通过特征重要性提升原型解释的局部与全局粒度。
Alike Parts: A Feature-Informed Approach to Local and Global Prototype Explanations
- 提出'同类部分'方法，聚焦实例与原型间共享的高重要性特征子集。
- 在全局原型选择中加入特征重要性项，提升所选原型的特征多样性。
- 实验表明新方法保持甚至提高代理模型预测保真度，适合需要可解释性的场景。
基于原型的解释为机器学习黑箱分类器提供了直观的示例化解释方式，但通常缺乏特征层面的细粒度。本文提出一种融合双层级特征重要性的框架：首先，针对局部解释，引入‘同类部分’方法，利用特征重要性得分突出被分类实例与其最近原型之间最相关且共享的特征子集，引导用户注意力；其次，在全局原型选择的目标函数中加入特征重要性项，主动促进所选原型特征归属的多样性。在六个基准数据集上的实验表明，这种增强的选择过程保持或在某些情况下提升代理模型的预测保真度，表明特征多样性不会损害模型保真度。
原文摘要 · Abstract (English)
Prototype-based explanations offer an intuitive, example-based approach to support the interpretability of machine learning black box classifiers but often lack feature-level granularity. We introduce a framework that integrates feature importance at two levels to address this gap. First, for local explanations, we propose \textit{alike parts}: a method that uses feature importance scores to highlight the most relevant, shared feature subsets between a classified instance and its nearest prototype, guiding user attention. Second, we augment the global prototype selection objective function with a feature importance term to actively promote diversity in the feature attributions of the selected prototypes. Experiments on six benchmark datasets show that this augmented selection process maintains or, in some cases, increases the prediction fidelity of the surrogate model, suggesting that feature diversity does not compromise model fidelity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。