Learning Models for Actionable Recourse
Learning Models for Actionable Recourse
复制标题
DOI：
--
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
Alexis Ross;Himabindu Lakkaraju;O. Bastani
中科院分区：
文献类型：
--
作者：
Alexis Ross;Himabindu Lakkaraju;O. Bastani
随着机器学习模型越来越多地部署在法律和财务决策等高风险领域中，人们对事后方法的产生反事实解释的兴趣越来越大。这种解释为个人提供了对预测结果（例如，申请人拒绝贷款）的不利影响，并以追索权的描述描述了他们如何改变自己的特征以获得积极的结果。我们提出了一种新颖的算法，该算法利用对抗性训练和PAC信心设定了学习模型，从理论上讲，从理论上保证求助于受影响的人，而没有牺牲准确性。我们通过对真实数据进行的广泛实验来证明方法的功效。
As machine learning models are increasingly deployed in high-stakes domains such as legal and financial decision-making, there has been growing interest in post-hoc methods for generating counterfactual explanations. Such explanations provide individuals adversely impacted by predicted outcomes (e.g., an applicant denied a loan) with recourse -- i.e., a description of how they can change their features to obtain a positive outcome. We propose a novel algorithm that leverages adversarial training and PAC confidence sets to learn models that theoretically guarantee recourse to affected individuals with high probability without sacrificing accuracy. We demonstrate the efficacy of our approach via extensive experiments on real data.