A Survey of Cross-domain Graph Learning: Progress and Future Directions

2025-03-14

AI Summary

Current graph learning models exhibit limited cross-domain transferability, hindering the development of graph foundation models. To address this, this paper presents a systematic survey of cross-domain graph learning, proposing— for the first time—a taxonomy grounded in information type (structural, feature-based, or hybrid) to clarify methodological evolution and identify future research directions. Leveraging insights from cross-domain paradigms in computer vision and natural language processing, we critically analyze, categorize, and reconceptualize existing approaches. We introduce the first unified taxonomy encompassing mainstream methodologies and publicly release an open, continuously updated resource repository. Our work establishes a theoretical framework and practical guidelines for cross-domain graph representation learning, thereby advancing the generalization and standardization of graph foundation models.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Knowledge Representation and Reasoning: Other Foundations of Knowledge Representation & Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches 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
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

Graph learning plays a vital role in mining and analyzing complex relationships involved in graph data, which is widely used in many real-world applications like transaction networks and communication networks. Foundation models in CV and NLP have shown powerful cross-domain capabilities that are also significant in graph domains. However, existing graph learning approaches struggle with cross-domain tasks. Inspired by successes in CV and NLP, cross-domain graph learning has once again become a focal point of attention to realizing true graph foundation models. In this survey, we present a comprehensive review and analysis of existing works on cross-domain graph learning. Concretely, we first propose a new taxonomy, categorizing existing approaches based on the learned cross-domain information: structure, feature, and structure-feature mixture. Next, we systematically survey representative methods in these categories. Finally, we discuss the remaining limitations of existing studies and highlight promising avenues for future research. Relevant papers are summarized and will be consistently updated at: https://github.com/cshhzhao/Awesome-Cross-Domain-Graph-Learning.

Problem

• Addresses challenges in cross-domain graph learning tasks.
• Proposes taxonomy for cross-domain graph learning approaches.
• Identifies future research directions in graph foundation models.

Innovation

• Proposes taxonomy for cross-domain graph learning
• Surveys methods based on structure and features
• Identifies future research directions in graph learning