On Formalizing Fairness in Prediction with Machine Learning

Abstract

Machine learning algorithms for prediction are increasingly being used in critical decisions affecting human lives. Various fairness formalizations, with no firm consensus yet, are employed to prevent such algorithms from systematically discriminating against people based on certain attributes protected by law. The aim of this article is to survey how fairness is formalized in the machine learning literature for the task of prediction and present these formalizations with their corresponding notions of distributive justice from the social sciences literature. We provide theoretical as well as empirical critiques of these notions from the social sciences literature and explain how these critiques limit the suitability of the corresponding fairness formalizations to certain domains. We also suggest two notions of distributive justice which address some of these critiques and discuss avenues for prospective fairness formalizations.

References in corpus (2)

• Equality of Opportunity in Supervised Learning
• Counterfactual Fairness

Cited by in corpus (44)

• Fairness in Machine Learning
• Fairness in Credit Scoring: Assessment, Implementation and Profit Implications
• Machine Learning Testing: Survey, Landscapes and Horizons
• Compositional Fairness Constraints for Graph Embeddings
• A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle
• Machine learning fairness notions: Bridging the gap with real-world applications
• Towards Equity and Algorithmic Fairness in Student Grade Prediction
• How Do Fairness Definitions Fare? Examining Public Attitudes Towards Algorithmic Definitions of Fairness
• Can Explainable AI Explain Unfairness? A Framework for Evaluating Explainable AI
• Mathematical Notions vs. Human Perception of Fairness: A Descriptive Approach to Fairness for Machine Learning
• End-To-End Bias Mitigation: Removing Gender Bias in Deep Learning
• Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation
• Measuring justice in machine learning
• Understanding Agent Incentives using Causal Influence Diagrams. Part I: Single Action Settings
• Properties of fairness measures in the context of varying class imbalance and protected group ratios
• Learning Fair and Transferable Representations
• Towards Logical Specification of Statistical Machine Learning
• Fairness in Forecasting and Learning Linear Dynamical Systems
• Statistical Equity: A Fairness Classification Objective
• Evaluating the Fairness of Discriminative Foundation Models in Computer Vision
• Data and Model Dependencies of Membership Inference Attack
• Exploring User Opinions of Fairness in Recommender Systems
• Designing Evaluations of Machine Learning Models for Subjective Inference: The Case of Sentence Toxicity
• Fairness in Forecasting of Observations of Linear Dynamical Systems
• The Future AI in Healthcare: A Tsunami of False Alarms or a Product of Experts?
• Fairness with Continuous Optimal Transport
• Distributive Justice and Fairness Metrics in Automated Decision-making: How Much Overlap Is There?
• User Acceptance of Gender Stereotypes in Automated Career Recommendations
• Technologies for Trustworthy Machine Learning: A Survey in a Socio-Technical Context
• Towards a Measure of Individual Fairness for Deep Learning
• Fairness in Deep Learning: A Computational Perspective
• Pooling of Causal Models under Counterfactual Fairness via Causal Judgement Aggregation
• The invisible power of fairness. How machine learning shapes democracy
• Metric-Free Individual Fairness with Cooperative Contextual Bandits
• An example of prediction which complies with Demographic Parity and equalizes group-wise risks in the context of regression
• Statistical discrimination in learning agents
• Equality of opportunity in travel behavior prediction with deep neural networks and discrete choice models
• A Unified Approach to Fair Online Learning via Blackwell Approachability
• Meta Clustering for Collaborative Learning
• Recommendation or Discrimination?: Quantifying Distribution Parity in Information Retrieval Systems
• Fairness constraints can help exact inference in structured prediction
• A Novel Information-Theoretic Objective to Disentangle Representations for Fair Classification
• Counterfactually Fair Prediction Using Multiple Causal Models
• Unfairness towards subjective opinions in Machine Learning