Equal Experience in Recommender Systems

TL;DR

This paper introduces a new fairness concept called 'equal experience' for recommender systems, aiming to reduce bias across groups while maintaining recommendation quality, through an optimization framework and efficient algorithms.

Contribution

The paper proposes a novel fairness notion for recommender systems and develops an optimization framework with algorithms to mitigate bias caused by data stereotypes.

Findings

Reduces unfairness in recommendations across groups

Maintains recommendation accuracy with minor degradation

Effective on synthetic and real datasets

Abstract

We explore the fairness issue that arises in recommender systems. Biased data due to inherent stereotypes of particular groups (e.g., male students' average rating on mathematics is often higher than that on humanities, and vice versa for females) may yield a limited scope of suggested items to a certain group of users. Our main contribution lies in the introduction of a novel fairness notion (that we call equal experience), which can serve to regulate such unfairness in the presence of biased data. The notion captures the degree of the equal experience of item recommendations across distinct groups. We propose an optimization framework that incorporates the fairness notion as a regularization term, as well as introduce computationally-efficient algorithms that solve the optimization. Experiments on synthetic and benchmark real datasets demonstrate that the proposed framework can indeed mitigate such unfairness while exhibiting a minor degradation of recommendation accuracy.