DegreEmbed: incorporating entity embedding into logic rule learning for knowledge graph reasoning

TL;DR

DegreEmbed is a novel approach that combines entity embedding with logic rule mining to improve link prediction in heterogeneous knowledge graphs, addressing the limitations of existing methods.

Contribution

This paper introduces DegreEmbed, integrating embedding learning with logical rule mining specifically for heterogeneous KGs, which enhances interpretability and prediction accuracy.

Findings

Outperforms state-of-the-art methods on real datasets

Mines high-quality, interpretable logical rules

Effectively handles heterogeneity in knowledge graphs

Abstract

Knowledge graphs (KGs), as structured representations of real world facts, are intelligent databases incorporating human knowledge that can help machine imitate the way of human problem solving. However, KGs are usually huge and there are inevitably missing facts in KGs, thus undermining applications such as question answering and recommender systems that are based on knowledge graph reasoning. Link prediction for knowledge graphs is the task aiming to complete missing facts by reasoning based on the existing knowledge. Two main streams of research are widely studied: one learns low-dimensional embeddings for entities and relations that can explore latent patterns, and the other gains good interpretability by mining logical rules. Unfortunately, the heterogeneity of modern KGs that involve entities and relations of various types is not well considered in the previous studies. In this paper, we propose DegreEmbed, a model that combines embedding-based learning and logic rule mining for inferring on KGs. Specifically, we study the problem of predicting missing links in heterogeneous KGs from the perspective of the degree of nodes. Experimentally, we demonstrate that our DegreEmbed model outperforms the state-of-the-art methods on real world datasets and the rules mined by our model are of high quality and interpretability.