陕西科技大学学报2024，Vol.42Issue(5)：191-197,7.
基于改进图卷积神经网络的半监督分类
Semi-supervised classification based on improved graph convolutional network
摘要
Abstract
Graph convolutional network(GCN)is a deep learning model for processing graph data.In the classic GCN,the aggregation between nodes does not consider the feature infor-mation of similarity between nodes,which affects the model accuracy and training conver-gence speed for the classification model.This paper proposes a graph convolutional neural network-IAW-GCN,via improved aggregation weights.The node aggregation weight func-tion is designed by utilizing the Manhattan distance metric that describes the node similarity,and the GCN model is improved by the node distance metric matrix.The feature matrix can adjust the node aggregation weight according to similarity during the message passing aggre-gation process in the model.Experimental results show that under the conditions of Cora,Citeseer and Pubmed standard citation data sets,the improved model has better classification accuracy and model performance in semi-supervised classification tasks.Particularly,the training convergence speed is better than the classic GCN model.This paper provids a new method for solving semi-supervised classification problems.关键词
图卷积神经网络/半监督分类/聚合函数Key words
graph convolutional network/semi-supervised classification/aggregation function分类
计算机与自动化引用本文复制引用
郭文强,薛博丰,候勇严,胡永龙..基于改进图卷积神经网络的半监督分类[J].陕西科技大学学报,2024,42(5):191-197,7.基金项目
陕西省科技厅重点研发计划项目(2024GX-YBXM-113) （2024GX-YBXM-113）
陕西省西安市科技计划项目(23GXFW0004) （23GXFW0004）
陕西科技大学博士科研启动基金项目(2023BJ-01) （2023BJ-01）
