期刊
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
卷 9, 期 2, 页码 205-234出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JAS.2021.1004311
关键词
Efficient training; graph convolutional networks (GCNs); graph neural networks (GNNs); sampling method
资金
- National Natural Science Foundation of China [61732018, 61872335, 61802367, 61876215]
- Strategic Priority Research Program of Chinese Academy of Sciences [XDC05000000]
- Beijing Academy of Artificial Intelligence (BAAI)
- Open Project Program of the State Key Laboratory of Mathematical Engineering and Advanced Computing [2019A07]
- Open Project of Zhejiang Laboratory
- Institute for Guo Qiang, Tsinghua University
This paper categorizes and provides a comprehensive survey of sampling methods for efficient training of GCN. It compares the characteristics and differences of these methods in detail within each category, and further gives an overall analysis across all categories. Additionally, it discusses the challenges and future research directions of sampling methods.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据