arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.04295cs.LGstat.ML
收藏

变换特征空间以解释机器学习模型

Transforming Feature Space to Interpret Machine Learning Models

Michael Stifel Center Jena for Data-Driven and Simulation Science(耶拿迈克尔·斯蒂菲尔数据驱动与仿真科学中心);Friedrich Schiller University Jena(耶拿弗里德里希·席勒大学)

Alexander Brenning

AI总结:

本文提出通过特征空间变换(如PCA和部分正交化)解释机器学习模型的新方法,可增强部分依赖图等post-hoc诊断工具,并在R包wiml中实现,通过遥感土地覆盖分类案例验证其有效性。

摘要:

用于解释机器学习模型的模型无关工具难以总结高维特征空间中强依赖特征的联合效应,而这些联合效应在模式识别中起着重要作用,例如在土地覆盖遥感中。本文提出了一种新颖的方法,通过特征空间变换的视角来解释机器学习模型。该方法可用于增强无条件以及有条件的post-hoc诊断工具,包括部分依赖图、累积局部效应图或置换特征重要性评估。虽然该方法也可应用于非线性变换,但我们重点关注线性变换,包括主成分分析(PCA)和一种部分正交化技术。结构化PCA和沿路径的诊断提供了表示领域知识的机会。新方法已在R包`wiml`中实现,该包可与现有的可解释机器学习包结合使用。通过一个具有46个特征的遥感土地覆盖分类案例研究,展示了所提方法在领域专家进行模型解释方面的潜力。

英文摘要:

Model-agnostic tools for interpreting machine-learning models struggle to summarize the joint effects of strongly dependent features in high-dimensional feature spaces, which play an important role in pattern recognition, for example in remote sensing of landcover. This contribution proposes a novel approach that interprets machine-learning models through the lens of feature space transformations. It can be used to enhance unconditional as well as conditional post-hoc diagnostic tools including partial dependence plots, accumulated local effects plots, or permutation feature importance assessments. While the approach can also be applied to nonlinear transformations, we focus on linear ones, including principal component analysis (PCA) and a partial orthogonalization technique. Structured PCA and diagnostics along paths offer opportunities for representing domain knowledge. The new approach is implemented in the R package `wiml`, which can be combined with existing explainable machine-learning packages. A case study on remote-sensing landcover classification with 46 features is used to demonstrate the potential of the proposed approach for model interpretation by domain experts.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑