A Fair Top-k Ranking Algorithm
A Fair Top-k Ranking Algorithm
复制标题
公平的Top-k排名算法
DOI：
--
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Ricardo Baeza
中科院分区：
文献类型：
--
作者：
Carlos Castillo Eurecat;Sara Hajian Eurecat;Ricardo Baeza
我们提出了一个正式的问题定义和算法来解决公平的Top-k排名问题。该问题包括创建一个排名的k个元素出池的n k个候选人。目标是最大化效用，最大化受到排名组公平性约束。我们对等级群体公平性的定义使用了保护群体的标准概念来扩展群体公平性的概念。它确保每个前x的排名包含的保护候选人的数量是从一个给定的目标比例，统计上无法区分，或超过它。效用目标有利于排名中的每个候选人都比任何不包括的候选人更有资格，排名中的候选人是按递减的资格排序。我们描述了一个有效的算法，这个问题，这是测试一系列现有的数据集，以及新的数据集。实验上，这种方法产生的排名是类似于所谓的“色盲”的排名，同时尊重公平的标准。据我们所知，FA*IR是基于统计测试的第一个算法，可用于减轻对代表性不足的群体的排名偏见。
We present a formal problem de nition and an algorithm to solve the Fair Top-k Ranking problem. The problem consists of creating a ranking of k elements out of a pool of n k candidates. The objective is to maximize utility, and maximization is subject to a ranked group fairness constraint. Our de nition of ranked group fairness uses the standard notion of protected group to extend the concept of group fairness. It ensures that every pre x of the rank contains a number of protected candidates that is statistically indistinguishable from a given target proportion, or exceeds it. The utility objective favors rankings in which every candidate included in the ranking is more quali ed than any candidate not included, and rankings in which candidates are sorted by decreasing quali cations. We describe an e cient algorithm for this problem, which is tested on a series of existing datasets, as well as new datasets. Experimentally, this approach yields a ranking that is similar to the so-called “color-blind” ranking, while respecting the fairness criteria. To the best of our knowledge, FA*IR is the rst algorithm grounded in statistical tests that can be used to mitigate biases in ranking against an under-represented group.