GFMPapers: Must-read papers on graph foundation models (GFMs)

This list is currently maintained by members in BUPT GAMMA Lab. If you like our project, please give us a star ⭐ on GitHub for the latest update.

We thank all the great contributors very much.

⭐[News] We will hold a tutorial about graph foundation model at the WebConf 2024! See you at Singapore!

Contents

• Contents
• Keywords Convention
• 0. Survey Papers
• 1. GNN-based Papers
• 2. LLM-based Papers
• 3. GNN+LLM-based Papers
• Contributors

Keywords Convention

backbone architecture

Pretraining

Adaptation

The meaning of each tag can be referred to in the "Towards Graph Foundation Models: A Survey and Beyond" paper.

0. Survey Papers

1. [arXiv 2023.8] Graph Meets LLMs: Towards Large Graph Models. [pdf][paperlist]
2. [arXiv 2023.10] Integrating Graphs with Large Language Models: Methods and Prospects. [pdf]
3. [arXiv 2023.10] Towards Graph Foundation Models: A Survey and Beyond. [pdf][paperlist]
4. [arXiv 2023.11] A Survey of Graph Meets Large Language Model: Progress and Future Directions. [pdf][paperlist]
5. [arXiv 2023.12] Large Language Models on Graphs: A Comprehensive Survey. [pdf][paperlist]

1. GNN-based Papers

1. [arXiv 2023.10] Enhancing Graph Neural Networks with Structure-Based Prompt [pdf]
2. [arXiv 2023.11] MultiGPrompt for Multi-Task Pre-Training and Prompting on Graphs [pdf]
3. [arXiv 2023.10] HetGPT: Harnessing the Power of Prompt Tuning in Pre-Trained Heterogeneous Graph Neural Networks [pdf]
4. [arXiv 2023.10] Prompt Tuning for Multi-View Graph Contrastive Learning [pdf]
5. [arXiv 2023.05] PRODIGY: Enabling In-context Learning Over Graphs. [pdf]
6. [arXiv 2023.05] G-Adapter: Towards Structure-Aware Parameter-Efficient Transfer Learning for Graph Transformer Networks. [pdf]
7. [arXiv 2023.04] AdapterGNN: Efficient Delta Tuning Improves Generalization Ability in Graph Neural Networks. [pdf]
8. [arXiv 2023.02] SGL-PT: A Strong Graph Learner with Graph Prompt Tuning. [pdf]
9. [KDD 2023] All in One: Multi-Task Prompting for Graph Neural Networks. [pdf]
10. [KDD 2023] A Data-centric Framework to Endow Graph Neural Networks with Out-Of-Distribution Detection Ability. [pdf] [code]
11. [AAAI 2023] Ma-gcl: Model augmentation tricks for graph contrastive learning. [pdf] [code]
12. [WWW 2023] GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner. [pdf] [code]
13. [WWW 2023] Graphprompt: Unifying pre-training and downstream tasks for graph neural networks. [pdf] [code]
14. [CIKM 2023] Voucher Abuse Detection with Prompt-based Fine-tuning on Graph Neural Networks. [pdf] [code]
15. [KDD 2022] GraphMAE: Self-supervised masked graph autoencoders. [pdf] [code]
16. [KDD 2022] Gppt: Graph pre-training and prompt tuning to generalize graph neural networks.
17. [arXiv 2022.09] Universal Prompt Tuning for Graph Neural Networks. [pdf]
18. [KDD 2021] Pre-training on large-scale heterogeneous graph. [pdf] [code]
19. [CIKM 2021] Contrastive pre-training of GNNs on heterogeneous graphs. [pdf] [code]
20. [ICML 2020] Deep graph contrastive representation learning. [pdf] [code]
21. [NeurIPS 2020] Self-supervised graph transformer on large-scale molecular data. [pdf]
22. [NeurIPS 2020] Graph contrastive learning with augmentations. [pdf] [code]
23. [KDD 2020] Gcc: Graph contrastive coding for graph neural network pre-training. [pdf] [code]
24. [KDD 2020] Gpt-gnn: Generative pre-training of graph neural networks. [pdf] [code]
25. [arXiv 2020.01] Graph-bert: Only attention is needed for learning graph representations. [pdf] [code]
26. [ICLR 2019] Deep graph infomax. [pdf] [code]
27. [arXiv 2016.11] Variational graph auto-encoders. [pdf] [code]

2. LLM-based Papers

1. [arXiv 2023.10] Talk Like a Graph: Encoding Graphs for Large Language Models [pdf]
2. [arxiv 2023.10] Graphtext: Graph reasoning in text space. [pdf]
3. [arXiv 2023.09] Can LLMs Effectively Leverage Graph Structural Information: When and Why [pdf]
4. [arXiv 2023.08] Natural language is all a graph needs. [pdf] [code]
5. [arxiv 2023.08] Evaluating large language models on graphs: Performance insights and comparative analysis. [pdf] [code]
6. [arxiv 2023.07] Can large language models empower molecular property prediction? [pdf] [code]
7. [arxiv 2023.07] Meta-Transformer: A Unified Framework for Multimodal Learning. [pdf] [code]
8. [arxiv 2023.07] Exploring the potential of large language models (llms) in learning on graphs [pdf] [code]
9. [arxiv 2023.05] Gimlet: A unified graph-text model for instruction-based molecule zero-shot learning. [pdf]
10. [arxiv 2023.05] Can language models solve graph problems in natural language? [pdf] [code]
11. [arxiv 2023.05] Gpt4graph: Can large language models understand graph structured data? an empirical evaluation and benchmarking [pdf]

3. GNN+LLM-based Papers

1. [arXiv 2023.10] Label-free Node Classification on Graphs with Large Language Models (LLMs) [pdf]
2. [arXiv_2023.09] One for All: Towards Training One Graph Model for All Classification Tasks [pdf]
3. [arXiv_2023.09] Prompt-based Node Feature Extractor for Few-shot Learning on Text-Attributed Graphs.[pdf]
4. [arxiv 2023.08] Simteg: A frustratingly simple approach improves textual graph learning. [pdf]
5. [arxiv 2023.05] Explanations as features: Llm-based features for text-attributed graphs. [pdf]
6. [arxiv 2023.05] Congrat: Self-supervised contrastive pretraining for joint graph and text embeddings. [pdf]
7. [arxiv 2023.04] Train your own GNN teacher: Graph-aware distillation on textual graphs. [pdf]
8. [arxiv 2023.04] Graph-toolformer: To empower llms with graph reasoning ability via prompt augmented by chatgpt. [pdf]
9. [ICLR 2023] Learning on large-scale text-attributed graphs via variational inference. [pdf]
10. [SIGIR 2023] Augmenting low-resource text classification with graph-grounded pre-training and prompting. [pdf]
11. [PMLR 2023] Enhancing activity prediction models in drug discovery with the ability to understand human language. [pdf]
12. [ICLR 2022] Node feature extraction by self-supervised multi-scale neighborhood prediction. [pdf]
13. [arxiv 2022.12] Multi-modal molecule structure-text model for text-based retrieval and editing. [pdf]
14. [arxiv 2022.09] A molecular multimodal foundation model associating molecule graphs with natural language. [pdf]
15. [NIPS 2021] Graphformers: Gnn-nested transformers for representation learning on textualgraph. [pdf]
16. [EMNLP 2021] Text2mol: Cross-modal molecule retrieval with natural language queries. [pdf]
17. [arxiv 2020.08] Graph-based modeling of online communities for fake news detection. [pdf]

Contributors

We thank all the contributors to this list. And more contributions are very welcome.