NNKGC: Improving Knowledge Graph Completion with Node Neighborhoods

TL;DR

This paper introduces a node neighborhood-enhanced framework for knowledge graph completion that models multi-hop neighborhoods with graph neural networks and adds an edge link prediction task, leading to improved and explainable results.

Contribution

It proposes a novel multi-hop neighborhood modeling approach with graph neural networks and an auxiliary link prediction task for better knowledge graph completion.

Findings

Effective on two public datasets

Predicts explainable results

Improves accuracy over baseline methods

Abstract

Knowledge graph completion (KGC) aims to discover missing relations of query entities. Current text-based models utilize the entity name and description to infer the tail entity given the head entity and a certain relation. Existing approaches also consider the neighborhood of the head entity. However, these methods tend to model the neighborhood using a flat structure and are only restricted to 1-hop neighbors. In this work, we propose a node neighborhood-enhanced framework for knowledge graph completion. It models the head entity neighborhood from multiple hops using graph neural networks to enrich the head node information. Moreover, we introduce an additional edge link prediction task to improve KGC. Evaluation on two public datasets shows that this framework is simple yet effective. The case study also shows that the model is able to predict explainable predictions.