LinkGPT: Teaching Large Language Models To Predict Missing Links

TL;DR

LinkGPT introduces a novel end-to-end LLM approach for link prediction in graphs, effectively integrating structural information and achieving state-of-the-art results with improved efficiency and generalization capabilities.

Contribution

The paper presents LinkGPT, the first end-to-end trained LLM for link prediction, with a two-stage instruction tuning and retrieval-reranking scheme for efficiency.

Findings

Achieves state-of-the-art link prediction performance.

Provides 10x inference speedup while maintaining accuracy.

Demonstrates strong zero-shot and few-shot generalization.

Abstract

Large Language Models (LLMs) have shown promising results on various language and vision tasks. Recently, there has been growing interest in applying LLMs to graph-based tasks, particularly on Text-Attributed Graphs (TAGs). However, most studies have focused on node classification, while the use of LLMs for link prediction (LP) remains understudied. In this work, we propose a new task on LLMs, where the objective is to leverage LLMs to predict missing links between nodes in a graph. This task evaluates an LLM's ability to reason over structured data and infer new facts based on learned patterns. This new task poses two key challenges: (1) How to effectively integrate pairwise structural information into the LLMs, which is known to be crucial for LP performance, and (2) how to solve the computational bottleneck when teaching LLMs to perform LP. To address these challenges, we propose LinkGPT, the first end-to-end trained LLM for LP tasks. To effectively enhance the LLM's ability to understand the underlying structure, we design a two-stage instruction tuning approach where the first stage fine-tunes the pairwise encoder, projector, and node projector, and the second stage further fine-tunes the LLMs to predict links. To address the efficiency challenges at inference time, we introduce a retrieval-reranking scheme. Experiments show that LinkGPT can achieve state-of-the-art performance on real-world graphs as well as superior generalization in zero-shot and few-shot learning, surpassing existing benchmarks. At inference time, it can achieve $10\times$ speedup while maintaining high LP accuracy.