Machine learningExplainable AI
LIME：局部可解释模型无关解释
LIME由Ribeiro、Singh和Guestrin于2016年提出，通过围绕感兴趣的单个预测构建一个简单、局部保真的代理模型来解释任何黑盒分类器或回归器的预测。LIME不解释全局模型，而是关注特定实例为何被如此分类，从而使深度神经网络和集成方法等复杂模型对最终用户、领域专家和审计人员具有可解释性。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
来源
- Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). "Why should I trust you?": Explaining the predictions of any classifier. ACM SIGKDD, 1135–1144. DOI: 10.1145/2939672.2939778 ↗
如何引用本页
ScholarGate. (2026, June 2). Local Interpretable Model-agnostic Explanations (LIME). ScholarGate. https://scholargate.app/zh/machine-learning/lime
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
Compare side by side →