Out-of-Distribution Generalization in Graph Foundation Models

2026-01-28

AI Summary

Graph Foundation Models (GFMs) face significant challenges in out-of-distribution (OOD) generalization, particularly when confronted with distribution shifts arising from changes in graph structure, semantics, modalities, or task formulations. This work presents the first systematic survey of recent advances in OOD generalization for GFMs, proposing a unified problem formulation and categorizing existing approaches based on whether the downstream task setting is fixed. It synthesizes key aspects including distribution shift modeling, cross-task generalization mechanisms, and robustness evaluation protocols, while summarizing prevalent experimental setups. The study further identifies current limitations and outlines a clear technical roadmap to guide future research in enhancing the OOD robustness and adaptability of graph foundation models.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

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: Robustness and generalizability of Web mining methods

Abstract

Graphs are a fundamental data structure for representing relational information in domains such as social networks, molecular systems, and knowledge graphs. However, graph learning models often suffer from limited generalization when applied beyond their training distributions. In practice, distribution shifts may arise from changes in graph structure, domain semantics, available modalities, or task formulations. To address these challenges, graph foundation models (GFMs) have recently emerged, aiming to learn general-purpose representations through large-scale pretraining across diverse graphs and tasks. In this survey, we review recent progress on GFMs from the perspective of out-of-distribution (OOD) generalization. We first discuss the main challenges posed by distribution shifts in graph learning and outline a unified problem setting. We then organize existing approaches based on whether they are designed to operate under a fixed task specification or to support generalization across heterogeneous task formulations, and summarize the corresponding OOD handling strategies and pretraining objectives. Finally, we review common evaluation protocols and discuss open directions for future research. To the best of our knowledge, this paper is the first survey for OOD generalization in GFMs.

Problem

• Out-of-Distribution Generalization
• Graph Foundation Models
• Distribution Shift
• Graph Learning
• Generalization

Innovation

• Graph Foundation Models
• Out-of-Distribution Generalization
• Distribution Shift
• Pretraining Objectives
• Heterogeneous Task Generalization