Equi-explanation Maps: Concise and Informative Global Summary Explanations
Equi-explanation Maps: Concise and Informative Global Summary Explanations
复制标题
DOI：
10.1145/3531146.3533112
复制
发表时间：
2022-06
期刊：
影响因子：
--
通讯作者：
Tanya Chowdhury;Razieh Rahimi;J. Allan
中科院分区：
文献类型：
--
作者：
Tanya Chowdhury;Razieh Rahimi;J. Allan
我们试图总结黑盒分类模型的模型逻辑，以便生成简洁和信息丰富的全局解释。我们提出了等解释映射，这是一种新的解释数据结构，它将感兴趣区域表示为等解释子空间及其解释向量的并。然后，我们提出了一种生成等解释地图的方法--E-Map。我们通过在UCI心脏病数据集和PIMA印第安人糖尿病数据集上为各种二进制分类模型(Logistic回归、支持向量机、MLP和XGBoost)生成等解释地图，展示了我们方法的广泛实用性。我们生成的映射中的每个子空间都是d维超长方体的并，为了便于解释，可以紧凑地表示这些超长方体。对于这些子空间中的每一个，我们都给出了线性解释，为每个解释特征分配了一个权重。我们通过从可解释性、保真度和信息性方面进行评估，与其他全球解释方法相比，证明使用等解释地图是合理的。一项用户研究进一步证实了使用等解释地图来生成紧凑和信息丰富的全球解释。
We attempt to summarize the model logic of a black-box classification model in order to generate concise and informative global explanations. We propose equi-explanation maps, a new explanation data-structure that presents the region of interest as a union of equi-explanation subspaces along with their explanation vectors. We then propose E-Map, a method to generate equi-explanation maps. We demonstrate the broad utility of our approach by generating equi-explanation maps for various binary classification models (Logistic Regression, SVM, MLP, and XGBoost) on the UCI Heart disease dataset and the Pima Indians diabetes dataset. Each subspace in our generated map is the union of d-dimensional hyper-cuboids which can be compactly represented for the sake of interpretability. For each of these subspaces, we present linear explanations assigning a weight to each explanation feature. We justify the use of equi-explanation maps in comparison to other global explanation methods by evaluating in terms of interpretability, fidelity, and informativeness. A user study further corroborates the use of equi-explanation maps to generate compact and informative global explanations.