方法对比

	可解释关联规则	可解释朴素贝叶斯
领域	机器学习	机器学习
方法族	Machine learning	Machine learning
起源年份	1993 (rules); 2010s (XAI framing)	1950s (Naive Bayes); 2000s–2010s (explainability focus)
提出者	Agrawal, R., Imielinski, T., & Swami, A. (foundational); XAI framing: broader community (2010s–present)	Zhang, H. (explainability framing); Naive Bayes: Good, I. J.
类型	Interpretable pattern mining / XAI technique	Probabilistic generative classifier with intrinsic explainability
开创性文献	Agrawal, R., Imielinski, T., & Swami, A. (1993). Mining association rules between sets of items in large databases. Proceedings of the 1993 ACM SIGMOD International Conference on Management of Data, 207–216.	Rish, I. (2001). An empirical study of the naive Bayes classifier. In IJCAI Workshop on Empirical Methods in AI (pp. 41–46).
别名	XAI association rules, interpretable association rules, rule-based explanation mining, transparent association rule learning	XNB, interpretable Naive Bayes, transparent Naive Bayes, explainable probabilistic classifier
相关	6	4
摘要	Explainable Association Rules leverages the inherently symbolic, if-then structure of association rule mining to provide human-readable explanations of data patterns or black-box model decisions. Because each rule explicitly states its antecedent and consequent together with support, confidence, and lift, the outputs are natively interpretable without requiring a secondary post-hoc surrogate.	Explainable Naive Bayes extends the classic probabilistic Naive Bayes classifier with transparent, human-readable explanations of its predictions. By surfacing class priors, per-feature likelihoods, and log-odds contributions, it offers the interpretability demanded in high-stakes domains such as medicine, law, and education without sacrificing the simplicity and speed that make Naive Bayes a reliable baseline.