DeforestVis: Behavior Analysis of Machine Learning Models with Surrogate Decision Stumps

arXiv:2304.00133v4 Announce Type: replace
Abstract: As the complexity of machine learning (ML) models increases and their application in different (and critical) domains grows, there is a strong demand for more interpretable and trustworthy ML. A direct, model-agnostic, way to interpret such models is to train surrogate models-such as rule sets and decision trees-that sufficiently approximate the original ones while being simpler and easier-to-explain. Yet, rule sets can become very lengthy, with many if-else statements, and decision tree depth grows rapidly …

abstract analysis application arxiv behavior behavior analysis complexity cs.hc cs.lg decision demand domains machine machine learning machine learning models model-agnostic train trustworthy type