A Pluggable Common Sense-Enhanced Framework for Knowledge Graph Completion

TL;DR

This paper introduces a flexible framework for knowledge graph completion that integrates common sense reasoning, improving accuracy by generating and utilizing explicit or implicit common sense, and is compatible with various embedding models.

Contribution

It presents a pluggable, adaptable framework that incorporates common sense into KGC, including novel negative sampling and inference methods for different KG types.

Findings

Outperforms existing models on multiple KGC tasks.

Demonstrates scalability across different knowledge graphs.

Effectively integrates common sense with factual triples.

Abstract

Knowledge graph completion (KGC) tasks aim to infer missing facts in a knowledge graph (KG) for many knowledge-intensive applications. However, existing embedding-based KGC approaches primarily rely on factual triples, potentially leading to outcomes inconsistent with common sense. Besides, generating explicit common sense is often impractical or costly for a KG. To address these challenges, we propose a pluggable common sense-enhanced KGC framework that incorporates both fact and common sense for KGC. This framework is adaptable to different KGs based on their entity concept richness and has the capability to automatically generate explicit or implicit common sense from factual triples. Furthermore, we introduce common sense-guided negative sampling and a coarse-to-fine inference approach for KGs with rich entity concepts. For KGs without concepts, we propose a dual scoring scheme involving a relation-aware concept embedding mechanism. Importantly, our approach can be integrated as a pluggable module for many knowledge graph embedding (KGE) models, facilitating joint common sense and fact-driven training and inference. The experiments illustrate that our framework exhibits good scalability and outperforms existing models across various KGC tasks.