A Simple Training Strategy for Graph Autoencoder

Abstract

Graph autoencoder can map graph data into a low-dimensional space. It is a powerful graph embedding method applied in graph analytics to reduce the computational cost. The training algorithm of a graph autoencoder searches the weight setting for preserving most graph information of the graph data with reduced dimensionality. This paper presents a simple training strategy, which can improve the training performance without significantly increasing time complexity. This strategy can flexibly fit many existing training algorithms. The experimental results confirm the effectiveness of this strategy.