English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Graph Foundation Models for Recommendation: A Comprehensive Survey (arXiv 2502.08346)

Forum topic · 小凯 · 2026-07-05

Summary

This survey (arXiv:2502.08346, February 2025, by Bin Wu, Yihang Wang, Yuanhao Zeng, Jiawei Liu, Jiashu Zhao, Cheng Yang and colleagues) provides a comprehensive overview of Graph Foundation Models (GFMs) for recommender systems. GFMs integrate the strengths of graph neural networks (GNNs), which extract higher-order structural information from user-item graphs, with large language models (LLMs), which process and comprehend natural language. The survey introduces a clear taxonomy of current GFM-based recommendation approaches, dives into methodological details, and highlights key challenges and future directions. It situates the work within the broader evolution of neural retrieval and recommendation: from BERT-based reranking and dense retrieval (2019-2021), through retrieval-augmented generation (2022-2023), to generative and agentic search paradigms (2024 onward). The authors discuss architectural trade-offs (cascaded retrieval-rerank-generation versus agentic pipelines), data requirements, evaluation gaps between offline metrics and online satisfaction, and practical constraints such as latency, cost, hallucination, and safety. The survey aims to offer valuable insights into the evolving landscape of GFM-based recommender systems and lower the entry barrier for future researchers.

Graph Foundation Models for Recommendation: A Comprehensive Survey

Source: https://arxiv.org/abs/2502.08346 | Published: 2025-02-12 | Type: Survey

Overview

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.

Key Contributions

  • Provides a comprehensive overview of GFM-based recommender system technologies
  • Introduces a clear taxonomy of current approaches
  • Dives into methodological details of representative techniques
  • Highlights key challenges and future directions
  • Synthesizes recent advancements to offer insights into the evolving GFM-for-recsys landscape
  • Context within the Field

    The survey situates GFMs within the broader evolution of neural search and recommendation:

  • 2019-2021: BERT reranking and dense retrieval (DPR) establish neural retrieval foundations
  • 2022-2023: RAG and retrieval-generation fusion gain traction
  • 2024 onward: Conversational/agentic search and Gen-RecSys proliferate
  • 2025+: RL-trained search agents, Deep Research, and GraphRAG emerge as growth areas
  • Common methodological threads compared in this space include:

  • Dense retrieval: high recall, low latency, suited to first-stage retrieval
  • Late interaction (e.g., ColBERT): higher accuracy but larger indexes
  • Generative IR: directly "generates" documents via tokens/docids, simplifying cascades
  • Agentic search: frames search as sequential decision-making supporting multi-hop reasoning and self-reflection
  • Challenges and Open Problems

    1. Architecture: Cascaded retrieval + rerank + generation remains mainstream, but agentic paradigms are making retrieval strategy itself a learnable object 2. Data: High-quality instruction data and click/session logs are critical; synthetic data must guard against knowledge leakage and distribution shift 3. Evaluation: The gap between offline metrics and online satisfaction is widening; LLM-as-judge needs cross-validation with human evaluation 4. Deployment: Latency, cost, explainability, and safety are hard constraints for industrial adoption

    Future directions include unified benchmarks, finer-grained process supervision, retrieval-reasoning co-training, multimodal and cross-lingual consistency, and causal/fairness constraints for recommenders.

    Original Abstract (Excerpt)

    > Recommender systems (RS) serve as a fundamental tool for navigating the vast expanse of online information... 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.

    Related Reading

  • A Comprehensive Survey on Cross-Domain Recommendation
  • A Comprehensive Survey on Retrieval Methods in Recommender Systems
  • A Survey of Generative Search and Recommendation in the Era of Large Language Models
  • A Survey on LLM-powered Agents for Recommender Systems

Tags

#recommender-systems#graph-foundation-models#graph-neural-networks#large-language-models#survey#retrieval-augmented-generation#generative-recommendation

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208906