方法对比

	反事实解释	LIME：局部可解释模型无关解释	逻辑回归
领域	机器学习	机器学习	研究统计学
方法族	Machine learning	Machine learning	Process / pipeline
起源年份	2017	2016	1958
提出者	Sandra Wachter, Brent Mittelstadt & Chris Russell	Marco Ribeiro, Sameer Singh & Carlos Guestrin	David Roxbee Cox
类型	Post-hoc, model-agnostic explanation	post-hoc local explanation	Method
开创性文献	Wachter, S., Mittelstadt, B., & Russell, C. (2017). Counterfactual explanations without opening the black box: Automated decisions and the GDPR. Harvard Journal of Law & Technology, 31, 841–887.	Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). "Why should I trust you?": Explaining the predictions of any classifier. ACM SIGKDD, 1135–1144.	Cox, D. R. (1958). The regression analysis of binary sequences. Journal of the Royal Statistical Society, Series B, 20(2), 215–242.
别名	Algorithmic Recourse, Contrastive Explanations, What-If Explanations, Karşıolgusal Açıklamalar	Local Surrogate Explanations, Model-Agnostic Local Explanations, Locally Faithful Approximations, Yerel Yorumlanabilir Model-Bağımsız Açıklamalar	logit model, binomial logistic regression, LR
相关	2	2	3
摘要	Counterfactual explanations, introduced by Wachter, Mittelstadt, and Russell in 2017, answer the question: 'What is the smallest change to the input that would have produced a different model output?' Rather than explaining why a model made a decision, they describe what would need to change for that decision to be reversed, making them particularly valuable for high-stakes applications such as credit scoring, medical diagnosis, and hiring decisions under frameworks like the EU GDPR.	LIME, introduced by Ribeiro, Singh, and Guestrin in 2016, explains the predictions of any black-box classifier or regressor by building a simple, locally faithful surrogate model around a single prediction of interest. Rather than explaining the global model, LIME focuses on why a specific instance was classified the way it was, making complex models such as deep neural networks and ensemble methods interpretable to end-users, domain experts, and auditors.	Logistic regression is a statistical method for modeling the probability of a binary outcome (disease present/absent, success/failure) as a function of continuous and categorical predictors. Developed by David Roxbee Cox (1958), it solves the problem of predicting categorical outcomes by applying a logistic transformation to constrain predictions to the [0,1] probability interval, enabling accurate risk stratification, diagnostic prediction, and causal inference in epidemiology, medicine, and social science.