A high-velocity paradigm shift towards Explainable Artificial Intelligence
(XAI) has emerged in recent years. Highly complex Machine Learning (ML) models
have flourished in many tasks of intelligence, and the questions have started
to shift away from traditional metrics of validity towards something deeper:
What is this model telling me about my data, and how is it arriving at these
conclusions? Inconsistencies between XAI and modeling techniques can have the
undesirable effect of casting doubt upon the efficacy of these explainability
approaches. To address these problems, we propose a systematic,
perturbation-based analysis against a popular, model-agnostic method in XAI,
SHapley Additive exPlanations (Shap). We devise algorithms to generate relative
feature importance in settings of dynamic inference amongst a suite of popular
machine learning and deep learning methods, and metrics that allow us to
quantify how well explanations generated under the static case hold. We propose
a taxonomy for feature importance methodology, measure alignment, and observe
quantifiable similarity amongst explanation models across several datasets.

面向可解释人工智能（XAI）的高速范式转变已在近年来出现。高度复杂的机器学习（ML）模型在许多智能任务中蓬勃发展，而问题开始从传统的有效性度量转向更深层次的问题：该模型告诉我关于我的数据什么，它是如何得出这些结论的？XAI 和建模技术之间的不一致可能对这些解释性方法的效力产生质疑。为了解决这些问题，我们提出了一种针对流行的 XAI 的模型不可知方法 SHapley Additive exPlanations（Shap）进行系统的扰动分析。我们设计了一些算法，在动态推理的设置下生成相对特征重要性，这些设置针对一套流行的机器学习和深度学习方法，以及允许我们量化静态情况下生成解释的质量的度量指标。我们提出了特征重要性方法论的分类体系，度量了一致性，并观察了几个数据集中解释模型之间的可量化相似性。