计算机应用 ›› 2020, Vol. 40 ›› Issue (1): 188-195.DOI: 10.11772/j.issn.1001-9081.2019061116

• 网络与通信 • 上一篇    下一篇

基于图编码网络的社交网络节点分类方法

郝志峰1,2, 柯妍蓉1, 李烁1, 蔡瑞初1, 温雯1, 王丽娟1   

  1. 1. 广东工业大学 计算机学院, 广州 510006;
    2. 佛山科学技术学院 数学与大数据学院, 广东 佛山 528000
  • 收稿日期:2019-06-27 修回日期:2019-08-14 出版日期:2020-01-10 发布日期:2019-10-08
  • 作者简介:郝志峰(1968-),男,江苏苏州人,教授,博士,主要研究方向:机器学习、人工智能;柯妍蓉(1993-),女,广东潮州人,硕士研究生,主要研究方向:机器学习、深度学习;李烁(1992-),男,河南平顶山人,硕士研究生,主要研究方向:机器学习、数据挖掘;蔡瑞初(1983-),男,浙江温州人,教授,博士,主要研究方向:机器学习、数据挖掘;温雯(1981-),女,江西赣州人,副教授,博士,主要研究方向:支持向量机、模式识别;王丽娟(1978-),女,河北邢台人,副教授,博士,主要研究方向:数据挖掘、机器学习。
  • 基金资助:
    国家自然科学基金-广东联合基金资助项目(U1501254)。

Node classification method in social network based on graph encoder network

HAO Zhifeng1,2, KE Yanrong1, LI Shuo1, CAI Ruichu1, WEN Wen1, WANG Lijuan1   

  1. 1. College of Computer Science, Guangdong University of Technology, Guangzhou Guangdong 510006, China;
    2. College of Mathematics and Big Data, Foshan University, Foshan Guangdong 528000, China
  • Received:2019-06-27 Revised:2019-08-14 Online:2020-01-10 Published:2019-10-08
  • Contact: 蔡瑞初
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China-Guangdong Joint Foundation (U1501254).

摘要: 针对如何融合节点自身属性以及网络结构信息实现社交网络节点分类的问题,提出了一种基于图编码网络的社交网络节点分类算法。首先,每个节点向邻域节点传播其携带的信息;其次,每个节点通过神经网络挖掘其与邻域节点之间可能隐含的关系,并且将这些关系进行融合;最后,每个节点根据自身信息以及与邻域节点关系的信息提取更高层次的特征,作为节点的表示,并且根据该表示对节点进行分类。在微博数据集上,与经典的深度随机游走模型、逻辑回归算法有以及最近提出的图卷积网络算法相比,所提算法分类准确率均有大于8%的提升;在DBLP数据集上,与多层感知器相比分类准确率提升4.83%,与图卷积网络相比分类准确率提升0.91%。

关键词: 社交网络, 节点分类, 图编码网络, 图神经网络, 图表示

Abstract: Aiming at how to merge the nodes' attributes and network structure information to realize the classification of social network nodes, a social network node classification algorithm based on graph encoder network was proposed. Firstly, the information of each node was propagated to its neighbors. Secondly, for each node, the possible implicit relationships between itself and its neighbor nodes were mined through neural network, and these relationships were merged together. Finally, the higher-level features of each node were extracted based on the information of the node itself and the relationships with the neighboring nodes and were used as the representation of the node, and the node was classified according to this representation. On the Weibo dataset, compared with DeepWalk model, logistic regression algorithm and the recently proposed graph convolutional network, the proposed algorithm has the classification accuracy greater than 8%; on the DBLP dataset, compared with multilayer perceptron, the classification accuracy of this algorithm is increased by 4.83%, and is increased by 0.91% compared with graph convolutional network.

Key words: social network, node classification, graph encoder network, Graph Neural Network (GNN), graph representation

中图分类号: