Sampling methods for efficient training of graph convolutional networks: A survey
It addresses efficiency and scalability issues for researchers and practitioners using GCNs, but is incremental as it reviews existing methods rather than proposing new ones.
This paper surveys sampling methods to tackle the high computational and storage costs of training Graph Convolutional Networks (GCNs) on large-scale graphs, categorizing them by sampling mechanisms and providing comparative analyses.
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 GCN model for large-scale graphs in a conventional way requires high computation and storage costs. Therefore, motivated by an urgent need in terms of efficiency and scalability in training GCN, sampling methods have been proposed and achieved a significant effect. In this paper, we categorize sampling methods based on the sampling mechanisms and provide a comprehensive survey of sampling methods for efficient training of GCN. To highlight the characteristics and differences of sampling methods, we present a detailed comparison within each category and further give an overall comparative analysis for the sampling methods in all categories. Finally, we discuss some challenges and future research directions of the sampling methods.