Graph Foundation Models for Recommendation: A Comprehensive Survey
Overview
- Paper: Graph Foundation Models for Recommendation: A Comprehensive Survey
- Authors: Bin Wu, Yihang Wang, Yuanhao Zeng, Jiawei Liu, Jiashu Zhao, Cheng Yang, et al. (10 authors total)
- Published: 2025-02-12
- Source: https://arxiv.org/abs/2502.08346
- Type: Survey
- Section: Recommender Engine Surveys
- Provides a unified perspective that consolidates scattered related work into a comparable framework.
- Gives a clear decomposition of method components (representation learning, retrievers, re-rankers, planners, generators, feedback mechanisms) to aid engineering adoption.
- Offers reproducible benchmarks, datasets, or classification tables, lowering the entry barrier for subsequent researchers.
- Discusses interfaces with emerging paradigms such as LLM tool calling, reinforcement learning, and multi-agent collaboration.
- Explicitly lists open problems: evaluation trustworthiness, latency and cost, hallucination and safety, and cross-lingual / multimodal extension.
- 2019-2021: BERT-based re-ranking and DPR established the foundations of neural retrieval.
- 2022-2023: RAG and FreshLLM drove fusion of retrieval and generation.
- 2024 onward: Conversational / agentic search and Gen-RecSys expanded rapidly.
- 2025-2026: RL-trained search agents, Deep Research, and GraphRAG are emerging growth areas.
- Datasets: MS MARCO, BEIR, Natural Questions, domain-specific corpora, and public recommendation datasets.
- Metrics: nDCG@10, MRR, Recall@k, Hit@k, human preference, task success rate, latency, and token cost.
- Baselines: BM25, dense retrieval, cross-encoder re-ranking, retrieval-free LLMs, commercial search APIs.
- Ablations: the contribution of each module (retrieval steps, re-ranking depth, training data scale) to final quality.
- A Comprehensive Review on Harnessing Large Language Models to Overcome…
- A Comprehensive Survey on Cross-Domain Recommendation
- A Comprehensive Survey on Retrieval Methods in Recommender Systems
- A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)
- A Survey of Generative Search and Recommendation in the Era of Large LLMs
- A Survey on LLM-powered Agents for Recommender Systems
- Original paper: Graph Foundation Models for Recommendation: A Comprehensive Survey. See the arXiv link above.
One-line summary
A systematic survey of Graph Foundation Models (GFMs) for recommender systems, covering a taxonomy of approaches, methodological details, and open challenges.
Background and motivation
Recommender systems have long faced challenges around efficiency, scalability, and understanding user intent in large-scale search and personalization systems. Traditional pipeline approaches often treat retrieval, ranking, and generation in isolation, which struggles to meet LLM-era demands for natural-language interaction, multi-hop reasoning, and up-to-date knowledge.
As the paper's abstract states:
> 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.
Core contributions
Timeline of the research landscape
Evaluation paradigms
Typical benchmarks and trends covered by surveys in this area include:
Quantitative results should be verified against the original PDF tables; this report is based on the abstract and public metadata.
Key insights
1. Architecture: cascaded retrieve-rank-generate remains mainstream, but the agentic paradigm is making "whether and how many times to retrieve" itself a learnable decision. 2. Data: high-quality instruction data and click/session logs are both 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 should be cross-validated with human evaluation. 4. Product: latency, cost, explainability, and safety are hard constraints for industrial deployment — academic benchmarks alone are insufficient.
Limitations and future directions
Commonly noted limitations include: lack of unified benchmarks, non-reproducible private data, LLM evaluation bias, and safety/cost constraints for agentic systems. Future work includes finer-grained process supervision, joint retrieval-reasoning training, enterprise metadata governance, and multimodal / cross-lingual consistency. For recommendation specifically, causal and fairness constraints and deeper integration with knowledge graphs and structured databases are promising directions.