Out-of-Distribution Generalization in Graph Foundation Models

TL;DR

This survey reviews recent advances in out-of-distribution generalization for graph foundation models, highlighting challenges, strategies, and evaluation protocols in diverse graph learning scenarios.

Contribution

It is the first comprehensive survey focusing on OOD generalization in graph foundation models, organizing approaches and identifying future research directions.

Findings

Organized approaches based on task specificity and heterogeneity.

Summarized OOD handling strategies and pretraining objectives.

Discussed evaluation protocols and open research directions.

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.