Fairness in Ranking, Part II: Learning-to-Rank and Recommender Systems
Fairness in Ranking, Part II: Learning-to-Rank and Recommender Systems
复制标题
DOI：
10.1145/3533380
复制
发表时间：
2022-05
影响因子：
16.6
通讯作者：
Meike Zehlike;Ke Yang;Julia Stoyanovich
中科院分区：
文献类型：
--
作者：
Meike Zehlike;Ke Yang;Julia Stoyanovich
在过去的几年里，已经有很多工作将公平性要求纳入算法排名，贡献来自数据管理，算法，信息检索和推荐系统社区。在这项调查中，我们对这项工作进行了系统的概述，提供了一个广泛的视角，将形式化和算法方法跨子领域联系起来。我们工作的一个重要贡献是围绕价值框架制定一个共同的叙述，这些框架激励排名中具体的公平性增强干预措施。这使我们能够统一介绍缓解目标和算法技术，以帮助实现这些目标或确定权衡。在本调查的第一部分，我们描述了四个分类框架的公平性增强的干预措施，沿着，我们在这篇文章中调查的技术方法，讨论评估数据集，并提出技术工作的公平性评分为基础的排名。在本调查的第二部分中，我们提出了在监督学习中引入公平性的方法，并给出了最近在推荐和匹配系统中公平性方面工作的代表性例子。我们还讨论了公平分数为基础的排名和公平的学习排名的评估框架，并得出了一套公平排名方法的评估建议。
In the past few years, there has been much work on incorporating fairness requirements into algorithmic rankers, with contributions coming from the data management, algorithms, information retrieval, and recommender systems communities. In this survey, we give a systematic overview of this work, offering a broad perspective that connects formalizations and algorithmic approaches across subfields. An important contribution of our work is in developing a common narrative around the value frameworks that motivate specific fairness-enhancing interventions in ranking. This allows us to unify the presentation of mitigation objectives and of algorithmic techniques to help meet those objectives or identify trade-offs. In the first part of this survey, we describe four classification frameworks for fairness-enhancing interventions, along which we relate the technical methods surveyed in this article, discuss evaluation datasets, and present technical work on fairness in score-based ranking. In the second part of this survey, we present methods that incorporate fairness in supervised learning, and also give representative examples of recent work on fairness in recommendation and matchmaking systems. We also discuss evaluation frameworks for fair score-based ranking and fair learning-to-rank, and draw a set of recommendations for the evaluation of fair ranking methods.