Local feature aggregation algorithm based on graph convolutional network  

作　　者：Hao WANG Liyan DONG Minghui SUN 

机构地区：[1]College of Computer Science and Technology,Jilin University,Changchun 130012,China [2]Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education,Jilin University,Changchun 130012,China

出　　处：《Frontiers of Computer Science》2022年第3期203-205,共3页中国计算机科学前沿（英文版）

基　　金：the National Natural Science Foundation of China(Grant Nos.61272209,61872164);in part by the Program of Science and Technology Development Plan of Jilin Province of China(20190302032GX);in part by the Fundamental Research Funds for the Central Universities(Jilin University).

摘　　要：1Introduction and main contributions In the field of social networks and knowledge graphs,semi-supervised learning models based on graph convolutional networks have achieved great success in node classification[1],inductive node embedding[2],link prediction[3],and recommend.These semi-supervised models based on graph convolutional network(GCN)[4]expect to obtain more feature information of a graph or accelerate the training.

关 键 词：CONVOLUTION AGGREGATION SEMI 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]