Retrieving Minimal and Sufficient Reasoning Subgraphs with Graph Foundation Models for Path-aware GraphRAG

2026-03-07

AI Summary

This work addresses the limitations of existing GraphRAG methods, which rely on heuristic rules in cold-start scenarios and struggle to produce reasoning subgraphs that are both structurally concise and informationally complete, resulting in poor generalization. To overcome this, we propose a cross-domain subgraph retrieval framework based on a pre-trained Graph Foundation Model (GFM) that directly generates multi-hop path-aware reasoning subgraphs in response to queries. An unsupervised information bottleneck mechanism is introduced to automatically distill a minimal yet sufficient “core evidence set.” By reorganizing relational paths into interpretable contextual prompts, our approach significantly enhances retrieval quality and answer generation performance on multi-hop question answering benchmarks while maintaining efficiency, marking the first successful reuse of graph foundation models for cross-domain subgraph retrieval.

Technology Category

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

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Graph-based retrieval-augmented generation (GraphRAG) exploits structured knowledge to support knowledge-intensive reasoning. However, most existing methods treat graphs as intermediate artifacts, and the few subgraph-based retrieval methods depend on heuristic rules coupled with domain-specific distributions. They fail in typical cold-start scenarios where data in target domains is scarce, thus yielding reasoning contexts that are either informationally incomplete or structurally redundant. In this work, we revisit retrieval from a structural perspective, and propose GFM-Retriever that directly responds to user queries with a subgraph, where a pre-trained Graph Foundation Model acts as a cross-domain Retriever for multi-hop path-aware reasoning. Building on this perspective, we repurpose a pre-trained GFM from an entity ranking function into a generalized retriever to support cross-domain retrieval. On top of the retrieved graph, we further derive a label-free subgraph selector optimized by a principled Information Bottleneck objective to identify the query-conditioned subgraph, which contains informationally sufficient and structurally minimal golden evidence in a self-contained"core set". To connect structure with generation, we explicitly extract and reorganize relational paths as in-context prompts, enabling interpretable reasoning. Extensive experiments on multi-hop question answering benchmarks demonstrate that GFM-Retriever achieves state-of-the-art performance in both retrieval quality and answer generation, while maintaining efficiency.

Problem

• GraphRAG
• subgraph retrieval
• cold-start
• multi-hop reasoning
• structured knowledge

Innovation

• Graph Foundation Model
• Subgraph Retrieval
• Information Bottleneck
• Path-aware Reasoning
• GraphRAG