Graph Foundation Models: A Comprehensive Survey

2025-05-21

AI Summary

Graph-structured data exhibit non-Euclidean geometry and complex relational semantics, posing fundamental challenges for foundational modeling. To address this, we systematically advance Graph Foundation Models (GFMs) by proposing the first modular 3D taxonomy—unifying backbone architectures, pretraining strategies, and adaptation mechanisms—while formalizing three generalization paradigms: generic, task-level, and domain-level. We tackle core challenges including structural alignment and heterogeneity modeling by integrating GNNs, Transformers, contrastive learning, masked graph autoencoding, and prompt-based fine-tuning, enabling joint optimization of graph structure modeling, semantic representation, and cross-task transfer. Furthermore, we establish a theoretical framework characterizing GFMs’ transferability and emergent capabilities, and release a unified open-source resource library. This work lays critical infrastructure for general intelligence over structured data.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Knowledge Representation and Reasoning: Other Foundations of Knowledge Representation & Reasoning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

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.

Problem

• Extending foundation models to non-Euclidean graph data
• Developing scalable general-purpose intelligence for structured data
• Addressing challenges in structural alignment and heterogeneity

Innovation

• Graph Foundation Models enable scalable structured data intelligence
• Modular framework includes backbone architectures and pretraining strategies
• Addresses challenges like structural alignment and heterogeneity