On the (Complete) Reasons Behind Decisions
On the (Complete) Reasons Behind Decisions
复制标题
DOI：
10.1007/s10849-022-09377-8
复制
发表时间：
2022-08-18
影响因子：
0.8
通讯作者：
Hirth, Auguste
中科院分区：
文献类型：
--
作者：
Darwiche, Adnan;Hirth, Auguste
最近的工作表明，一些常见的机器学习分类器的输入输出行为可以以符号形式捕获，允许人们使用符号技术来推理这些分类器的行为。这包括解释决策，测量鲁棒性，并通过推理相应的符号分类器来证明机器学习分类器的形式属性。在这项工作中，我们提出了一个理论，揭示了布尔分类器的决策背后的原因，并研究了它的一些理论和实践意义。我们的理论的核心是一个完整的理由的概念，这可以被视为一个必要和充分的条件，为什么作出决定。我们展示了如何完整的原因可以用于计算的概念，如充分的理由（也被称为PI解释和溯因解释），它如何可以用于确定决策和分类器的偏见，以及它如何可以用于评估反事实的陈述，如“一个决定将坚持，即使...因为... .“我们提出了一个线性时间算法，用于计算决策背后的完整推理，假设分类器由适当形式的布尔电路表示。然后，我们将展示如何计算的完整的原因可以用来回答许多查询的决定在线性或多项式时间。最后，我们以一个案例研究来总结，该案例研究说明了我们介绍的各种概念和技术。
Recent work has shown that the input-output behavior of some common machine learning classifiers can be captured in symbolic form, allowing one to reason about the behavior of these classifiers using symbolic techniques. This includes explaining decisions, measuring robustness, and proving formal properties of machine learning classifiers by reasoning about the corresponding symbolic classifiers. In this work, we present a theory for unveiling the reasons behind the decisions made by Boolean classifiers and study some of its theoretical and practical implications. At the core of our theory is the notion of a complete reason, which can be viewed as a necessary and sufficient condition for why a decision was made. We show how the complete reason can be used for computing notions such as sufficient reasons (also known as PI-explanations and abductive explanations), how it can be used for determining decision and classifier bias and how it can be used for evaluating counterfactual statements such as "a decision will stick even if ...because ... ." We present a linear-time algorithm for computing the complete reasoning behind a decision, assuming the classifier is represented by a Boolean circuit of appropriate form. We then show how the computed complete reason can be used to answer many queries about a decision in linear or polynomial time. We finally conclude with a case study that illustrates the various notions and techniques we introduced.