Pareto Pairwise Ranking for Fairness Enhancement of Recommender Systems
This addresses fairness issues in recommender systems for users, though it is incremental as it builds on existing ranking methods.
The paper tackles the problem of fairness in recommender systems by proposing Pareto Pairwise Ranking, a new learning-to-rank algorithm that is competitive on accuracy metrics and demonstrated to be the most fair compared to 9 other algorithms.
Learning to rank is an effective recommendation approach since its introduction around 2010. Famous algorithms such as Bayesian Personalized Ranking and Collaborative Less is More Filtering have left deep impact in both academia and industry. However, most learning to rank approaches focus on improving technical accuracy metrics such as AUC, MRR and NDCG. Other evaluation metrics of recommender systems like fairness have been largely overlooked until in recent years. In this paper, we propose a new learning to rank algorithm named Pareto Pairwise Ranking. We are inspired by the idea of Bayesian Personalized Ranking and power law distribution. We show that our algorithm is competitive with other algorithms when evaluated on technical accuracy metrics. What is more important, in our experiment section we demonstrate that Pareto Pairwise Ranking is the most fair algorithm in comparison with 9 other contemporary algorithms.