FastGAE: Scalable Graph Autoencoders with Stochastic Subgraph Decoding
Machine Learning
2021-04-14 v5 Social and Information Networks
Machine Learning
Abstract
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.
Cite
@article{arxiv.2002.01910,
title = {FastGAE: Scalable Graph Autoencoders with Stochastic Subgraph Decoding},
author = {Guillaume Salha and Romain Hennequin and Jean-Baptiste Remy and Manuel Moussallam and Michalis Vazirgiannis},
journal= {arXiv preprint arXiv:2002.01910},
year = {2021}
}
Comments
Accepted for publication in Elsevier's Neural Networks journal