In-Context Learning with Topological Information for Knowledge Graph Completion

TL;DR

This paper introduces a novel in-context learning method that incorporates topological and ontological information to improve knowledge graph completion, demonstrating superior results in both transductive and inductive settings.

Contribution

The paper presents a new approach integrating topological information into in-context learning for KGC, effectively handling both transductive and inductive scenarios.

Findings

Achieves strong performance on ILPC-small and ILPC-large datasets.

Effectively leverages ontological knowledge for inductive KGC.

Outperforms baseline methods in various settings.

Abstract

Knowledge graphs (KGs) are crucial for representing and reasoning over structured information, supporting a wide range of applications such as information retrieval, question answering, and decision-making. However, their effectiveness is often hindered by incompleteness, limiting their potential for real-world impact. While knowledge graph completion (KGC) has been extensively studied in the literature, recent advances in generative AI models, particularly large language models (LLMs), have introduced new opportunities for innovation. In-context learning has recently emerged as a promising approach for leveraging pretrained knowledge of LLMs across a range of natural language processing tasks and has been widely adopted in both academia and industry. However, how to utilize in-context learning for effective KGC remains relatively underexplored. We develop a novel method that incorporates topological information through in-context learning to enhance KGC performance. By integrating ontological knowledge and graph structure into the context of LLMs, our approach achieves strong performance in the transductive setting i.e., nodes in the test graph dataset are present in the training graph dataset. Furthermore, we apply our approach to KGC in the more challenging inductive setting, i.e., nodes in the training graph dataset and test graph dataset are disjoint, leveraging the ontology to infer useful information about missing nodes which serve as contextual cues for the LLM during inference. Our method demonstrates superior performance compared to baselines on the ILPC-small and ILPC-large datasets.