Evolving graph attention networks for dynamic link prediction
PLOS One · 01.06.2026 · 21 (6) · e0349685
DOI: 10.1371/journal.pone.0349685 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 01.06.2026. Verfasst von Yucai Jiang und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Automotive and Mechanical Engineering, Lu'an Vocational Technical College, Lu'an, Anhui, China. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Outstanding Talents Training Program of Anhui Higher Education Institutions in 2021.
Abstract (Originalsprache)
Graph neural networks (GNNs), which learn node representations via aggregating their neighbors, have shown superior performance and become the de facto efficient toolkit for analyzing and learning from data with structured properties. However, most existing GNNs are designed for static graphs and assume fixed graph structures and node sets. In many real-world applications, graphs evolve continuously over time—with nodes and edges appearing or disappearing—rendering static models insufficient for capturing these temporal dynamics. In this paper, we propose Evolving Graph Attention Networks (EGAT), a novel framework for dynamic graph representation learning. Specifically, EGAT leverages the anisotropic attention mechanism of Graph Attention Networks (GATs) to capture complex inter-node relationships. Crucially, the multi-head attention weights of the GAT are evolved over time via a recurrent neural network (RNN), enabling the model to adaptively adjust the importance of different neighbors as the graph topology and relational dynamics change. This weight-evolving paradigm couples the anisotropic attention mechanism of GATs with a recurrent subnetwork, enabling the joint modeling of topological evolution and temporal relational dynamics. Extensive experiments on benchmark datasets demonstrate that the proposed model consistently outperforms state-of-the-art baselines.
Autor:innen und Institutionen
- School of Automotive and Mechanical Engineering, Lu'an Vocational Technical College, Lu'an, Anhui, China.
- School of Computer and Information, Anhui Polytechnic University, Wuhu, Anhui, China.
- Visual Computing Research Center, Shenzhen University, Shenzhen, Guangdong, China.
- School of Big Data and Artificial Intelligence, Anhui Institute of Information Technology, Wuhu, Anhui, China.
- School of Computer and Information, Anhui Normal University, Wuhu, Anhui, China.
ORCID-Profile: Rongying Shan
Förderung
- Outstanding Talents Training Program of Anhui Higher Education Institutions in 2021
Zitieren
APA
Jiang, Y., Shan, R., Fu, G., Li, Z., Sun, J., Bao, Z., & Wei, F. (2026). Evolving graph attention networks for dynamic link prediction. PLOS One, 21(6), e0349685. https://doi.org/10.1371/journal.pone.0349685
Vancouver
Jiang Y, Shan R, Fu G, Li Z, Sun J, Bao Z, et al. Evolving graph attention networks for dynamic link prediction. PLOS One. 2026;21(6):e0349685. doi:10.1371/journal.pone.0349685
BibTeX
@article{Jiang2026,
author = {Jiang, Yucai and Shan, Rongying and Fu, Gang and Li, Zhuolin and Sun, Jingjing and Bao, Zhongyun and Wei, Feifei},
title = {Evolving graph attention networks for dynamic link prediction},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {6},
pages = {e0349685},
doi = {10.1371/journal.pone.0349685}
}
EUVIMED