Weighted dynamic network link prediction based on graph autoencoder

With the development of deep learning, Graph Autoencoders (GAE) within unsupervised learning frameworks have been widely applied to representation learning in dynamic networks. However, existing methods typically assume that the node set remains fixed across all time slices and ignore edge weight in...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Information sciences Jg. 720; S. 122507
Hauptverfasser: Mei, Peng, Zhao, Yuhong, Wang, Jingyu, Liang, Yefei
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Inc 01.12.2025
Schlagworte:
Dynamic network
Graph attention
Graph autoencoder
Link prediction
Unsupervised learning
Link prediction
Graph autoencoder
Dynamic network
Graph attention
Unsupervised learning
ISSN:0020-0255
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:With the development of deep learning, Graph Autoencoders (GAE) within unsupervised learning frameworks have been widely applied to representation learning in dynamic networks. However, existing methods typically assume that the node set remains fixed across all time slices and ignore edge weight information, which limits the ability to capture network dynamics and distinguish the strength of node relationships. To address these issues, this paper proposes a weighted dynamic network link prediction framework based on GAE, called GAE_GGLA. This framework introduces an alignment module that can handle non-fixed node sets to adapt to dynamic network environments. Additionally, the edge weight matrix is used as a bias term in the graph attention network to calculate attention coefficients, guiding the learning of node features and enhancing their representational capacity. Furthermore, the GAE encoder employs graph convolution network (GCN) and long short-term memory (LSTM) networks to capture, respectively, structural features and temporal evolution. The alignment module connects different node sets through adjacent time slices, ensuring the continuity and consistency of network information. Finally, the GAE decoder reconstructs the adjacency matrix of the original graph to achieve link prediction. Experiments conducted on five different datasets demonstrate that the proposed method significantly outperforms state-of-the-art baselines. •Introduced a Graph Auto Encoder-based node feature learning method.•Solved the non fixed problem of time slice node set through alignment module.•Validated the framework's effectiveness through extensive experiments.
ISSN:0020-0255
DOI:10.1016/j.ins.2025.122507