Explainable Deep RDFS Reasoner

TL;DR

This paper presents an explainable deep learning approach for RDFS reasoning that not only infers triples but also provides derivations, enhancing interpretability in neural-symbolic reasoning systems.

Contribution

It introduces a neural network model that generates explanations for inferred triples in RDFS reasoning, building on graph words and neural machine translation techniques.

Findings

Achieved up to 96% validation accuracy on datasets

Provided derivations for inferred triples

Enhanced explainability in neural-symbolic reasoning

Abstract

Recent research efforts aiming to bridge the Neural-Symbolic gap for RDFS reasoning proved empirically that deep learning techniques can be used to learn RDFS inference rules. However, one of their main deficiencies compared to rule-based reasoners is the lack of derivations for the inferred triples (i.e. explainability in AI terms). In this paper, we build on these approaches to provide not only the inferred graph but also explain how these triples were inferred. In the graph words approach, RDF graphs are represented as a sequence of graph words where inference can be achieved through neural machine translation. To achieve explainability in RDFS reasoning, we revisit this approach and introduce a new neural network model that gets the input graph--as a sequence of graph words-- as well as the encoding of the inferred triple and outputs the derivation for the inferred triple. We evaluated our justification model on two datasets: a synthetic dataset-- LUBM benchmark-- and a real-world dataset --ScholarlyData about conferences-- where the lowest validation accuracy approached 96%.