Shapley Residuals: Quantifying the limits of the Shapley value for explanations
Shapley Residuals: Quantifying the limits of the Shapley value for explanations
复制标题
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Indra Elizabeth Kumar;C. Scheidegger;S. Venkatasubramanian;Sorelle A. Friedler
中科院分区：
文献类型：
--
作者：
Indra Elizabeth Kumar;C. Scheidegger;S. Venkatasubramanian;Sorelle A. Friedler
目前流行的特征重要性计算方法是通过合作博弈(fiRst defi)来计算非线性模型的加性近似，该博弈描述了模型特征的不同子集的值，然后计算得到的博弈的Shapley值来增加特征之间的信用属性。然而，其中Shapley值是真实游戏的较差近似值的特定fic建模设置还没有被很好地描述。在这篇文章中，我们利用对Shapley值的解释作为向量空间之间的正交投影的结果来计算表示该投影的核分量的残差。我们提供了一个计算这些残差的算法，根据残差的值描述了不同的建模设置，并证明了它们捕获了Shapley值无法捕获的关于模型预测的信息。因此，Shapley残差可以作为对实践者的警告，不要高估基于Shapley值的解释给他们对模型的洞察的程度。
Popular feature importance techniques compute additive approximations to nonlinear models by first defining a cooperative game describing the value of different subsets of the model’s features, then calculating the resulting game’s Shapley values to attribute credit additively between the features. However, the specific modeling settings in which the Shapley values are a poor approximation for the true game have not been well-described. In this paper we utilize an interpretation of Shapley values as the result of an orthogonal projection between vector spaces to calculate a residual representing the kernel component of that projection. We provide an algorithm for computing these residuals, characterize different modeling settings based on the value of the residuals, and demonstrate that they capture information about model predictions that Shapley values cannot. Shapley residuals can thus act as a warning to practitioners against overestimating the degree to which Shapley-value-based explanations give them insight into a model.