典型文献
Sampling Methods for Efficient Training of Graph Convolutional Networks: A Survey
文献摘要：
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.
文献关键词：
中图分类号：
作者姓名：
Xin Liu;Mingyu Yan;Lei Deng;Guoqi Li;Xiaochun Ye;Dongrui Fan
作者机构：
State Key Laboratory of Computer Architecture,Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100086;School of Computer Science and Technology,University of Chinese Academy of Sciences,Beijing 100049,China;State Key Laboratory of Computer Architecture,Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100086,China;Department of Precision Instrument,Center for Brain Inspired Computing Research,Tsinghua University,Beijing 100084,China
文献出处：
引用格式：
[1]Xin Liu;Mingyu Yan;Lei Deng;Guoqi Li;Xiaochun Ye;Dongrui Fan-.Sampling Methods for Efficient Training of Graph Convolutional Networks: A Survey)[J].自动化学报（英文版）,2022(02):205-234
A类：
B类：
Sampling,Methods,Efficient,Training,Graph,Convolutional,Networks,Survey,convolutional,networks,GCNs,have,received,significant,attention,from,various,research,fields,due,excellent,performance,learning,representations,Although,performs,well,compared,other,methods,still,faces,challenges,model,large,scale,graphs,conventional,way,requires,computation,storage,costs,Therefore,motivated,by,urgent,need,terms,efficiency,scalability,training,sampling,been,proposed,achieved,effect,In,this,paper,categorize,mechanisms,provide,comprehensive,survey,efficient,To,highlight,characteristics,differences,detailed,comparison,within,each,category,further,give,overall,comparative,analysis,categories,Finally,discuss,some,future,directions
AB值：
0.650566
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
