通过分解黑箱模型，用可解释的近似模型学习其行为。
midr: Learning from Black-Box Models by Maximum Interpretation Decomposition
- 用最小平方误差将黑箱模型分解为低阶加性形式。
- 构建全局代理模型，实现对原模型的可解释分析。
- 适合需要理解黑箱模型决策逻辑的研究者使用。
在要求模型和预测可解释性的领域中，采用适当的可解释机器学习（IML）与可解释人工智能（XAI）方法至关重要。本文介绍R包midr，实现了最大解释分解（Maximum Interpretation Decomposition, MID）这一新型黑箱模型解释工具。MID是一种函数分解方法，通过最小化黑箱模型预测函数与其加性表示之间的平方误差，获得一个低阶加性近似。midr使我们能够通过构建具备高级分析能力的全局代理模型，从黑箱模型中学习。本文回顾了相关工作与MID的理论基础，并演示了该包的使用方式，讨论了其若干关键特性。
原文摘要 · Abstract (English)
The use of appropriate methods of Interpretable Machine Learning (IML) and eXplainable Artificial Intelligence (XAI) is essential for adopting black-box predictive models in fields where model and prediction explainability is required. As a novel tool for interpreting black-box models, we introduce the R package midr, which implements Maximum Interpretation Decomposition (MID). MID is a functional decomposition approach that derives a low-order additive representation of a black-box model by minimizing the squared error between the model's prediction function and this additive representation. midr enables learning from black-box models by constructing a global surrogate model with advanced analytical capabilities. After reviewing related work and the theoretical foundation of MID, we demonstrate the package's usage and discuss some of its key features.
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。