Graph Foundation Models: A Comprehensive Survey

TL;DR

This survey reviews the development of Graph Foundation Models (GFMs), highlighting their architectures, pretraining, and adaptation strategies, and discusses their potential to enable scalable, general-purpose reasoning over structured graph data.

Contribution

It provides a comprehensive, modular overview of GFMs, categorizing them by scope, and discusses theoretical foundations, challenges, and future research directions.

Findings

GFMs unify diverse graph learning efforts under a modular framework.

The survey identifies key challenges like heterogeneity and scalability.

GFMs have potential to become foundational for reasoning over structured 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.