论文标题
Xaudit：对审核的理论审核
XAudit : A Theoretical Look at Auditing with Explanations
论文作者
论文摘要
负责使用机器学习需要对不良属性进行审核。尽管一大批作品提出了使用解释进行审计，但如何做到这一点，以及为什么仍然相对不了解。这项工作正式化了解释在审核中的作用，并调查了模型解释是否以及如何帮助审核。具体而言，我们提出了基于解释的算法，用于审核线性分类器和决策树以提高功能敏感性。我们的结果表明，反事实解释对审核非常有帮助。尽管在最坏的情况下，锚定和决策路径可能并不那么有益，但在平均案例中，它们确实有很多帮助。
Responsible use of machine learning requires models to be audited for undesirable properties. While a body of work has proposed using explanations for auditing, how to do so and why has remained relatively ill-understood. This work formalizes the role of explanations in auditing and investigates if and how model explanations can help audits. Specifically, we propose explanation-based algorithms for auditing linear classifiers and decision trees for feature sensitivity. Our results illustrate that Counterfactual explanations are extremely helpful for auditing. While Anchors and decision paths may not be as beneficial in the worst-case, in the average-case they do aid a lot.
