Contrastive Explanations with Local Foil Trees
Contrastive Explanations with Local Foil Trees
复制标题
DOI：
--
复制
发表时间：
2018-06
期刊：
影响因子：
--
通讯作者：
J. V. D. Waa;M. Robeer;J. Diggelen;Matthieu J. S. Brinkhuis;Mark Antonius Neerincx
中科院分区：
文献类型：
--
作者：
J. V. D. Waa;M. Robeer;J. Diggelen;Matthieu J. S. Brinkhuis;Mark Antonius Neerincx
可解释机器学习 (iML) 和可解释人工智能 (XAI) 的最新进展根据分类任务中特征的重要性构建解释。然而，在高维特征空间中，如果不限制重要特征集，这种方法可能变得不可行。我们建议利用人类的倾向来提出诸如“为什么是这个输出（事实）而不是那个输出（陪衬）？”之类的问题。将特征数量减少到在要求的对比中起主要作用的特征数量。我们提出的方法利用本地训练的一对多决策树来识别不相交的规则集，这些规则使树将数据点分类为陪衬而不是事实。在本研究中，我们在三个基准分类任务上说明了这种方法。
Recent advances in interpretable Machine Learning (iML) and eXplainable AI (XAI) construct explanations based on the importance of features in classification tasks. However, in a high-dimensional feature space this approach may become unfeasible without restraining the set of important features. We propose to utilize the human tendency to ask questions like "Why this output (the fact) instead of that output (the foil)?" to reduce the number of features to those that play a main role in the asked contrast. Our proposed method utilizes locally trained one-versus-all decision trees to identify the disjoint set of rules that causes the tree to classify data points as the foil and not as the fact. In this study we illustrate this approach on three benchmark classification tasks.