Policy Learning for Fairness in Ranking

Abstract

Conventional Learning-to-Rank (LTR) methods optimize the utility of the rankings to the users, but they are oblivious to their impact on the ranked items. However, there has been a growing understanding that the latter is important to consider for a wide range of ranking applications (e.g. online marketplaces, job placement, admissions). To address this need, we propose a general LTR framework that can optimize a wide range of utility metrics (e.g. NDCG) while satisfying fairness of exposure constraints with respect to the items. This framework expands the class of learnable ranking functions to stochastic ranking policies, which provides a language for rigorously expressing fairness specifications. Furthermore, we provide a new LTR algorithm called Fair-PG-Rank for directly searching the space of fair ranking policies via a policy-gradient approach. Beyond the theoretical evidence in deriving the framework and the algorithm, we provide empirical results on simulated and real-world datasets verifying the effectiveness of the approach in individual and group-fairness settings.

References in corpus (7)

• Equality of Opportunity in Supervised Learning
• Counterfactual Fairness
• Fairness of Exposure in Rankings
• FA*IR: A Fair Top-k Ranking Algorithm
• Designing Fair Ranking Schemes
• On the relation between accuracy and fairness in binary classification
• Intervention Harvesting for Context-Dependent Examination-Bias Estimation

Cited by in corpus (33)

• Fairness in Machine Learning: A Survey
• User-oriented Fairness in Recommendation
• Controlling Fairness and Bias in Dynamic Learning-to-Rank
• Evaluating Stochastic Rankings with Expected Exposure
• Personalized Counterfactual Fairness in Recommendation
• Fairness in Ranking: A Survey
• User Fairness, Item Fairness, and Diversity for Rankings in Two-Sided Markets
• Equality of Learning Opportunity via Individual Fairness in Personalized Recommendations
• Fair Ranking as Fair Division: Impact-Based Individual Fairness in Ranking
• Fairness of Exposure in Light of Incomplete Exposure Estimation
• Understanding and Mitigating the Effect of Outliers in Fair Ranking
• Achieving Fairness in the Stochastic Multi-armed Bandit Problem
• Learning Fair Scoring Functions: Bipartite Ranking under ROC-based Fairness Constraints
• Learning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement Learning
• The Role of Relevance in Fair Ranking
• Probabilistic Permutation Graph Search: Black-Box Optimization for Fairness in Ranking
• Fairness of Exposure in Stochastic Bandits
• Predictive Uncertainty-based Bias Mitigation in Ranking
• Vertical Allocation-based Fair Exposure Amortizing in Ranking
• On the Problem of Underranking in Group-Fair Ranking
• Consequential Ranking Algorithms and Long-term Welfare
• Intersectional Affirmative Action Policies for Top-k Candidates Selection
• Pairwise Fairness for Ranking and Regression
• Fairness Through Counterfactual Utilities
• Fairness Through Regularization for Learning to Rank
• Fairness in Ranking under Uncertainty
• A Pre-processing Method for Fairness in Ranking
• Towards Model-Agnostic Post-Hoc Adjustment for Balancing Ranking Fairness and Algorithm Utility
• Calibrating Explore-Exploit Trade-off for Fair Online Learning to Rank
• On the Fairness of Randomized Trials for Recommendation with Heterogeneous Demographics and Beyond
• Computationally Efficient Optimization of Plackett-Luce Ranking Models for Relevance and Fairness
• Practical Compositional Fairness: Understanding Fairness in Multi-Component Recommender Systems
• Estimating the Hessian Matrix of Ranking Objectives for Stochastic Learning to Rank with Gradient Boosted Trees