InterpretML: A Unified Framework for Machine Learning Interpretability
InterpretML: A Unified Framework for Machine Learning Interpretability
复制标题
InterpretML：机器学习可解释性的统一框架
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
R. Caruana
中科院分区：
文献类型：
--
作者：
Harsha Nori;Samuel Jenkins;Paul Koch;R. Caruana
InterpretML是一个开源Python包，它向从业者和研究人员公开了机器学习可解释性算法。InterpretML公开了两种类型的可解释性-玻璃盒模型，这是为可解释性而设计的机器学习模型（例如：线性模型，规则列表，广义加法模型），以及用于解释现有系统的黑盒可解释性技术（例如：部分依赖，LIME）。该软件包通过在统一的API下公开多个方法，并通过内置的可扩展可视化平台，使从业者能够轻松地比较可解释性算法。InterpretML还包括可解释的提升机的第一个实现，这是一个强大的、可解释的玻璃盒模型，可以像许多黑盒模型一样准确。MIT许可源代码可以从github.com/microsoft/interpret下载。
InterpretML is an open-source Python package which exposes machine learning interpretability algorithms to practitioners and researchers. InterpretML exposes two types of interpretability - glassbox models, which are machine learning models designed for interpretability (ex: linear models, rule lists, generalized additive models), and blackbox explainability techniques for explaining existing systems (ex: Partial Dependence, LIME). The package enables practitioners to easily compare interpretability algorithms by exposing multiple methods under a unified API, and by having a built-in, extensible visualization platform. InterpretML also includes the first implementation of the Explainable Boosting Machine, a powerful, interpretable, glassbox model that can be as accurate as many blackbox models. The MIT licensed source code can be downloaded from github.com/microsoft/interpret.
DOI：
10.1145/3278721.3278725
发表时间：
2017-10
期刊：
Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society
影响因子：
--
作者：
S. Tan;R. Caruana;G. Hooker;Yin Lou
通讯作者：
S. Tan;R. Caruana;G. Hooker;Yin Lou