.png){kind=icon}
返回
A decision-theoretic approach for model interpretability in Bayesian framework
.png){kind=icon}
OA
AI
DOI：10.1007/s10994-020-05901-8.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
A salient approach to interpretable machine learning is to restrict modeling to simple models. In the Bayesian framework, this can be pursued by restricting the model structure and prior to favor interpretable models. Fundamentally, however, interpretability is about users' preferences, not the data generation mechanism; it is more natural to formulate interpretability as a utility function. In this work, we propose an interpretability utility, which explicates the trade-off between explanation fidelity and interpretability in the Bayesian framework. The method consists of two steps. First, a reference model, possibly a black-box Bayesian predictive model which does not compromise accuracy, is fitted to the training data. Second, a proxy model from an interpretable model family that best mimics the predictive behaviour of the reference model is found by optimizing the interpretability utility function. The approach is model agnostic-neither the interpretable model nor the reference model are restricted to a certain class of models-and the optimization problem can be solved using standard tools. Through experiments on real-word data sets, using decision trees as interpretable models and Bayesian additive regression models as reference models, we show that for the same level of interpretability, our approach generates more accurate models than the alternative of restricting the prior. We also propose a systematic way to measure stability of interpretabile models constructed by different interpretability approaches and show that our proposed approach generates more stable models.
Keyword:
Interpretable machine learning
Bayesian predictive models
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
2.9
论文数:
2.7K
被引数:
3.4W
机构
引用论文
Efficacy and safety of danoprevir plus sofosbuvir in GT 1, 2, 3, or 6 chronic hepatitis C patients with or without cirrhosis in China.png)
Medicine
OAAI
MedicineIF0
OAAI分享收藏The partial amino acid sequences of the two H2B histones from sperm of the sea urchin Psammechinus miliaris海胆精子中两个H2B组蛋白的部分氨基酸序列
PREAI
分享收藏Facile synthesis of tremelliform Co0.85Se nanosheets: An efficient catalyst for the decomposition of hydrazine hydratetremelliform Co0.85Se纳米片的简易合成: 水合肼分解的有效催化剂
PREAI
分享收藏Current treatments and outlook in adenocarcinoma of the esophagogastric junction: a narrative reviewOAAI
OAAI分享收藏Gradient-based learning applied to document recognition基于梯度的学习在文档识别中的应用PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏
查看更多内容