电子学报 ›› 2022, Vol. 50 ›› Issue (9): 2155-2163.DOI: 10.12263/DZXB.20210592

• 学术论文 • 上一篇    下一篇

基于嵌套生成对抗学习的网络嵌入

沈鹏飞1, 徐臻1, 王英2   

  1. 1.中国电子科技南湖研究院,浙江 嘉兴 314001
    2.吉林大学计算机科学与技术学院,吉林 长春 130012
  • 收稿日期:2021-05-10 修回日期:2021-08-23 出版日期:2022-09-25
    • 作者简介:
    • 沈鹏飞 男,1988年生,甘肃武威人,中国电子科技南湖研究院高级工程师,研究方向:机器学习、深度学习、图神经网络、信息网络嵌入和认知智能. E-mail: shen_pf@qq.com
      徐 臻 男,1989年生,浙江衢州人,中国电子科技南湖研究院高级工程师,研究方向:认知智能、知识图谱、多智能协同和博弈.E-mail: xuzhen@cnaeit.com
      王 英(通讯作者) 女,1981年4月生,黑龙江省阿城市人,现为吉林大学计算机科学与技术学院教授,博士生导师,研究方向为人工智能、机器学习、社会计算.
    • 基金资助:
    • 国家自然科学基金 (61872161)

Network Embedding Based on Nested Generative Adversarial Networks

SHEN Peng-fei1, XU Zhen1, WANG Ying2   

  1. 1.China Nanhu Academy of Electronics and Information Technology,Jiaxing,Zhejiang 314001,China
    2.College of Computer Science and Technology,Jilin University,Changchun,Jilin 130012,China
  • Received:2021-05-10 Revised:2021-08-23 Online:2022-09-25 Published:2022-12-07

摘要:

当前网络嵌入研究更多关注信息网络结构和结点之间一阶或高阶近似关系,对于网络结点自身属性考虑较少.本文提出一种嵌套的生成对抗网络模型N-GAN(Nesting Generative Adversarial Networks for Network Embedding),实现了网络结构和节点属性同时嵌入到低维向量,从而最大程度保存原始高维信息网络特征.N-GAN模型设计灵活,具有很好的延伸性和扩张性,并在真实数据上验证了N-GAN的性能及其稳定性,其嵌入的低维表示在不同应用中表现出不错的性能.

关键词: 数据挖掘, 网络嵌入, 生成对抗学习, 信息网络

Abstract:

The current network embedding researches focus more on the information network structure and first-order or higher-order approximation of nodes, but less on the attributes of network nodes. This paper proposes a nested generative adversarial network model N-GAN(Nesting Generative Adversarial Networks for Network Embedding), which embeds the network structure and nodes' attributes into the low-dimensional vector at the same time, so as to preserve the feature of the original high-dimensional information network maximumly. N-GAN model is flexible in design and has good extensibility and expansibility. The performance and stability of N-GAN model are verified on real datasets. The embedded low-dimensional representation of N-GAN model shows good performance in different tasks.

Key words: data mining, network embedding, generative adversarial learning, information network

中图分类号: