arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.06146cs.LGcs.AI
收藏

可操作追索权的学习模型

Learning Models for Actionable Recourse

Harvard University(哈佛大学);Allen Institute for Artificial Intelligence(艾伦人工智能研究所);University of Pennsylvania(宾夕法尼亚大学)

Alexis Ross, Himabindu Lakkaraju, Osbert Bastani

摘要:

随着机器学习模型越来越多地部署在法律和金融决策等高风险领域,人们对用于生成反事实解释的事后方法越来越感兴趣。这些解释为受到预测结果不利影响的个人提供了帮助(例如,申请人拒绝贷款)有追索权--即,描述他们如何改变自己的特征以获得积极的结果。我们提出了一种新的算法,该算法利用对抗训练和PAC置信集来学习模型,理论上保证在不牺牲准确性的情况下以高概率求助于受影响的个体。我们证明了我们的方法的有效性,通过大量的实验真实数据。

英文摘要:

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.

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。

↑