# RAGraph: A General Retrieval-Augmented Graph Learning Framework

arXiv: https://arxiv.org/abs/2410.23855 · HTML: https://mlsanity.com/paper/2410.23855/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 9 of its 139 references that are in the map.
- First posted on arXiv 31 Oct 2024.

## Placed in

- Retrieval-augmented generation / [Knowledge-graph and structured-knowledge RAG](https://mlsanity.com/rag/knowledge-graph-and-structured-knowledge-rag/)

## Builds on (most cited first, 9 of 9)

- [Strategies for Pre-training Graph Neural Networks](https://mlsanity.com/paper/1905.12265/) (2019)
- [Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphs](https://mlsanity.com/paper/1909.01515/) (2019)
- [Graph Prompt Learning: A Comprehensive Survey and Beyond](https://mlsanity.com/paper/2311.16534/) (2023)
- [Non-Homophilic Graph Pre-Training and Prompt Learning](https://mlsanity.com/paper/2408.12594/) (2024)
- [KnowPO: Knowledge-aware Preference Optimization for Controllable Knowledge Selection in Retrieval-Augmented Language Models](https://mlsanity.com/paper/2408.03297/) (2024)
- [Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuning](https://mlsanity.com/paper/2410.10360/) (2024)
- [Prompt Learning on Temporal Interaction Graphs](https://mlsanity.com/paper/2402.06326/) (2024)
- [Node-Time Conditional Prompt Learning In Dynamic Graphs](https://mlsanity.com/paper/2405.13937/) (2024)
- [A Survey of Few-Shot Learning on Graphs: from Meta-Learning to Pre-Training and Prompt Learning](https://mlsanity.com/paper/2402.01440/) (2024)

## Built on by (most cited first, 24 of 24)

- [Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective](https://mlsanity.com/paper/2412.09972/) (2024)
- [Hyper-RAG: Combating LLM Hallucinations using Hypergraph-Driven Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.08758/) (2025)
- [Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey](https://mlsanity.com/paper/2504.10499/) (2025)
- [Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement](https://mlsanity.com/paper/2505.12684/) (2025)
- [Graph is a Substrate Across Data Modalities](https://mlsanity.com/paper/2601.22384/) (2026)
- [MM-OpenFGL: A Comprehensive Benchmark for Multimodal Federated Graph Learning](https://mlsanity.com/paper/2601.22416/) (2026)
- [Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks](https://mlsanity.com/paper/2412.12456/) (2024)
- [MolSpectra: Pre-training 3D Molecular Representation with Multi-modal Energy Spectra](https://mlsanity.com/paper/2502.16284/) (2025)
- [GraphRAFT: Retrieval Augmented Fine-Tuning for Knowledge Graphs on Graph Databases](https://mlsanity.com/paper/2504.05478/) (2025)
- [GraphSearch: Agentic Search-Augmented Reasoning for Zero-Shot Graph Learning](https://mlsanity.com/paper/2601.08621/) (2026)
- [Multi-Domain Riemannian Graph Gluing for Building Graph Foundation Models](https://mlsanity.com/paper/2603.00618/) (2026)
- [GraphRunner: A Multi-Stage Framework for Efficient and Accurate Graph-Based Retrieval](https://mlsanity.com/paper/2507.08945/) (2025)
- [Sparse Causal Discovery with Generative Intervention for Unsupervised Graph Domain Adaptation](https://mlsanity.com/paper/2507.07621/) (2025)
- [EvoGraph-R1: Self-Evolving Multimodal Knowledge Hypergraphs for Agentic Retrieval](https://mlsanity.com/paper/2607.12764/) (2026)
- [Knowledge Fusion via Bidirectional Information Aggregation](https://mlsanity.com/paper/2507.08704/) (2025)
- [Embodiment Transfer Learning for Vision-Language-Action Models](https://mlsanity.com/paper/2511.01224/) (2025)
- [LoGIC: Budgeted Context Construction for Node-Level Graph In-Context Learning with Tabular Foundation Models](https://mlsanity.com/paper/2609.05955/) (2026)
- [GOSU: Retrieval-Augmented Generation with Global-Level Optimized Semantic Unit-Centric Framework](https://mlsanity.com/paper/2509.00449/) (2025)
- [Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG](https://mlsanity.com/paper/2509.25530/) (2025)
- [Rethinking Graph Domain Adaptation: A Spectral Contrastive Perspective](https://mlsanity.com/paper/2510.13254/) (2025)
- [AutothinkRAG: Complexity-Aware Control of Retrieval-Augmented Reasoning for Image-Text Interaction](https://mlsanity.com/paper/2603.05551/) (2026)
- [A Unified Graph Language Model for Multi-Domain Multi-Task Graph Alignment Instruction Tuning](https://mlsanity.com/paper/2605.12197/) (2026)
- [Are Common Substructures Transferable? Riemannian Graph Foundation Model with Neural Vector Bundles](https://mlsanity.com/paper/2606.03270/) (2026)
- [When Language Models Meet NeuroGraphs: Exploring Enhanced Agentic LLM Framework Towards Brain Network Analysis](https://mlsanity.com/paper/2607.22082/) (2026)

## Abstract (arXiv)

Graph Neural Networks (GNNs) have become essential in interpreting relational data across various domains, yet, they often struggle to generalize to unseen graph data that differs markedly from training instances. In this paper, we introduce a novel framework called General Retrieval-Augmented Graph Learning (RAGraph), which brings external graph data into the general graph foundation model to improve model generalization on unseen scenarios. On the top of our framework is a toy graph vector library that we established, which captures key attributes, such as features and task-specific label information. During inference, the RAGraph adeptly retrieves similar toy graphs based on key similarities in downstream tasks, integrating the retrieved data to enrich the learning context via the message-passing prompting mechanism. Our extensive experimental evaluations demonstrate that RAGraph significantly outperforms state-of-the-art graph learning methods in multiple tasks such as node classification, link prediction, and graph classification across both dynamic and static datasets. Furthermore, extensive testing confirms that RAGraph consistently maintains high performance without the need for task-specific fine-tuning, highlighting its adaptability, robustness, and broad applicability.