A Unified Approach to Interpreting Model Predictions, Scott M Lundberg, Su-In Lee, 2017Advances in Neural Information Processing Systems 30 (NIPS 2017) (NeurIPS) - 提出了SHAP的开创性论文,SHAP是一种博弈论解释框架,统一了多种可解释性方法并提供了一致的特征归因,包括模型无关(KernelSHAP)和模型特定(TreeSHAP)的实现。