Simple and Interpretable Probabilistic Classifiers for Knowledge Graphs
This work addresses the problem of interpretable probabilistic classification for incomplete Knowledge Graphs, but it appears incremental as it builds on existing models like Naive Bayes.
The paper tackles learning probabilistic classifiers from incomplete data in Knowledge Graphs using Description Logics, proposing an inductive approach based on simple belief networks like Naive Bayes and a two-tier extension, and shows they can be converted into interpretable probabilistic axioms with empirical evaluation on random classification problems.
Tackling the problem of learning probabilistic classifiers from incomplete data in the context of Knowledge Graphs expressed in Description Logics, we describe an inductive approach based on learning simple belief networks. Specifically, we consider a basic probabilistic model, a Naive Bayes classifier, based on multivariate Bernoullis and its extension to a two-tier network in which this classification model is connected to a lower layer consisting of a mixture of Bernoullis. We show how such models can be converted into (probabilistic) axioms (or rules) thus ensuring more interpretability. Moreover they may be also initialized exploiting expert knowledge. We present and discuss the outcomes of an empirical evaluation which aimed at testing the effectiveness of the models on a number of random classification problems with different ontologies.