Retrieval Augmented Generation for Dynamic Graph Modeling

TL;DR

This paper introduces RAG4DyG, a novel framework that enhances dynamic graph modeling by incorporating relevant examples through retrieval and generation, improving adaptability and prediction accuracy in evolving graph structures.

Contribution

The paper proposes a retrieval-augmented framework with contrastive learning and graph fusion strategies for dynamic graph modeling, addressing limitations of existing methods.

Findings

Improves predictive accuracy on real-world datasets.

Effective in both transductive and inductive scenarios.

Enhances adaptability to unseen nodes and evolving graphs.

Abstract

Modeling dynamic graphs, such as those found in social networks, recommendation systems, and e-commerce platforms, is crucial for capturing evolving relationships and delivering relevant insights over time. Traditional approaches primarily rely on graph neural networks with temporal components or sequence generation models, which often focus narrowly on the historical context of target nodes. This limitation restricts the ability to adapt to new and emerging patterns in dynamic graphs. To address this challenge, we propose a novel framework, Retrieval-Augmented Generation for Dynamic Graph modeling (RAG4DyG), which enhances dynamic graph predictions by incorporating contextually and temporally relevant examples from broader graph structures. Our approach includes a time- and context-aware contrastive learning module to identify high-quality demonstrations and a graph fusion strategy to effectively integrate these examples with historical contexts. The proposed framework is designed to be effective in both transductive and inductive scenarios, ensuring adaptability to previously unseen nodes and evolving graph structures. Extensive experiments across multiple real-world datasets demonstrate the effectiveness of RAG4DyG in improving predictive accuracy and adaptability for dynamic graph modeling. The code and datasets are publicly available at https://github.com/YuxiaWu/RAG4DyG.