作者
Solon Barocas, Andrew Selbst, Manish Raghavan
发表日期
2020
研讨会论文
Conference on Fairness, Accountability, and Transparency (FAccT)
简介
Counterfactual explanations are gaining prominence within technical, legal, and business circles as a way to explain the decisions of a machine learning model. These explanations share a trait with the long-established "principal reason" explanations required by U.S. credit laws: they both explain a decision by highlighting a set of features deemed most relevant---and withholding others.
These "feature-highlighting explanations" have several desirable properties: They place no constraints on model complexity, do not require model disclosure, detail what needed to be different to achieve a different decision, and seem to automate compliance with the law. But they are far more complex and subjective than they appear.
In this paper, we demonstrate that the utility of feature-highlighting explanations relies on a number of easily overlooked assumptions: that the recommended change in feature values clearly maps to …
学术搜索中的文章
S Barocas, AD Selbst, M Raghavan - Proceedings of the 2020 conference on fairness …, 2020
S Barocas, D Andrew - … counterfactual explanations and principal reasons.” In …, 2020
S Barocas, AD Selbst, M Raghavan - 2020
S Barocas, D Andrew - … counterfactual explanations and principal reasons.” In …