Explaining individual predictions when features are dependent: More accurate approximations to Shapley values
Explaining individual predictions when features are dependent: More accurate approximations to Shapley values
复制标题
DOI：
10.1016/j.artint.2021.103502
复制
发表时间：
2021-04-19
影响因子：
14.4
通讯作者：
Loland, Anders
中科院分区：
文献类型：
--
作者：
Aas, Kjersti;Jullum, Martin;Loland, Anders
解释复杂或看似简单的机器学习模型是一个重要的实际问题。我们希望通过学习简单、可解释的解释来解释这些模型中的个别预测。Shapley值是一个可以用于此目的的博弈论概念。Shapley Value框架具有一系列理想的理论属性，原则上可以处理任何预测模型。内核形状是更高维度中Shapley值的计算效率近似值。与其他几种现有方法一样，该方法假定功能是独立的。由于Shapley值当前在特征关联时包含不切实际的数据实例，因此解释可能非常具有误导性。即使使用简单的线性模型进行预测，情况也是如此。在本文中，我们扩展了Kernel Shap方法来处理依赖特征。我们提供了几个具有不同程度特征依赖的线性和非线性模型的例子，其中我们的方法给出了对真实Shapley值更精确的近似。(C)2021年提交人。爱思唯尔出版公司(Elsevier B.V.)
Explaining complex or seemingly simple machine learning models is an important practical problem. We want to explain individual predictions from such models by learning simple, interpretable explanations. Shapley valueis a game theoretic concept that can be used for this purpose. The Shapley value framework has a series of desirable theoretical properties, and can in principle handle any predictive model. Kernel SHAP is a computationally efficient approximation to Shapley values in higher dimensions. Like several other existing methods, this approach assumes that the features are independent. Since Shapley values currently suffer from inclusion of unrealistic data instances when features are correlated, the explanations may be very misleading. This is the case even if a simple linear model is used for predictions. In this paper, we extend the Kernel SHAP method to handle dependent features. We provide several examples of linear and non-linear models with various degrees of feature dependence, where our method gives more accurate approximations to the true Shapley values. (C) 2021 The Authors. Published by Elsevier B.V.