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

图卷积神经网络(GCN)是一种用于处理图数据的深度学习模型.在经典的GCN中节点之间的聚合,未考虑节点间相似度的特征信息,影响了分类模型的准确性和模型训练的收敛速度.本文提出了一种改进聚合权重的图卷积神经网络IAW-GCN,通过利用描述节点相似度的曼哈顿距离度量设计了节点聚合权重函数,并用节点距离度量矩阵改进了GCN模型中的特征矩阵,使得IAW-GCN模型在消息传递聚合过程中根据相似度调节节点聚合权重.实验结果表明,在Cora、Citeseer和Pubmed标准引文数据集条件下,IAW-GCN在半监督分类任务中的分类准确率和模型训练收敛速度均优于经典GCN,为解决半监督分类问题提供了一种新方法.

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 information of similarity between nodes,which affects the model accuracy and training convergence speed for the classification model.This paper proposes a graph convolutional neural network-IAW-GCN,via improved aggregation weights.The node aggregation weight function 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 aggregation 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.