Computing Rule-Based Explanations of Machine Learning Classifiers using Knowledge Graphs
This work addresses the lack of transparency in machine learning classifiers for researchers and practitioners, offering a novel symbolic approach.
The authors tackled the problem of explaining machine learning classifiers by using knowledge graphs to generate first-order logic rules, providing a symbolic representation for black-box model explanations.
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.