Verified SHAP: Provable Bounds for Exact Shapley Values of Neural Networks 事件

Verified SHAP: Provable Bounds for Exact Shapley Values of Neural Networks arXiv:2605.24084v1 Announce Type: cross Abstract: 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 c