Counterfactual Explanations for Oblique Decision Trees: Exact, Efficient Algorithms
Counterfactual Explanations for Oblique Decision Trees: Exact, Efficient Algorithms
复制标题
倾斜决策树的反事实解释：精确、高效的算法
DOI：
10.1609/aaai.v35i8.16851
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Suryabhan Singh Hada
中科院分区：
文献类型：
--
作者：
Miguel 'A. Carreira;Suryabhan Singh Hada
我们考虑反事实解释，即最小限度地调整源输入实例中的特征，以便在给定分类器下将其分类为目标类的问题。作为一种查询训练模型并提出可能的行动来推翻其决定的方法，这已经成为最近感兴趣的话题。在数学上，这个问题在形式上等同于寻找对抗性例子的问题，后者最近也引起了极大的关注。大多数关于反事实解释或对抗性示例的工作都集中在可微分分类器上，例如神经网络。我们专注于分类树，包括轴向和斜向（具有超平面分裂）。虽然这里的反事实优化问题是非凸和不可微的，但我们证明了精确解可以非常有效地计算，即使使用高维特征向量和连续和分类特征，并在不同的数据集和设置中证明了这一点。研究结果与金融、医学或法律应用特别相关，在这些领域，可解释性和反事实解释尤为重要。
We consider counterfactual explanations, the problem of minimally adjusting features in a source input instance so that it is classified as a target class under a given classifier. This has become a topic of recent interest as a way to query a trained model and suggest possible actions to overturn its decision. Mathematically, the problem is formally equivalent to that of finding adversarial examples, which also has attracted significant attention recently. Most work on either counterfactual explanations or adversarial examples has focused on differentiable classifiers, such as neural nets. We focus on classification trees, both axis-aligned and oblique (having hyperplane splits). Although here the counterfactual optimization problem is nonconvex and nondifferentiable, we show that an exact solution can be computed very efficiently, even with high-dimensional feature vectors and with both continuous and categorical features, and demonstrate it in different datasets and settings. The results are particularly relevant for finance, medicine or legal applications, where interpretability and counterfactual explanations are particularly important.