The Multisided Complexity of Fairness in Recommender Systems
The Multisided Complexity of Fairness in Recommender Systems
复制标题
DOI：
10.1002/aaai.12054
复制
发表时间：
2022-06
期刊：
影响因子：
--
通讯作者：
Nasim Sonboli;R. Burke;Michael D. Ekstrand;Rishabh Mehrotra
中科院分区：
文献类型：
--
作者：
Nasim Sonboli;R. Burke;Michael D. Ekstrand;Rishabh Mehrotra
推荐系统在利益相关者之间的接口处做好准备：例如，在推荐就业列表的情况下，是求职者和雇主，或者在推荐音乐的情况下，是艺术家和听众。在这种多边平台中，推荐系统在大规模发现产品和信息方面发挥着关键作用。然而，随着它们在社会中变得越来越普遍，它们的利益和危害的公平分配越来越受到审查，就像机器学习一样。虽然推荐系统可以表现出许多在其他机器学习环境中遇到的偏见，但个性化和多面性的交叉使得推荐系统中的公平性问题表现得非常不同。在这篇文章中，我们讨论了最近的工作在推荐中的多边公平性领域，首先简要介绍了算法公平性和多利益相关者推荐的核心思想。我们描述了用于测量公平性的技术和用于增强推荐输出中的公平性的算法方法。我们还讨论了可能导致不公平推荐结果的反馈和流行效应。最后，我们介绍了几个有前途的方向，在这一领域的未来研究。
Recommender systems are poised at the interface between stakeholders: for example, job applicants and employers in the case of recommendations of employment listings, or artists and listeners in the case of music recommendation. In such multisided platforms, recommender systems play a key role in enabling discovery of products and information at large scales. However, as they have become more and more pervasive in society, the equitable distribution of their benefits and harms have been increasingly under scrutiny, as is the case with machine learning generally. While recommender systems can exhibit many of the biases encountered in other machine learning settings, the intersection of personalization and multisidedness makes the question of fairness in recommender systems manifest itself quite differently. In this article, we discuss recent work in the area of multisided fairness in recommendation, starting with a brief introduction to core ideas in algorithmic fairness and multistakeholder recommendation. We describe techniques for measuring fairness and algorithmic approaches for enhancing fairness in recommendation outputs. We also discuss feedback and popularity effects that can lead to unfair recommendation outcomes. Finally, we introduce several promising directions for future research in this area.