论文标题
PDD-shap：使用功能分解的Shapley值的快速近似
PDD-SHAP: Fast Approximations for Shapley Values using Functional Decomposition
论文作者
论文摘要
由于其强大的理论属性，Shapley值已变得非常流行，以解释黑匣子模型做出的预测。不幸的是，大多数计算沙普利值的现有技术在计算上非常昂贵。我们建议使用基于ANOVA的功能分解模型来近似所解释的黑框模型，该算法是PDD-shap。这使我们能够计算出比大型数据集的现有方法快的shapley值数量级，当需要解释许多预测时，大大降低了计算沙普利值的摊销成本。
Because of their strong theoretical properties, Shapley values have become very popular as a way to explain predictions made by black box models. Unfortuately, most existing techniques to compute Shapley values are computationally very expensive. We propose PDD-SHAP, an algorithm that uses an ANOVA-based functional decomposition model to approximate the black-box model being explained. This allows us to calculate Shapley values orders of magnitude faster than existing methods for large datasets, significantly reducing the amortized cost of computing Shapley values when many predictions need to be explained.
