论文标题
上下文重要性和实用性：理论基础
Contextual Importance and Utility: aTheoretical Foundation
论文作者
论文摘要
本文提供了新的理论，以支持可解释的AI（XAI）方法上下文重要性和效用（CIU）。 CIU算术基于多属性效用理论的概念，该理论为CIU提供了坚实的理论基础。还定义了上下文影响的新颖概念，这使得可以将CIU与所谓的添加剂特征归因（AFA）方法进行比较，以解释模型 - 不合稳定结果解释。一个关键的要点是，AFA方法使用的“影响”概念甚至是为了解释简单模型的结果解释目的。简单模型的实验表明，使用上下文重要性（CI）和上下文效用（CU）的解释产生了解释，其中基于影响力的方法失败。还表明，CI和CU保证对解释模型的解释忠实。
This paper provides new theory to support to the eXplainable AI (XAI) method Contextual Importance and Utility (CIU). CIU arithmetic is based on the concepts of Multi-Attribute Utility Theory, which gives CIU a solid theoretical foundation. The novel concept of contextual influence is also defined, which makes it possible to compare CIU directly with so-called additive feature attribution (AFA) methods for model-agnostic outcome explanation. One key takeaway is that the "influence" concept used by AFA methods is inadequate for outcome explanation purposes even for simple models to explain. Experiments with simple models show that explanations using contextual importance (CI) and contextual utility (CU) produce explanations where influence-based methods fail. It is also shown that CI and CU guarantees explanation faithfulness towards the explained model.
