Feature attributions are ubiquitous tools for understanding the predictions of machine learning models. However, the calculation of popular methods for scoring input variables such as SHAP and LIME suffers from high instability due to random sampling. Leveraging ideas from multiple hypothesis testing, we devise attribution methods that ensure the most important features are ranked correctly with high probability. Given SHAP estimates from KernelSHAP or Shapley Sampling, we demonstrate how to retrospectively verify the number of stable rankings. Further, we introduce efficient sampling algorithms for SHAP and LIME that guarantee the $K$ highest-ranked features have the proper ordering. Finally, we show how to adapt these local feature attribution methods for the global importance setting.

翻译：特征归因是理解机器学习模型预测的普遍工具。然而，由于随机采样，SHAP和LIME等流行输入变量评分方法的计算存在高度不稳定性。借助多重假设检验的思想，我们设计了能够以高概率确保最重要特征被正确排序的归因方法。给定来自KernelSHAP或Shapley采样的SHAP估计值，我们展示了如何回顾性验证稳定排序的数量。此外，我们为SHAP和LIME引入了高效采样算法，以保证排序最高的$K$个特征具有正确的顺序。最后，我们展示了如何将这些局部特征归因方法适配到全局重要性场景中。