Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

4-2025

Abstract

Dynamic graphs capture evolving interactions between entities, such as in social networks, online learning platforms, and crowdsourcing projects. For dynamic graph modeling, dynamic graph neural networks (DGNNs) have emerged as a mainstream technique. However, they are generally pre-trained on the link prediction task, leaving a significant gap from the objectives of downstream tasks such as node classification. To bridge the gap, prompt-based learning has gained traction on graphs, but most existing efforts focus on static graphs and neglect the evolution of dynamic graphs. In this paper, we propose DYGPROMPT, a novel pre-training and prompt learning framework for dynamic graph modeling. First, we design dual prompts to address the discrepancy in both task objectives and temporal variations across pre-training and downstream tasks. Second, we recognize that node and time patterns often characterize each other, and propose dual condition-nets to model the evolving node-time patterns in downstream tasks. Finally, we thoroughly evaluate and analyze DYGPROMPT through extensive experiments on four public datasets.

Discipline

Graphics and Human Computer Interfaces

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

Proceedings of the Thirteenth International Conference on Learning Representations, Singapore, April 24-28

First Page

1

Last Page

20

Identifier

10.48550/arXiv.2405.13937

Publisher

ICLR

City or Country

Singapore

Additional URL

https://doi.org/10.48550/arXiv.2405.13937

Download

Share

COinS