This repository curates a comprehensive list of academic papers exploring the intersection of Large Graph Models (LGMs) and Large Language Models (LLMs). It aims to serve researchers and practitioners by cataloging advancements in this rapidly evolving field, highlighting the potential for LGMs to revolutionize graph machine learning.

How It Works

The repository organizes papers into thematic categories such as "Perspective and Survey," "Prompt," "Model LLMs as Graph Models," "Graph Prompts," and "Applications." This structure facilitates easy navigation and discovery of relevant research, covering foundational concepts, novel methodologies, and practical use cases across domains like knowledge graphs, molecules, and neural architecture search.

Quick Start & Requirements

No installation or execution is required. This is a curated list of research papers.

Highlighted Details

• Extensive coverage of papers from major conferences (NeurIPS, ICML, KDD, WWW, AAAI, CVPR) and arXiv.
• Categorization includes foundational surveys, prompt-based learning, LLMs applied to graph tasks, and specific application domains.
• Links to papers (arXiv or conference proceedings) and, where available, associated code repositories are provided.
• Includes a perspective paper "Graph Meets LLMs: Towards Large Graph Models" for foundational understanding.

Maintenance & Community

The repository is maintained by THUMNLab and encourages community contributions via pull requests for missing papers or suggestions.

Licensing & Compatibility

The repository itself is licensed under an unspecified license. The linked papers are subject to their respective publisher or arXiv licenses.

Limitations & Caveats

This is a curated list of research papers and does not provide any executable code or models. The scope is limited to published research and may not include all emerging work.