A bi-diffusion based layer-wise sampling method for deep learning in large graphs

Yu He, Shiyang Wen, Wenjin Wu, Yan Zhang, Siran Yang, Yuan Wei, Di Zhang, Guojie Song, Wei Lin, Liang Wang, Bo Zheng

Keywords: Layerwise Sampling, Graph Neural Networks, Attention Mechanism

Abstract:

The Graph Convolutional Network (GCN) and its variants are powerful models for graph representation learning and have recently achieved great success on many graph-based applications. However, most of them target on shallow models (e.g. 2 layers) on relatively small graphs. Very recently, although many acceleration methods have been developed for GCNs training,
it still remains a severe challenge how to scale GCN-like models to larger graphs and deeper layers due to the over-expansion of neighborhoods across layers. In this paper, to address the above challenge, we propose a novel layer-wise sampling strategy, which samples the nodes layer by layer conditionally based on the factors of the bi-directional diffusion between layers. In this way, we potentially restrict the time complexity linear to the number of layers, and construct a mini-batch of nodes with high local bi-directional influence (correlation). Further, we apply the self-attention mechanism to flexibly learn suitable weights for the sampled nodes, which allows the model to be able to incorporate both the first-order and higher-order proximities during a single layer propagation process without extra recursive propagation or skip connection. Extensive experiments on three large benchmark graphs demonstrate the effectiveness and efficiency of the proposed model.