical Federated Learning
• Deontological Ethics By Monotonicity Shape Constraints
• Fair Classification and Social Welfare
• Measuring Fairness Under Unawareness of Sensitive Attributes: A Quantification-Based Approach
• Probably Approximately Correct Constrained Learning
• Fairness-aware Summarization for Justified Decision-Making
• Fair Sparse Regression with Clustering: An Invex Relaxation for a Combinatorial Problem
• Improved Complexities for Stochastic Conditional Gradient Methods under Interpolation-like Conditions
• Debiasing Credit Scoring using Evolutionary Algorithms
• Coping with Mistreatment in Fair Algorithms