摘要
复杂网络节点分类大多基于图神经网络学习节点表示而实现,图神经网络通过邻域聚合对复杂网络局部结构信息进行编码。然而,图神经网络的过平滑问题导致复杂网络节点分类性能受限。基于此,提出一种基于增强图神经网络和对比学习的复杂网络节点分类方法。该方法不仅为邻域节点引入注意力来区分各邻居节点的重要性,而且采用局部邻域重叠度和全局邻域重叠度构造边的特征,从而扩大节点表示的信息量。最后,引入对比学习对神经网络进行训练,从而利用网络全局节点分类先验信息对节点表示进行联合优化。在Cora、Citeseer、PubMed和Chameleon公开网络数据集上进行了实验,结果表明,相较于其他先进方法,所提方法的节点分类性能更好,并通过消融实验验证了所提方法的有效性。
Node classification methods of complex network are mostly realized based on node representation learned by the graph neural network,the graph neural network encodes local structure information of complex networks through neighborhood aggregation.However,the over-smoothing problem of the graph neural network limits the node classification performance of complex network.In view of this problem,a node classification method of complex networks based on enhanced graph neural networks and contrastive learning was proposed.In the proposed method,not only the attention was introduced to the neighborhood nodes,in order to differentiate the importance of each neighbor node,but also the feature of each edge was constructed with combination of the local neighborhood overlap and the global neighborhood overlap,so as to expand the information of the node representation.Finally,contrastive learning was introduced to train the neural networks,so that the network’s global node priori information was utilized to jointly optimize the node representation.Experiments were performed on Cora,Citeseer,PubMed and Chameleon public network datasets.The results demonstrate that compared to the other advanced methods,the proposed method achieves better node classification performance,moreover,the effectiveness of the proposed method is verified through ablation study.
作者
徐培玲
王玉
谭艳丽
XU Peiling;WANG Yu;TAN Yanli(Department of Electronic Information,Shanxi Institute of Economics and Business,Taiyuan 030024,China;School of Information and Communication Engineering,North University of China,Taiyuan 030051,China;Department of Electronic Engineering,Taiyuan Institute of Technology,Taiyuan 030000,China)
出处
《电信科学》
北大核心
2025年第8期127-138,共12页
Telecommunications Science
基金
教育部产学合作协同育人项目(No.220606517245903)。
关键词
网络节点分类
复杂网络
图神经网络
图注意力网络
对比学习
network node classification
complex network
graph neural network
graph attention network
contrastive learning
