Event-Aware Prompt Learning for Dynamic Graphs

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yu, Xingtong, Liang, Ruijuan, Jiang, Renhe, Li, Dongyuan, Zhao, Yunxiao, Zhang, Xinming, Fang, Yuan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910243883057152
author Yu, Xingtong
Liang, Ruijuan
Jiang, Renhe
Li, Dongyuan
Zhao, Yunxiao
Zhang, Xinming
Fang, Yuan
author_facet Yu, Xingtong
Liang, Ruijuan
Jiang, Renhe
Li, Dongyuan
Zhao, Yunxiao
Zhang, Xinming
Fang, Yuan
contents Real-world graph typically evolve via a series of events, modeling dynamic interactions between objects across various domains. For dynamic graph learning, dynamic graph neural networks (DGNNs) have emerged as popular solutions. Recently, prompt learning methods have been explored on dynamic graphs. However, existing methods generally focus on capturing the relationship between nodes and time, while overlooking the impact of historical events. In this paper, we propose EVP, an event-aware dynamic graph prompt learning framework that can serve as a plug-in to existing methods, enhancing their ability to leverage historical events knowledge. First, we extract a series of historical events for each node and introduce an event adaptation mechanism to align the fine-grained characteristics of these events with downstream tasks. Second, we propose an event aggregation mechanism to effectively integrate historical knowledge into node representations. Finally, we conduct extensive experiments on four public datasets to evaluate and analyze EVP.
format Preprint
id arxiv_https___arxiv_org_abs_2510_11339
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Event-Aware Prompt Learning for Dynamic Graphs
Yu, Xingtong
Liang, Ruijuan
Jiang, Renhe
Li, Dongyuan
Zhao, Yunxiao
Zhang, Xinming
Fang, Yuan
Machine Learning
Artificial Intelligence
Real-world graph typically evolve via a series of events, modeling dynamic interactions between objects across various domains. For dynamic graph learning, dynamic graph neural networks (DGNNs) have emerged as popular solutions. Recently, prompt learning methods have been explored on dynamic graphs. However, existing methods generally focus on capturing the relationship between nodes and time, while overlooking the impact of historical events. In this paper, we propose EVP, an event-aware dynamic graph prompt learning framework that can serve as a plug-in to existing methods, enhancing their ability to leverage historical events knowledge. First, we extract a series of historical events for each node and introduce an event adaptation mechanism to align the fine-grained characteristics of these events with downstream tasks. Second, we propose an event aggregation mechanism to effectively integrate historical knowledge into node representations. Finally, we conduct extensive experiments on four public datasets to evaluate and analyze EVP.
title Event-Aware Prompt Learning for Dynamic Graphs
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2510.11339