RAGraph: A General Retrieval-Augmented Graph Learning Framework

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Xinke, Qiu, Rihong, Xu, Yongxin, Zhang, Wentao, Zhu, Yichen, Zhang, Ruizhe, Fang, Yuchen, Chu, Xu, Zhao, Junfeng, Wang, Yasha
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915052397789184
author Jiang, Xinke
Qiu, Rihong
Xu, Yongxin
Zhang, Wentao
Zhu, Yichen
Zhang, Ruizhe
Fang, Yuchen
Chu, Xu
Zhao, Junfeng
Wang, Yasha
author_facet Jiang, Xinke
Qiu, Rihong
Xu, Yongxin
Zhang, Wentao
Zhu, Yichen
Zhang, Ruizhe
Fang, Yuchen
Chu, Xu
Zhao, Junfeng
Wang, Yasha
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_23855
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RAGraph: A General Retrieval-Augmented Graph Learning Framework
Jiang, Xinke
Qiu, Rihong
Xu, Yongxin
Zhang, Wentao
Zhu, Yichen
Zhang, Ruizhe
Fang, Yuchen
Chu, Xu
Zhao, Junfeng
Wang, Yasha
Machine Learning
Artificial Intelligence
Social and Information Networks
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.
title RAGraph: A General Retrieval-Augmented Graph Learning Framework
topic Machine Learning
Artificial Intelligence
Social and Information Networks
url https://arxiv.org/abs/2410.23855