FastGAE: Scalable graph autoencoders with stochastic subgraph decoding

Graph autoencoders (AE) and variational autoencoders (VAE) are powerful node embedding methods, but suffer from scalability issues. In this paper, we introduce FastGAE, a general framework to scale graph AE and VAE to large graphs with millions of nodes and edges. Our strategy, based on an effective...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Neural networks Jg. 142; S. 1 - 19
Hauptverfasser: Salha, Guillaume, Hennequin, Romain, Remy, Jean-Baptiste, Moussallam, Manuel, Vazirgiannis, Michalis
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States Elsevier Ltd 01.10.2021
Elsevier
Schlagworte:
Computer Science
Graph autoencoders
Graph convolutional networks
Graph variational autoencoders
Link prediction
Node clustering
Scalability
Link prediction
Graph autoencoders
Graph variational autoencoders
Graph convolutional networks
Scalability
Node clustering
ISSN:0893-6080, 1879-2782, 1879-2782
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Graph autoencoders (AE) and variational autoencoders (VAE) are powerful node embedding methods, but suffer from scalability issues. In this paper, we introduce FastGAE, a general framework to scale graph AE and VAE to large graphs with millions of nodes and edges. Our strategy, based on an effective stochastic subgraph decoding scheme, significantly speeds up the training of graph AE and VAE while preserving or even improving performances. We demonstrate the effectiveness of FastGAE on various real-world graphs, outperforming the few existing approaches to scale graph AE and VAE by a wide margin.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0893-6080
1879-2782
1879-2782
DOI:10.1016/j.neunet.2021.04.015