Unverified50% confidenceFactExact time
The paper provides an analytical form of Shapley values for weighted naive Bayes (a closed-form analytical solution requiring no sampling).
1
Sources
50%
Confidence
Long-term
Relevance
10/9/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSHAP由Scott Lundberg于2017年在NeurIPS论文中提出，是唯一同时满足局部准确性、缺失性和一致性三个公理的归因方法64% similarUnverifiedThe paper develops a maximum likelihood inference method that remains applicable even when the normalizing constant is intractable.63% similarUnverifiedShapley values satisfy four axioms—efficiency, symmetry, dummy, and additivity—and are considered the theoretically fairest method of feature attribution.61% similarVerifiedSHAP (SHapley Additive exPlanations) was proposed by Lundberg and Lee in 2017 and is based on the Shapley value principle from cooperative game theory.60% similarUnverifiedThe theoretical basis of SHAP comes from the concept of Shapley values in cooperative game theory, proposed by Nobel Prize-winning economist Lloyd Shapley in 1953; in 2017, Lundberg and Lee introduced it into the field of machine learning.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/990777API
curl https://kongchang.com/api/v1/knowledge/claims/990777MCP
get_claim(id=990777)