Node Co-occurrence based Graph Neural Networks for Knowledge Graph Link Prediction

TL;DR

This paper presents NoGE, a novel graph neural network model that leverages co-occurrence information among entities and relations to enhance knowledge graph link prediction, achieving state-of-the-art results on challenging datasets.

Contribution

The paper introduces NoGE, which constructs a unified graph considering entities and relations as nodes, and employs Dual Quaternion Graph Neural Networks for improved knowledge graph completion.

Findings

NoGE outperforms existing models on three benchmark datasets.

Incorporating co-occurrence improves link prediction accuracy.

DualQGNN effectively updates entity and relation representations.

Abstract

We introduce a novel embedding model, named NoGE, which aims to integrate co-occurrence among entities and relations into graph neural networks to improve knowledge graph completion (i.e., link prediction). Given a knowledge graph, NoGE constructs a single graph considering entities and relations as individual nodes. NoGE then computes weights for edges among nodes based on the co-occurrence of entities and relations. Next, NoGE proposes Dual Quaternion Graph Neural Networks (DualQGNN) and utilizes DualQGNN to update vector representations for entity and relation nodes. NoGE then adopts a score function to produce the triple scores. Comprehensive experimental results show that NoGE obtains state-of-the-art results on three new and difficult benchmark datasets CoDEx for knowledge graph completion.