RAGraph: A General Retrieval-Augmented Graph Learning Framework
This addresses generalization issues in graph learning for applications in domains like social networks or bioinformatics, though it appears incremental as it builds on existing retrieval-augmented and graph foundation model concepts.
The paper tackles the problem of graph neural networks struggling to generalize to unseen graph data by introducing RAGraph, a retrieval-augmented framework that uses external graph data to enhance learning, resulting in significant outperformance over state-of-the-art methods in tasks like node classification and link prediction across various datasets.
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.