Provably Stable Feature Rankings with SHAP and LIME

Feature attributions are ubiquitous tools for understanding the predictions of machine learning models. However, popular methods for scoring input variables such as SHAP and LIME suffer from high instability due to random sampling. Leveraging ideas from multiple hypothesis testing, we devise attribution methods that correctly rank the most important features with high probability. Our algorithm RankSHAP guarantees that the $K$ highest Shapley values have the proper ordering with probability exceeding $1-\alpha$. Empirical results demonstrate its validity and impressive computational efficiency. We also build on previous work to yield similar results for LIME, ensuring the most important features are selected in the right order.