Computing Rule-Based Explanations of Machine Learning Classifiers using Knowledge Graphs
Artificial Intelligence
2022-02-09 v1
Abstract
The use of symbolic knowledge representation and reasoning as a way to resolve the lack of transparency of machine learning classifiers is a research area that lately attracts many researchers. In this work, we use knowledge graphs as the underlying framework providing the terminology for representing explanations for the operation of a machine learning classifier. In particular, given a description of the application domain of the classifier in the form of a knowledge graph, we introduce a novel method for extracting and representing black-box explanations of its operation, in the form of first-order logic rules expressed in the terminology of the knowledge graph.
Cite
@article{arxiv.2202.03971,
title = {Computing Rule-Based Explanations of Machine Learning Classifiers using Knowledge Graphs},
author = {Edmund Dervakos and Orfeas Menis-Mastromichalakis and Alexandros Chortaras and Giorgos Stamou},
journal= {arXiv preprint arXiv:2202.03971},
year = {2022}
}