基于图关系选择的深度聚类网络  

Deep Clustering Network Based on Graph Relationship Selection

作　　者：孙艳丰 杜鹏飞 SUN Yanfeng;DU Pengfei(Faculty of Information Technology,Beijing University of Technology,Beijing 100124,China)

机构地区：[1]北京工业大学信息学部,北京100124

出　　处：《北京工业大学学报》2024年第12期1428-1436,共9页Journal of Beijing University of Technology

基　　金：国家自然科学基金资助项目(62172023)。

摘　　要：针对在深度聚类中基于图卷积网络(graph convolutional network,GCN)编码图结构信息的方法存在过拟合的问题,提出一种通过对比学习将图邻接关系融合到传统深度网络中对图结构进行编码的方法。首先,该方法中使用自动编码器(auto-encoder,AE)来学习节点特征的深层次潜在表示;然后,通过对比学习从图关系中学习有区分性的节点表示,同时设计了更细致的节点间影响力关系,从而为对比学习提供有力的正负样本选择依据;最后,通过自监督的方式训练网络以实现聚类任务。在6个基准数据集上进行了大量实验,结果表明,提出的方法显著地提高了聚类精度。To solve the problem of overfitting in the method of encoding graph structure information based on graph convolutional network(GCN)in depth clustering,a method is proposed to encode graph structure by fusing graph adjacency into traditional depth network through contrastive learning.First,in this method,an auto-encoder(AE)was used to learn the deep potential representation of node features.Then,through contrastive learning,discriminative node representations were learned from graph relationships,and more detailed inter node influence was designed to provide a strong basis for selecting positive and negative samples for contrastive learning.Finally,the network was trained by self-supervised learning to implement node clustering.A large number of experiments on six benchmark datasets show that the proposed method significantly improves the clustering accuracy.

关 键 词：节点聚类 图卷积网络(graph convolutional network GCN) 自动编码器(auto-encoder AE) 图关系 对比学习 自监督 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]