arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.01096cs.LG
收藏

斜决策树的反事实推理:精确有效的算法

Counterfactual Explanations for Oblique Decision Trees: Exact, Efficient Algorithms

University of California, Merced(加州大学默塞德分校)

Miguel Á. Carreira-Perpiñán, Suryabhan Singh Hada

摘要:

我们考虑反事实的解释,最低限度地调整源输入实例中的功能,使其被归类为一个给定的分类器下的目标类的问题。这已经成为最近感兴趣的话题,作为查询训练模型并建议可能的行动来推翻其决定的一种方式。从数学上讲,这个问题在形式上等价于寻找对抗性例子,这也是最近引起广泛关注的问题。大多数关于反事实解释或对抗性例子的工作都集中在可区分的分类器上,比如神经网络。我们专注于分类树,轴对齐和倾斜(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,我们表明,精确的解决方案可以非常有效地计算,即使是高维特征向量和连续和分类特征,并证明它在不同的数据集和设置。这些结果与金融、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。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑