Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.15116 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913850081673216 |
|---|---|
| author | Wang, Zehong Liu, Zheyuan Ma, Tianyi Li, Jiazheng Zhang, Zheyuan Fu, Xingbo Li, Yiyang Yuan, Zhengqing Song, Wei Ma, Yijun Zeng, Qingkai Chen, Xiusi Zhao, Jianan Li, Jundong Jiang, Meng Lio, Pietro Chawla, Nitesh Zhang, Chuxu Ye, Yanfang |
| author_facet | Wang, Zehong Liu, Zheyuan Ma, Tianyi Li, Jiazheng Zhang, Zheyuan Fu, Xingbo Li, Yiyang Yuan, Zhengqing Song, Wei Ma, Yijun Zeng, Qingkai Chen, Xiusi Zhao, Jianan Li, Jundong Jiang, Meng Lio, Pietro Chawla, Nitesh Zhang, Chuxu Ye, Yanfang |
| contents | Graph-structured data pervades domains such as social networks, biological systems, knowledge graphs, and recommender systems. While foundation models have transformed natural language processing, vision, and multimodal learning through large-scale pretraining and generalization, extending these capabilities to graphs -- characterized by non-Euclidean structures and complex relational semantics -- poses unique challenges and opens new opportunities. To this end, Graph Foundation Models (GFMs) aim to bring scalable, general-purpose intelligence to structured data, enabling broad transfer across graph-centric tasks and domains. This survey provides a comprehensive overview of GFMs, unifying diverse efforts under a modular framework comprising three key components: backbone architectures, pretraining strategies, and adaptation mechanisms. We categorize GFMs by their generalization scope -- universal, task-specific, and domain-specific -- and review representative methods, key innovations, and theoretical insights within each category. Beyond methodology, we examine theoretical foundations including transferability and emergent capabilities, and highlight key challenges such as structural alignment, heterogeneity, scalability, and evaluation. Positioned at the intersection of graph learning and general-purpose AI, GFMs are poised to become foundational infrastructure for open-ended reasoning over structured data. This survey consolidates current progress and outlines future directions to guide research in this rapidly evolving field. Resources are available at https://github.com/Zehong-Wang/Awesome-Foundation-Models-on-Graphs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_15116 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Graph Foundation Models: A Comprehensive Survey Wang, Zehong Liu, Zheyuan Ma, Tianyi Li, Jiazheng Zhang, Zheyuan Fu, Xingbo Li, Yiyang Yuan, Zhengqing Song, Wei Ma, Yijun Zeng, Qingkai Chen, Xiusi Zhao, Jianan Li, Jundong Jiang, Meng Lio, Pietro Chawla, Nitesh Zhang, Chuxu Ye, Yanfang Machine Learning Artificial Intelligence Social and Information Networks Graph-structured data pervades domains such as social networks, biological systems, knowledge graphs, and recommender systems. While foundation models have transformed natural language processing, vision, and multimodal learning through large-scale pretraining and generalization, extending these capabilities to graphs -- characterized by non-Euclidean structures and complex relational semantics -- poses unique challenges and opens new opportunities. To this end, Graph Foundation Models (GFMs) aim to bring scalable, general-purpose intelligence to structured data, enabling broad transfer across graph-centric tasks and domains. This survey provides a comprehensive overview of GFMs, unifying diverse efforts under a modular framework comprising three key components: backbone architectures, pretraining strategies, and adaptation mechanisms. We categorize GFMs by their generalization scope -- universal, task-specific, and domain-specific -- and review representative methods, key innovations, and theoretical insights within each category. Beyond methodology, we examine theoretical foundations including transferability and emergent capabilities, and highlight key challenges such as structural alignment, heterogeneity, scalability, and evaluation. Positioned at the intersection of graph learning and general-purpose AI, GFMs are poised to become foundational infrastructure for open-ended reasoning over structured data. This survey consolidates current progress and outlines future directions to guide research in this rapidly evolving field. Resources are available at https://github.com/Zehong-Wang/Awesome-Foundation-Models-on-Graphs. |
| title | Graph Foundation Models: A Comprehensive Survey |
| topic | Machine Learning Artificial Intelligence Social and Information Networks |
| url | https://arxiv.org/abs/2505.15116 |