iFair: Learning Individually Fair Data Representations for Algorithmic Decision Making
iFair: Learning Individually Fair Data Representations for Algorithmic Decision Making
复制标题
iFair：学习用于算法决策的单独公平数据表示
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
K. Gummadi
中科院分区：
文献类型：
--
作者：
Preethi Lahoti;G. Weikum;K. Gummadi
在越来越多的应用程序中，人们对算法决策进行评级和排名，这些应用程序通常基于机器学习。关于如何将公平纳入这些任务的研究普遍追求群体公平的范式：给予特定受保护群体足够的成功率。相比之下，个人公平的替代范式受到的关注相对较少，本文提出了这一较少探索的方向。本文介绍了一种将用户记录概率映射为低秩表示的方法，该方法协调了个体公平性和下游应用中分类器和排序的效用。我们的个人公平概念要求用户在所有任务相关属性（如工作资格）上相似，并且忽略所有潜在的歧视属性（如性别），应该有相似的结果。我们通过将其应用于各种现实世界数据集上的分类和学习排序任务来展示我们方法的多功能性。我们的实验表明，在此设置下，与最佳的先前工作相比，有了实质性的改进。
People are rated and ranked, towards algorithmic decision making in an increasing number of applications, typically based on machine learning. Research on how to incorporate fairness into such tasks has prevalently pursued the paradigm of group fairness: giving adequate success rates to specifically protected groups. In contrast, the alternative paradigm of individual fairness has received relatively little attention, and this paper advances this less explored direction. The paper introduces a method for probabilistically mapping user records into a lowrank representation that reconciles individual fairness and the utility of classifiers and rankings in downstream applications. Our notion of individual fairness requires that users who are similar in all task-relevant attributes such as job qualification, and disregarding all potentially discriminating attributes such as gender, should have similar outcomes. We demonstrate the versatility of our method by applying it to classification and learning-to-rank tasks on a variety of real-world datasets. Our experiments show substantial improvements over the best prior work for this setting.