2020/02/05 by Salha, Guillaume, Hennequin, Romain, Remy, Jean-Baptiste +2
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Social and Information Networks (cs.SI)
paper · doi:10.48550/arxiv.2002.01910
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.