arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.11295cs.LGcs.CCcs.CYcs.DMcs.DS
收藏

森林中的公平相关聚类

Fair Correlation Clustering in Forests

Humboldt University of Berlin(柏林洪堡大学);Hasso Plattner Institute, University of Potsdam(波茨坦大学哈索·普拉特纳研究所);University of Vienna(维也纳大学)

Katrin Casel, Tobias Friedrich, Martin Schirneck, Simon Wietheger

摘要:

算法公平性的研究近年来受到越来越多的关注。这源于人们意识到,机器学习系统的输入数据中的偏差可能导致歧视性输出。对于聚类任务,公平性的最核心概念之一是Chierichetti,Kumar,Lattanzi和Vassilvitskii的形式化[NeurIPS 2017]。如果每个聚类具有与整个输入集相同的敏感属性的表现分布,则聚类被称为公平的。这是由各种应用程序所激发的,其中要聚类的对象具有不应过度表示或表示不足的敏感属性。我们讨论了这种公平的概念相关聚类的适用性。现有的文献所产生的公平相关聚类问题要么提出近似算法与穷人的近似保证或严重限制可能的敏感属性的分布(往往只有两种表现形式与1:1的比例被认为)。我们的目标是了解在这两个极端之间是否有希望获得更好的结果。为此,我们考虑限制图形类,使我们能够描述敏感属性的分布,这种形式的公平性是从复杂性的角度来看,易于处理。虽然现有的工作公平相关聚类给出了近似算法,我们专注于精确的解决方案,并调查是否有有效的可解决的情况。相关聚类的不公平版本在森林中是微不足道的,但增加公平性会产生令人惊讶的丰富复杂性。我们概述了公平相关聚类从易处理到难处理的森林的分布和类型。最令人惊讶的是,公平相关聚类困难的原因并不是公平条件的严格性。

英文摘要:

The study of algorithmic fairness received growing attention recently. This stems from the awareness that bias in the input data for machine learning systems may result in discriminatory outputs. For clustering tasks, one of the most central notions of fairness is the formalization by Chierichetti, Kumar, Lattanzi, and Vassilvitskii [NeurIPS 2017]. A clustering is said to be fair, if each cluster has the same distribution of manifestations of a sensitive attribute as the whole input set. This is motivated by various applications where the objects to be clustered have sensitive attributes that should not be over- or underrepresented. We discuss the applicability of this fairness notion to Correlation Clustering. The existing literature on the resulting Fair Correlation Clustering problem either presents approximation algorithms with poor approximation guarantees or severely limits the possible distributions of the sensitive attribute (often only two manifestations with a 1:1 ratio are considered). Our goal is to understand if there is hope for better results in between these two extremes. To this end, we consider restricted graph classes which allow us to characterize the distributions of sensitive attributes for which this form of fairness is tractable from a complexity point of view. While existing work on Fair Correlation Clustering gives approximation algorithms, we focus on exact solutions and investigate whether there are efficiently solvable instances. The unfair version of Correlation Clustering is trivial on forests, but adding fairness creates a surprisingly rich picture of complexities. We give an overview of the distributions and types of forests where Fair Correlation Clustering turns from tractable to intractable. The most surprising insight to us is the fact that the cause of the hardness of Fair Correlation Clustering is not the strictness of the fairness condition.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑