Fairness for Robust Log Loss Classification

Abstract

Developing classification methods with high accuracy that also avoid unfair treatment of different groups has become increasingly important for data-driven decision making in social applications. Many existing methods enforce fairness constraints on a selected classifier (e.g., logistic regression) by directly forming constrained optimizations. We instead re-derive a new classifier from the first principles of distributional robustness that incorporates fairness criteria into a worst-case logarithmic loss minimization. This construction takes the form of a minimax game and produces a parametric exponential family conditional distribution that resembles truncated logistic regression. We present the theoretical benefits of our approach in terms of its convexity and asymptotic convergence. We then demonstrate the practical advantages of our approach on three benchmark fairness datasets.

References in corpus (18)

• Scikit-learn: Machine Learning in Python
• Equality of Opportunity in Supervised Learning
• Fairness of Exposure in Rankings
• Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory
• Fairness Constraints: Mechanisms for Fair Classification
• On Fairness and Calibration
• AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
• Fairness Without Demographics in Repeated Loss Minimization
• Learning Adversarially Fair and Transferable Representations
• Learning Non-Discriminatory Predictors
• From Parity to Preference-based Notions of Fairness in Classification
• Empirical Risk Minimization under Fairness Constraints
• Penalizing Unfairness in Binary Classification
• Obtaining fairness using optimal transport theory
• FairGAN: Fairness-aware Generative Adversarial Networks
• Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees
• Improved Adversarial Learning for Fair Classification
• Consistent Robust Adversarial Prediction for General Multiclass Classification

Cited by in corpus (9)

• A Distributionally Robust Approach to Fair Classification
• Rényi Fair Inference
• On Tilted Losses in Machine Learning: Theory and Applications
• Nonconvex-Nonconcave Min-Max Optimization with a Small Maximization Domain
• Robust Fairness-aware Learning Under Sample Selection Bias
• Tilted Empirical Risk Minimization
• Fairness Through Regularization for Learning to Rank
• Algorithm Fairness in AI for Medicine and Healthcare
• Bias-Tolerant Fair Classification