Graph Foundation Models for Recommendation: A Comprehensive Survey

2025-02-12

AI Summary

This paper addresses the dual challenges of user-item relational modeling and multi-source semantic understanding in recommender systems. We propose the first comprehensive taxonomy of Graph Foundation Models (GFMs) for recommendation, systematically unifying graph neural networks’ structural modeling capability with large language models’ textual comprehension strength to jointly model graph topology and cross-modal semantics. We formally categorize GFM-based recommendation into three fusion paradigms—embedding-level, representation-level, and prompt-level—marking the first explicit classification of its kind. The work identifies and analyzes three core challenges: cross-modal alignment, scalable training, and interpretability. Our survey framework comprehensively covers 2020–2024 mainstream advances, synthesizing algorithmic design principles, industrial deployment considerations, and theoretical foundations. This taxonomy serves as a systematic reference for researchers and practitioners advancing GFM-based recommendation.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Recommender Systems
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Recommender systems (RS) serve as a fundamental tool for navigating the vast expanse of online information, with deep learning advancements playing an increasingly important role in improving ranking accuracy. Among these, graph neural networks (GNNs) excel at extracting higher-order structural information, while large language models (LLMs) are designed to process and comprehend natural language, making both approaches highly effective and widely adopted. Recent research has focused on graph foundation models (GFMs), which integrate the strengths of GNNs and LLMs to model complex RS problems more efficiently by leveraging the graph-based structure of user-item relationships alongside textual understanding. In this survey, we provide a comprehensive overview of GFM-based RS technologies by introducing a clear taxonomy of current approaches, diving into methodological details, and highlighting key challenges and future directions. By synthesizing recent advancements, we aim to offer valuable insights into the evolving landscape of GFM-based recommender systems.

Problem

• Graph Foundation Models for Recommendation
• Integrate GNNs and LLMs
• Enhance user-item relationship modeling

Innovation

• Integrates GNNs and LLMs
• Models user-item graph structures
• Enhances recommendation with textual understanding