"And the Winner Is...": Dynamic Lotteries for Multi-group Fairness-Aware Recommendation

Abstract

As recommender systems are being designed and deployed for an increasing number of socially-consequential applications, it has become important to consider what properties of fairness these systems exhibit. There has been considerable research on recommendation fairness. However, we argue that the previous literature has been based on simple, uniform and often uni-dimensional notions of fairness assumptions that do not recognize the real-world complexities of fairness-aware applications. In this paper, we explicitly represent the design decisions that enter into the trade-off between accuracy and fairness across multiply-defined and intersecting protected groups, supporting multiple fairness metrics. The framework also allows the recommender to adjust its performance based on the historical view of recommendations that have been delivered over a time horizon, dynamically rebalancing between fairness concerns. Within this framework, we formulate lottery-based mechanisms for choosing between fairness concerns, and demonstrate their performance in two recommendation domains.

References in corpus (7)

• Equality of Opportunity in Supervised Learning
• Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness
• Multisided Fairness for Recommendation
• Personalizing Fairness-aware Re-ranking
• The Conference Paper Assignment Problem: Using Order Weighted Averages to Assign Indivisible Goods
• Egalitarianism of Random Assignment Mechanisms
• Equilibria Under the Probabilistic Serial Rule

Cited by in corpus (1)

• FairFML: Fair Federated Machine Learning with a Case Study on Reducing Gender Disparities in Cardiac Arrest Outcome Prediction