arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.05266cs.AI
收藏

论决策树的解释力

On the Explanatory Power of Decision Trees

CRIL, Université d’Artois & CNRS, France(阿尔图瓦大学CRIL实验室与法国国家科学研究中心);Institut Universitaire de France(法国大学研究院)

Gilles Audemard, Steve Bellart, Louenas Bounia, Frédéric Koriche, Jean-Marie Lagniez, Pierre Marquis

摘要:

决策树长期以来被认为是敏感应用中的首选模型,其中可解释性至关重要。在本文中,我们研究了布尔决策树的计算能力,在推导,最小化,并计数充分的理由和对比解释。我们证明了一个决策树的实例的最小尺寸的所有充分理由的集合可以指数大于输入(实例和决策树)的大小。因此,生成全套充分理由可能是遥不可及的。此外,计算一个充分的理由通常是不够的;事实上,同一个实例的两个充分的理由可能在许多特征上有所不同。为了处理这个问题,并生成合成视图的所有充分的理由,我们引入的概念,相关的功能和必要的功能,表征(可能否定)的功能出现在至少一个或在每个充分的理由,我们表明,它们可以计算在多项式时间。我们还介绍了解释的重要性的概念,这表明如何频繁的每个(可能否定)功能是在所有充分的理由。我们展示了如何解释的重要性的一个功能和足够的理由的数量可以通过一个模型计数操作,这在许多情况下是实际的。我们还解释了如何枚举最小尺寸的充分理由。我们最后表明,不同于充分的理由,一个实例的所有对比解释的决策树的集合可以导出,最小化和计数在多项式时间。

英文摘要:

Decision trees have long been recognized as models of choice in sensitive applications where interpretability is of paramount importance. In this paper, we examine the computational ability of Boolean decision trees in deriving, minimizing, and counting sufficient reasons and contrastive explanations. We prove that the set of all sufficient reasons of minimal size for an instance given a decision tree can be exponentially larger than the size of the input (the instance and the decision tree). Therefore, generating the full set of sufficient reasons can be out of reach. In addition, computing a single sufficient reason does not prove enough in general; indeed, two sufficient reasons for the same instance may differ on many features. To deal with this issue and generate synthetic views of the set of all sufficient reasons, we introduce the notions of relevant features and of necessary features that characterize the (possibly negated) features appearing in at least one or in every sufficient reason, and we show that they can be computed in polynomial time. We also introduce the notion of explanatory importance, that indicates how frequent each (possibly negated) feature is in the set of all sufficient reasons. We show how the explanatory importance of a feature and the number of sufficient reasons can be obtained via a model counting operation, which turns out to be practical in many cases. We also explain how to enumerate sufficient reasons of minimal size. We finally show that, unlike sufficient reasons, the set of all contrastive explanations for an instance given a decision tree can be derived, minimized and counted in polynomial time.

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。

↑