Multi-view representation model based on graph autoencoder

Graph representation learning is a hot topic in non-Euclidean data in various domains, such as social networks, biological networks, etc. When some data labels are missing, graph autoencoder and graph variational autoencoder can perform outstanding abilities on node clustering or link prediction tas...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Information sciences Jg. 632; S. 439 - 453
Hauptverfasser: Li, Jingci, Lu, Guangquan, Wu, Zhengtian, Ling, Fuqing
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Inc 01.06.2023
Schlagworte:
Graph autoencoder
Graph representation learning
Multi-view learning
Unsupervised learning
Graph representation learning
Graph autoencoder
Unsupervised learning
Multi-view learning
ISSN:0020-0255, 1872-6291
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Graph representation learning is a hot topic in non-Euclidean data in various domains, such as social networks, biological networks, etc. When some data labels are missing, graph autoencoder and graph variational autoencoder can perform outstanding abilities on node clustering or link prediction tasks. However, most existing graph representation learning ignores data's multi-modal features and takes the node features and graph structure features as one view. Besides, most graph autoencoders only reconstruct the node feature matrix or adjacency matrix, which does not fully use the hidden representation information. In this paper, we propose a multi-view representation model based on graph autoencoder, which can employ the global structure topology, latent local topology, and feature relative information. Meanwhile, we add another decoder to reconstruct the node feature matrix as an auxiliary task. In this way, the proposed framework can utilize the learned representation sufficiently. We validate the effectiveness of our framework on four datasets, and the experimental results demonstrate superior performance compared with other advanced frameworks.
ISSN:0020-0255
1872-6291
DOI:10.1016/j.ins.2023.02.092