Sampling Methods for Efficient Training of Graph Convolutional Networks: A Survey

Graph convolutional networks (GCNs) have received significant attention from various research fields due to the excellent performance in learning graph representations. Although GCN performs well compared with other methods, it still faces challenges. Training a model for large-scale graphs conventional way requires high computation and storage costs. Therefore, motivated by an urgent need terms of efficiency scalability training GCN, sampling methods been proposed achieved effect. In this paper, we categorize based on mechanisms provide comprehensive survey efficient GCN. To highlight characteristics differences present detailed comparison within each category further give overall comparative analysis all categories. Finally, discuss some challenges future directions methods.