Learning Model-Agnostic Counterfactual Explanations for Tabular Data
Learning Model-Agnostic Counterfactual Explanations for Tabular Data
复制标题
DOI：
10.1145/3366423.3380087
复制
发表时间：
2019-10
期刊：
影响因子：
--
通讯作者：
Martin Pawelczyk;Klaus Broelemann;Gjergji Kasneci
中科院分区：
文献类型：
--
作者：
Martin Pawelczyk;Klaus Broelemann;Gjergji Kasneci
反事实解释可以通过识别输入向量的最小变化来获得，从而从用户的角度以积极的方式影响预测；例如，从“拒绝贷款”到“获得贷款”，或从“心血管疾病高风险”到“低风险”。以前的方法不能确保产生的反事实是近似的（即，不是局部异常值），并与具有大量数据密度的区域（即，接近正确分类的观测值）相连，这两个要求被称为反事实忠实度。我们的贡献是双重的。首先，从多种学习文献中汲取思想，我们开发了一个名为C-CHVAE的框架，该框架生成忠实的反事实。其次，我们建议使用一个标准来量化某个反事实建议的难易程度，以补充反事实质量度量的目录。我们的现实世界实验表明，忠实的反事实是以更高的难度为代价的。
Counterfactual explanations can be obtained by identifying the smallest change made to an input vector to influence a prediction in a positive way from a user’s viewpoint; for example, from ’loan rejected’ to ’awarded’ or from ’high risk of cardiovascular disease’ to ’low risk’. Previous approaches would not ensure that the produced counterfactuals be proximate (i.e., not local outliers) and connected to regions with substantial data density (i.e., close to correctly classified observations), two requirements known as counterfactual faithfulness. Our contribution is twofold. First, drawing ideas from the manifold learning literature, we develop a framework, called C-CHVAE, that generates faithful counterfactuals. Second, we suggest to complement the catalog of counterfactual quality measures using a criterion to quantify the degree of difficulty for a certain counterfactual suggestion. Our real world experiments suggest that faithful counterfactuals come at the cost of higher degrees of difficulty.