Shapley additive explanations (SHAP) are widely recognised as computationally intractable for neural networks, since they induce an exponential search space over the input features. In this work, we take a first step towards scaling exact SHAP computation to larger search spaces by introducing an algorithm that leverages recent advances in neural network verification to compute arbitrarily tight exact lower and upper bounds on SHAP values for neural networks, ultimately recovering the exact SHAP values. We demonstrate that our approach scales to orders of magnitude larger search spaces than state-of-the-art exact methods. This provides an important first step towards exact SHAP computation and establishes a principled cornerstone for evaluating statistical approximation methods on larger search spaces.

翻译：Shapley加法解释（SHAP）被广泛认为对神经网络而言在计算上难以处理，因为它引入了关于输入特征的指数级搜索空间。在本工作中，我们通过引入一种算法，利用神经网络验证领域的最新进展来计算神经网络中SHAP值的任意紧致精确上下界，最终恢复精确SHAP值，从而迈出了将精确SHAP计算扩展到更大搜索空间的第一步。我们证明，我们的方法可扩展至比现有最优精确方法大数个数量级的搜索空间。这为精确SHAP计算提供了重要的第一步，并为在更大搜索空间上评估统计近似方法奠定了原则性基石。