Towards Enhancing Relational Rules for Knowledge Graph Link Prediction

TL;DR

This paper introduces RUN-GNN, a novel graph neural network that improves knowledge graph reasoning by modeling relation composition order and entity information flow, leading to better link prediction accuracy.

Contribution

The paper proposes RUN-GNN, which incorporates relation sequentiality and lagged information propagation handling, advancing relational rule learning in GNN-based reasoning.

Findings

RUN-GNN outperforms existing models on multiple datasets.

It improves reasoning accuracy in both transductive and inductive tasks.

The approach effectively models relation order and entity information flow.

Abstract

Graph neural networks (GNNs) have shown promising performance for knowledge graph reasoning. A recent variant of GNN called progressive relational graph neural network (PRGNN), utilizes relational rules to infer missing knowledge in relational digraphs and achieves notable results. However, during reasoning with PRGNN, two important properties are often overlooked: (1) the sequentiality of relation composition, where the order of combining different relations affects the semantics of the relational rules, and (2) the lagged entity information propagation, where the transmission speed of required information lags behind the appearance speed of new entities. Ignoring these properties leads to incorrect relational rule learning and decreased reasoning accuracy. To address these issues, we propose a novel knowledge graph reasoning approach, the Relational rUle eNhanced Graph Neural Network (RUN-GNN). Specifically, RUN-GNN employs a query related fusion gate unit to model the sequentiality of relation composition and utilizes a buffering update mechanism to alleviate the negative effect of lagged entity information propagation, resulting in higher-quality relational rule learning. Experimental results on multiple datasets demonstrate the superiority of RUN-GNN is superior on both transductive and inductive link prediction tasks.