KERMIT: Knowledge Graph Completion of Enhanced Relation Modeling with Inverse Transformation

TL;DR

This paper introduces KERMIT, a knowledge graph completion method that enhances relation modeling by generating coherent descriptions with large language models, using inverse relations for data augmentation, and leveraging label information for a fully supervised contrastive framework, resulting in improved performance on standard datasets.

Contribution

The paper proposes a novel KGC approach combining LLM-generated descriptions, inverse relation augmentation, and label-based supervision for improved accuracy.

Findings

Achieves 4.2% improvement in Hit@1 on WN18RR

Achieves 3.4% improvement in Hit@3 on FB15k-237

Demonstrates superior performance over existing methods

Abstract

Knowledge graph completion (KGC) revolves around populating missing triples in a knowledge graph using available information. Text-based methods, which depend on textual descriptions of triples, often encounter difficulties when these descriptions lack sufficient information for accurate prediction-an issue inherent to the datasets and not easily resolved through modeling alone. To address this and ensure data consistency, we first use large language models (LLMs) to generate coherent descriptions, bridging the semantic gap between queries and answers. Secondly, we utilize inverse relations to create a symmetric graph, thereby providing augmented training samples for KGC. Additionally, we employ the label information inherent in knowledge graphs (KGs) to enhance the existing contrastive framework, making it fully supervised. These efforts have led to significant performance improvements on the WN18RR and FB15k-237 datasets. According to standard evaluation metrics, our approach achieves a 4.2% improvement in Hit@1 on WN18RR and a 3.4% improvement in Hit@3 on FB15k-237, demonstrating superior performance.