Multi-Aspect Explainable Inductive Relation Prediction by Sentence Transformer

TL;DR

This paper introduces a novel sentence transformer model, KRST, that leverages reliable relation paths for inductive relation prediction in knowledge graphs, providing multi-aspect explanations and outperforming state-of-the-art models.

Contribution

The paper proposes relation path confidence filtering and a new sentence transformer, KRST, for improved inductive relation prediction with explainability in knowledge graphs.

Findings

KRST outperforms SOTA in most transductive and inductive cases.

KRST achieves top results in 11 of 12 few-shot scenarios.

Reliable path filtering enhances model performance.

Abstract

Recent studies on knowledge graphs (KGs) show that path-based methods empowered by pre-trained language models perform well in the provision of inductive and explainable relation predictions. In this paper, we introduce the concepts of relation path coverage and relation path confidence to filter out unreliable paths prior to model training to elevate the model performance. Moreover, we propose Knowledge Reasoning Sentence Transformer (KRST) to predict inductive relations in KGs. KRST is designed to encode the extracted reliable paths in KGs, allowing us to properly cluster paths and provide multi-aspect explanations. We conduct extensive experiments on three real-world datasets. The experimental results show that compared to SOTA models, KRST achieves the best performance in most transductive and inductive test cases (4 of 6), and in 11 of 12 few-shot test cases.