This repository is a curated collection of academic papers and resources focused on the integration of Large Language Models (LLMs) with Graph Learning. It targets researchers and practitioners in graph neural networks (GNNs) and LLMs, providing a structured overview of advancements in this rapidly evolving field. The primary benefit is a comprehensive, categorized summary of research, aiding in understanding current trends and identifying future research directions.

How It Works

The repository categorizes LLM-for-Graph research into four primary paradigms: "GNNs as Prefix," "LLMs as Prefix," "LLMs-Graphs Integration," and "LLMs-Only." These are further broken down into nine secondary categories, offering a systematic way to navigate the literature. This structured approach helps researchers quickly grasp the landscape of how LLMs are being adapted to enhance graph-based tasks, from using LLM embeddings as GNN inputs to developing LLM-native graph reasoning agents.

Quick Start & Requirements

This repository is a curated list of papers and does not have a direct installation or execution command. It serves as a reference guide.

Highlighted Details

• Features a KDD 2024 accepted survey paper, "A Survey of Large Language Models for Graphs."
• Includes resources from major conferences like KDD, WWW, NeurIPS, ICLR, AAAI, IJCAI, and SIGIR.
• Organizes papers into distinct categories based on the integration strategy of LLMs and graph learning.
• Provides links to papers for detailed study.

Maintenance & Community

The project is actively maintained, with recent updates and accepted papers from 2024. Contributions are welcomed via pull requests. The README is inspired by other "Awesome" lists in related fields.

Licensing & Compatibility

The repository itself, as a collection of links and summaries, does not appear to have a specific license. The linked papers retain their original publication licenses. Compatibility for commercial use would depend on the licenses of the individual research papers cited.

Limitations & Caveats

This is a survey and resource collection, not an executable library. It relies on external links to papers, which may be behind paywalls or require institutional access. The rapid pace of research means the list may not be exhaustive or immediately up-to-date with the very latest preprints.