An Algorithmic Framework for Fairness Elicitation
An Algorithmic Framework for Fairness Elicitation
复制标题
DOI：
10.4230/lipics.forc.2021.2
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
Christopher Jung;Michael Kearns;Seth Neel;Aaron Roth;Logan Stapleton;Zhiwei Steven Wu
中科院分区：
文献类型：
--
作者：
Christopher Jung;Michael Kearns;Seth Neel;Aaron Roth;Logan Stapleton;Zhiwei Steven Wu
我们考虑的设置中，正确的公平概念是不是简单的数学定义（如各组之间的错误率平等），但可能更复杂和微妙的，因此需要从个人或集体利益相关者的启发。我们引入了一个框架，在这个框架中，成对的个人可以被确定为需要（近似）平等的待遇下的学习模型，或需要有序的治疗，如“申请人爱丽丝应该至少有可能获得贷款申请人鲍勃”。我们提供了一个可证明收敛和预言机有效的算法，学习最准确的模型受到公平性的约束，并证明泛化的准确性和公平性的界限。该算法还可以联合收割机传统的统计公平性的概念，从而“纠正”或修改后者由前者引发的约束。我们报告的行为研究的初步结果，我们的框架，使用人类主体的公平约束引起的COMPAS刑事累犯数据集。
We consider settings in which the right notion of fairness is not captured by simple mathematical definitions (such as equality of error rates across groups), but might be more complex and nuanced and thus require elicitation from individual or collective stakeholders. We introduce a framework in which pairs of individuals can be identified as requiring (approximately) equal treatment under a learned model, or requiring ordered treatment such as "applicant Alice should be at least as likely to receive a loan as applicant Bob". We provide a provably convergent and oracle efficient algorithm for learning the most accurate model subject to the elicited fairness constraints, and prove generalization bounds for both accuracy and fairness. This algorithm can also combine the elicited constraints with traditional statistical fairness notions, thus "correcting" or modifying the latter by the former. We report preliminary findings of a behavioral study of our framework using human-subject fairness constraints elicited on the COMPAS criminal recidivism dataset.