An LLM-guided framework for link prediction in homogeneous graphs

Abstract As social networks grow, link prediction has become vital in network analysis, estimating the likelihood of connections between unconnected nodes based on similarity scores. This study explores the intersection of Large Language Models (LLMs) and Graph Learning, with a particular focus on Link Prediction tasks on Homogeneous Networks, where we are using LLMs to analyze social network structures and predict missing links. There have been several studies that leveraged LLMs for Knowledge Graphs, Heterogeneous Graphs, and Text-Attributed Graphs. However, leveraging LLMs for Homogeneous Graphs with no textual information is still an understudied area, which is what we aimed to explore. We developed a framework that leverages LLMs for link prediction tasks requiring no textual information with different learning strategies. Our results demonstrate improvement in model performance for predicting missing links, especially when provided with few examples or fine-tuned on the domain-specific datasets, achieving results on par with state-of-the-art results, even with no fine-tuning.