方法对比

	可解释投票集成	SHAP (SHapley Additive exPlanations)
领域	机器学习	机器学习
方法族	Machine learning	Machine learning
起源年份	2016–2020	2017
提出者	Composite: voting ensemble (Dietterich, 2000) + XAI frameworks (Ribeiro et al., 2016; Lundberg & Lee, 2017)	Lundberg, S.M. & Lee, S.-I.
类型	Ensemble with post-hoc or ante-hoc interpretability	Model-explanation method (Shapley-value attribution)
开创性文献	Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30, 4765–4774.	Lundberg, S.M. & Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems, 30, 4766–4777.
别名	XAI voting ensemble, interpretable voting classifier, transparent voting ensemble, explainable majority vote model	SHAP Değerleri (Model Açıklanabilirlik), Shapley additive explanations, SHAP values, model explainability
相关	6	5
摘要	An Explainable Voting Ensemble combines predictions from multiple diverse base models through majority vote (hard voting) or averaged probabilities (soft voting), then applies post-hoc or ante-hoc XAI techniques — such as SHAP values, LIME, or permutation importance — to produce feature-level explanations for the combined model's decisions. The goal is to retain the accuracy gains of ensemble aggregation while meeting interpretability requirements in high-stakes or regulated applications.	SHAP is a model-explanation method, introduced by Scott Lundberg and Su-In Lee in 2017, that uses Shapley values from cooperative game theory to measure how much each feature contributes to an individual prediction, making the output of black-box machine-learning models interpretable. It supports both global explanations (overall feature importance) and local explanations (why one specific prediction came out the way it did).