Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment

Abstract

Automated data-driven decision making systems are increasingly being used to assist, or even replace humans in many settings. These systems function by learning from historical decisions, often taken by humans. In order to maximize the utility of these systems (or, classifiers), their training involves minimizing the errors (or, misclassifications) over the given historical data. However, it is quite possible that the optimally trained classifier makes decisions for people belonging to different social groups with different misclassification rates (e.g., misclassification rates for females are higher than for males), thereby placing these groups at an unfair disadvantage. To account for and avoid such unfairness, in this paper, we introduce a new notion of unfairness, disparate mistreatment, which is defined in terms of misclassification rates. We then propose intuitive measures of disparate mistreatment for decision boundary-based classifiers, which can be easily incorporated into their formulation as convex-concave constraints. Experiments on synthetic as well as real world datasets show that our methodology is effective at avoiding disparate mistreatment, often at a small cost in terms of accuracy.

arXiv commentTo appear in Proceedings of the 26th International World Wide Web Conference (WWW), 2017. Code available at: https://github.com/mbilalzafar/fair-classification

References in corpus (3)

• Equality of Opportunity in Supervised Learning
• Inherent Trade-Offs in the Fair Determination of Risk Scores
• Fairness Constraints: Mechanisms for Fair Classification

Cited by in corpus (77)

• Fairness And Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, And Mitigation Strategies
• Prediction-Based Decisions and Fairness: A Catalogue of Choices, Assumptions, and Definitions
• Fairness of Exposure in Rankings
• Fairness in Machine Learning: A Survey
• A Survey on the Fairness of Recommender Systems
• Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Search
• Equity of Attention: Amortizing Individual Fairness in Rankings
• Fairness in Machine Learning
• Explaining Models: An Empirical Study of How Explanations Impact Fairness Judgment
• A Clarification of the Nuances in the Fairness Metrics Landscape
• User-oriented Fairness in Recommendation
• Fairness in Recommender Systems: Research Landscape and Future Directions
• A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual & Group Unfairness via Inequality Indices
• Learning Model-Agnostic Counterfactual Explanations for Tabular Data
• Towards Fairness-Aware Federated Learning
• The Butterfly Effect in Artificial Intelligence Systems: Implications for AI Bias and Fairness
• Fighting Fire with Fire: Using Antidote Data to Improve Polarization and Fairness of Recommender Systems
• Fairness in Algorithmic Decision Making: An Excursion Through the Lens of Causality
• Fair Task Allocation in Crowdsourced Delivery
• Explanations, Fairness, and Appropriate Reliance in Human-AI Decision-Making
• AdaFair: Cumulative Fairness Adaptive Boosting
• Fair Regression for Health Care Spending
• POTs: Protective Optimization Technologies
• Machine learning fairness notions: Bridging the gap with real-world applications
• Soliciting Stakeholders' Fairness Notions in Child Maltreatment Predictive Systems
• How fair can we go in machine learning? Assessing the boundaries of fairness in decision trees
• Fairness in Risk Assessment Instruments: Post-Processing to Achieve Counterfactual Equalized Odds
• Fairness in Semi-supervised Learning: Unlabeled Data Help to Reduce Discrimination
• A survey on datasets for fairness-aware machine learning
• Marrying Fairness and Explainability in Supervised Learning
• Case Study: Predictive Fairness to Reduce Misdemeanor Recidivism Through Social Service Interventions
• Fair Classification with Group-Dependent Label Noise
• Mitigating Unfairness via Evolutionary Multi-objective Ensemble Learning
• Trajectories of Blocked Community Members: Redemption, Recidivism and Departure
• Towards Individual and Multistakeholder Fairness in Tourism Recommender Systems
• Visus: An Interactive System for Automatic Machine Learning Model Building and Curation
• Out of Context: Investigating the Bias and Fairness Concerns of "Artificial Intelligence as a Service"
• What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspective
• Algorithmic Decision Making with Conditional Fairness
• A General Framework for Fair Regression
• Avoiding Disparity Amplification under Different Worldviews
• Fairness in Agreement With European Values: An Interdisciplinary Perspective on AI Regulation
• FairOD: Fairness-aware Outlier Detection
• Enforcing Group Fairness in Algorithmic Decision Making: Utility Maximization Under Sufficiency
• Runtime Monitoring of Dynamic Fairness Properties
• FairBalance: How to Achieve Equalized Odds With Data Pre-processing
• Measuring the effects of confounders in medical supervised classification problems: the Confounding Index (CI)
• Fairness Implications of Encoding Protected Categorical Attributes
• Removing the influence of a group variable in high-dimensional predictive modelling
• Disparate Impact Diminishes Consumer Trust Even for Advantaged Users
• Towards Fairness in Personalized Ads Using Impression Variance Aware Reinforcement Learning
• Empirical observation of negligible fairness-accuracy trade-offs in machine learning for public policy
• Joint Fairness Model with Applications to Risk Predictions for Under-represented Populations
• Towards Logical Specification of Statistical Machine Learning
• Disentangled Representation with Causal Constraints for Counterfactual Fairness
• A Framework for Designing Fair Ubiquitous Computing Systems
• Don't Throw it Away! The Utility of Unlabeled Data in Fair Decision Making
• FairIF: Boosting Fairness in Deep Learning via Influence Functions with Validation Set Sensitive Attributes
• Evaluating the Fairness of Discriminative Foundation Models in Computer Vision
• An Epistemic Approach to the Formal Specification of Statistical Machine Learning
• Fairness in Multi-Task Learning via Wasserstein Barycenters
• RecRec: Algorithmic Recourse for Recommender Systems
• A Ranking Approach to Fair Classification
• MAPPING: Debiasing Graph Neural Networks for Fair Node Classification with Limited Sensitive Information Leakage
• Formalising Anti-Discrimination Law in Automated Decision Systems
• Improving Fairness in Adaptive Social Exergames via Shapley Bandits
• Fair Inputs and Fair Outputs: The Incompatibility of Fairness in Privacy and Accuracy
• Long-Term Fairness in Sequential Multi-Agent Selection with Positive Reinforcement
• Convex Fairness Constrained Model Using Causal Effect Estimators
• Fairness in KI-Systemen
• On the Impact of Data Quality on Image Classification Fairness
• A Canonical Data Transformation for Achieving Inter- and Within-group Fairness
• Fairness-aware Federated Minimax Optimization with Convergence Guarantee
• Learning from Discriminatory Training Data
• (Un)certainty of (Un)fairness: Preference-Based Selection of Certainly Fair Decision-Makers
• Algorithmic Fairness Datasets: the Story so Far
• Oh the Prices You'll See: Designing a Fair Exchange System to Mitigate Personalized Pricing