A Convex Framework for Fair Regression

Abstract

We introduce a flexible family of fairness regularizers for (linear and logistic) regression problems. These regularizers all enjoy convexity, permitting fast optimization, and they span the rang from notions of group fairness to strong individual fairness. By varying the weight on the fairness regularizer, we can compute the efficient frontier of the accuracy-fairness trade-off on any given dataset, and we measure the severity of this trade-off via a numerical quantity we call the Price of Fairness (PoF). The centerpiece of our results is an extensive comparative study of the PoF across six different datasets in which fairness is a primary consideration.

References in corpus (3)

• Equality of Opportunity in Supervised Learning
• On the (im)possibility of fairness
• Learning Non-Discriminatory Predictors

Cited by in corpus (70)

• Fairness in Machine Learning: A Survey
• Fairness in Machine Learning
• A Clarification of the Nuances in the Fairness Metrics Landscape
• Fighting Fire with Fire: Using Antidote Data to Improve Polarization and Fairness of Recommender Systems
• A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle
• Empirical Risk Minimization under Fairness Constraints
• Fair Regression for Health Care Spending
• Calibration for the (Computationally-Identifiable) Masses
• Robust Optimization for Fairness with Noisy Protected Groups
• A survey on datasets for fairness-aware machine learning
• Inherent Limitations of AI Fairness
• Probably Approximately Metric-Fair Learning
• Socially Responsible AI Algorithms: Issues, Purposes, and Challenges
• Mitigating Unfairness via Evolutionary Multi-objective Ensemble Learning
• What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspective
• Fairness in Agreement With European Values: An Interdisciplinary Perspective on AI Regulation
• Constrained Learning with Non-Convex Losses
• Review of Mathematical frameworks for Fairness in Machine Learning
• Achieving Fairness in the Stochastic Multi-armed Bandit Problem
• Software Engineering for Fairness: A Case Study with Hyperparameter Optimization
• Rényi Fair Inference
• Two-stage Algorithm for Fairness-aware Machine Learning
• Towards Accuracy-Fairness Paradox: Adversarial Example-based Data Augmentation for Visual Debiasing
• Learning Optimal and Fair Decision Trees for Non-Discriminative Decision-Making
• Loss-Aversively Fair Classification
• Accounting for Model Uncertainty in Algorithmic Discrimination
• Same-Day Delivery with Fairness
• Subverting Fair Image Search with Generative Adversarial Perturbations
• Does Gender Matter? Towards Fairness in Dialogue Systems
• Interpretable and Fair Boolean Rule Sets via Column Generation
• Removing biased data to improve fairness and accuracy
• Modeling Techniques for Machine Learning Fairness: A Survey
• Deontological Ethics By Monotonicity Shape Constraints
• Fast Fair Regression via Efficient Approximations of Mutual Information
• Fair Forests: Regularized Tree Induction to Minimize Model Bias
• FairST: Equitable Spatial and Temporal Demand Prediction for New Mobility Systems
• Addressing multiple metrics of group fairness in data-driven decision making
• Fairness Measures for Regression via Probabilistic Classification
• Statistical Equity: A Fairness Classification Objective
• Auditing Cross-Cultural Consistency of Human-Annotated Labels for Recommendation Systems
• The Fairness-Accuracy Pareto Front
• Fairness Warnings and Fair-MAML: Learning Fairly with Minimal Data
• Improving Fairness in Adaptive Social Exergames via Shapley Bandits
• Avoiding Resentment Via Monotonic Fairness
• What About Applied Fairness?
• Augmented Fairness: An Interpretable Model Augmenting Decision-Makers' Fairness
• Fairness and Missing Values
• Intersectionality: Multiple Group Fairness in Expectation Constraints
• Pairwise Fairness for Ranking and Regression
• Priority-based Post-Processing Bias Mitigation for Individual and Group Fairness
• Probabilistic Verification of Neural Networks Against Group Fairness
• Fair Data Representation for Machine Learning at the Pareto Frontier
• A Primal-Dual Subgradient Approachfor Fair Meta Learning
• Transitioning from Real to Synthetic data: Quantifying the bias in model
• Learning Fair and Interpretable Representations via Linear Orthogonalization
• Fair Decision Rules for Binary Classification
• Probably Approximately Correct Constrained Learning
• The Sharpe predictor for fairness in machine learning
• Fair Representation Learning using Interpolation Enabled Disentanglement
• Fairness-aware Outlier Ensemble
• Grading video interviews with fairness considerations
• Fairness-aware Summarization for Justified Decision-Making
• Fair Algorithms for Learning in Allocation Problems
• Obstructing Classification via Projection
• Fair Sparse Regression with Clustering: An Invex Relaxation for a Combinatorial Problem
• Bias-Tolerant Fair Classification
• Pairwise Fairness for Ordinal Regression
• Rank-Based Multi-task Learning for Fair Regression
• Unfairness Discovery and Prevention For Few-Shot Regression
• Fair Meta-Learning For Few-Shot Classification