计算机科学与探索 ›› 2022, Vol. 16 ›› Issue (11): 2505-2518.DOI: 10.3778/j.issn.1673-9418.2104075

• 网络与信息安全 • 上一篇    下一篇

融合节点属性和无环路径的社交网络嵌入方法

王本钰, 顾益军+(), 彭舒凡   

  1. 中国人民公安大学 信息网络安全学院,北京 100032
  • 收稿日期:2021-04-02 修回日期:2021-05-17 出版日期:2022-11-01 发布日期:2021-05-25
  • 通讯作者: + E-mail: guyijun@ppsuc.edu.cn
  • 作者简介:王本钰(1998—),男,江苏盐城人,硕士研究生,主要研究方向为复杂网络、深度学习。
    顾益军(1968—),男,江苏无锡人,博士,教授,博士生导师,主要研究方向为复杂网络、深度学习。
    彭舒凡(1998—),男,江苏无锡人,硕士研究生,主要研究方向为复杂网络、深度学习。
  • 基金资助:
    公安部科技强警基础工作专项项目(2020GABJC02);中国人民公安大学基本科研业务费项目(2021JKF420)

Social Network Embedding Method Combining Node Attributes and Loop-Free Path

WANG Benyu, GU Yijun+(), PENG Shufan   

  1. School of Information and Network Security, People’s Public Security University of China, Beijing 100032, China
  • Received:2021-04-02 Revised:2021-05-17 Online:2022-11-01 Published:2021-05-25
  • About author:WANG Benyu, born in 1998, M.S. candidate. His research interests include complex network and deep learning.
    GU Yijun, born in 1968, Ph.D., professor, Ph.D. supervisor. His research interests include complex network and deep learning.
    PENG Shufan, born in 1998, M.S. candidate. His research interests include complex network and deep learning.
  • Supported by:
    Police Project of Science and Technology to Strengthen the Basic Work of Ministry of Public Security of China(2020GABJC02);Basic Research Funds of People’s Public Security University of China(2021JKF420)

摘要:

网络嵌入的目标是学习网络中节点的低维特征表示,将学习到的特征用于网络的各种分析任务中,例如节点分类、链路预测、社区发现和推荐等。现有的网络嵌入方法对于社交网络中高阶结构信息利用不足并且没有考虑社交网络结构信息和属性信息的相关性,应用于社交网络中效果并不理想。为了解决这些问题,提出了一种融合节点属性和无环路径的社交网络嵌入方法(LFNE)。该算法首先基于节点间无环路径计算节点高阶结构相似性,消除环状路径和大度节点对于节点结构相似性的影响,使得网络嵌入方法可以更好地融合社交网络高阶结构信息。然后结合节点间无环路径相似性度量指标计算节点属性相似性,充分利用社交网络结构信息和属性信息的相关性,消除属性信息中存在的噪音。最后融合节点结构相似性和属性相似性应用于堆叠降噪自动编码器中学习节点的低维特征表示。在3个社交网络数据集上与近几年代表性算法进行实验对比,实验结果表明LFNE算法在节点分类和链路预测实验中可以取得相对显著的效果,具有更好的网络嵌入表现。

关键词: 网络嵌入, 社交网络, 节点属性, 无环路径, 堆叠降噪自动编码器

Abstract:

Network embedding’s goal is to learn the low-dimensional node feature representation in the network. The learned features are used in various network analysis tasks, such as node classification, link prediction, community detection and recommendation, etc. The existing network embedding methods do not make full use of high-order structure information in social networks. Moreover, the correlation between structure information and node attribute information is not considered. The effect of these methods applied in the social network is not ideal. A social network embedding method combining loop-free path and attributes network embedding (LFNE) is proposed to solve these problems. The high-order structural similarity of nodes is calculated first based on the loop-free path between nodes to eliminate the influence of loop path and large-degree nodes on node structure similarity. This algorithm makes the network embedding method better integrate the high-order social network structure information. Then the node attributes similarity is calculated by combining the loop-free path similarity measurement index between nodes, and the correlation between social network structure information and attribute information is fully utilized to eliminate the noise in attribute information. Finally, the node structure similarity and attribute similarity are fused and applied to learning the low-dimensional feature representation of nodes in the stacked denoising autoencoder. Comparison of experiments with representative algorithms in recent years on three social network datasets shows that the LFNE algorithm can achieve relatively significant results in node classification and link prediction with better network embedding performance.

Key words: network embedding, social network, node attributes, loop-free path, stacked denoising autoencoder

中图分类号: