Unverified50% confidenceFactExact time
SHAP的核心思想是将每个特征对模型预测的贡献量化，使得所有特征贡献之和等于模型预测值与基线值的差
1
Sources
50%
Confidence
Long-term
Relevance
8/28/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedSHAP基于博弈论中的Shapley值，能够量化每个特征对最终预测结果的贡献度，是目前工业界应用最广泛的解释性工具之一79% similarUnverifiedSHAP用于特征归因（解释每个特征对预测的贡献度），DiCE用于生成多样化的反事实样本，二者互补78% similarUnverifiedSHAP值通过博弈论中的沙普利值方法量化每个特征对单一预测结果的贡献度，LIME通过在预测点附近构建局部线性近似模型解释个案决策75% similarUnverifiedSHAP (SHapley Additive exPlanations) is a mainstream machine learning model explanation framework whose theoretical basis derives from Shapley values in game theory.68% similarUnverifiedLIME (Local Interpretable Model-Agnostic Explanations) and SHAP (SHapley Additive exPlanations) are the primary tools for providing post-hoc explanations for complex black-box models.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/813020API
curl https://kongchang.com/api/v1/knowledge/claims/813020MCP
get_claim(id=813020)