《计算机应用》唯一官方网站 ›› 2023, Vol. 43 ›› Issue (1): 8-14.DOI: 10.11772/j.issn.1001-9081.2021101860

所属专题: 人工智能

• 人工智能 • 上一篇    下一篇

基于One-Shot聚合自编码器的图表示学习

袁立宁1, 刘钊2   

  1. 1.中国人民公安大学 信息网络安全学院,北京 100038
    2.中国人民公安大学 研究生院,北京 100038
  • 收稿日期:2021-11-02 修回日期:2021-12-15 发布日期:2021-12-31
  • 通讯作者: 刘钊(1981—),男,北京人,讲师,博士,主要研究方向:机器学习、计算机视觉。liuzhao@ppsuc.edu.cn
  • 作者简介:袁立宁(1995—),男,河北唐山人,硕士研究生,CCF会员,主要研究方向:机器学习、图神经网络;;
  • 基金资助:
    中央高校基本科研业务费专项(2019JKF425); 国家重点研发计划项目(2020YFC1522600)。

Graph representation learning by autoencoder with one-shot aggregation

YUAN Lining1, LIU Zhao2   

  1. 1.School of Information and Cyber Security, People’s Public Security University of China, Beijing 100038, China
    2.Graduate School, People’s Public Security University of China, Beijing 100038, China
  • Received:2021-11-02 Revised:2021-12-15 Online:2021-12-31
  • Contact: LIU Zhao, born in 1981, Ph. D., lecturer. His research interests include machine learning, computer vision.
  • About author:YUAN Lining, born in 1995, M. S. candidate. His research interests include machine learning, graph neural network;
  • Supported by:
    This work is partially supported by Fundamental Research Funds for the Central Universities (2019JKF425), National Key Research and Development Program of China (2020YFC1522600).

摘要: 自编码器(AE)是一种高效的图数据表示学习模型,但大多数图自编码器(GAE)为浅层模型,其效率会随着隐藏层的增加而降低。针对上述问题,提出基于One-Shot聚合(OSA)和指数线性(ELU)函数的GAE模型OSA-GAE和图变分自编码器模型OSA-VGAE。首先,利用多层图卷积网络(GCN)构建编码器,并引入OSA和ELU函数;然后,在解码阶段使用内积解码器恢复图的拓扑结构;此外,为了防止模型训练过程中的参数过拟合,在损失函数中引入正则化项。实验结果表明,OSA和ELU函数可以有效提高深层GAE的性能,改善模型的梯度信息传递。在使用6层GCN时,基准引文数据集PubMed的链接预测任务中,深层OSA-VGAE相较于原始的VGAE在ROC曲线下的面积(AUC)和平均精度(AP)上分别提升了8.67和6.85个百分点,深层OSA-GAE相较于原始的GAE在AP和AUC上分别提升了6.82和4.39个百分点。

关键词: 自编码器, 图自编码器, 图卷积网络, One-Shot聚合, 链接预测

Abstract: AutoEncoder (AE) is an efficient learning model for graph data representation, but most of the Graph AutoEncoders (GAEs) are shallow models, their efficiencies decrease with the increase of hidden layers. Aiming at the above problems, a new GAE model OSA-GAE and a new Variational Graph AutoEncoder OSA-VGAE were proposed based on One-Shot Aggregation (OSA) and Exponential Linear Unit (ELU). Firstly, the encoder was constructed by a multi-layer Graph Convolutional Network (GCN), and OSA and ELU function were introduced. Then, the topology of the graph was recovered by the inner product decoder in the decoding stage. In addition, a regularization term was introduced to the loss function in order to prevent parameter overfitting during the model training process. Experimental results show that OSA and ELU function can improve the performance and gradient information transmission of the deep GAEs. In the link prediction task of benchmark citation dataset PubMed, when using 6-layer GCN, deep OSA-VGAE improves Area Under ROC Curve (AUC) and Average Precision (AP) by 8.67 and 6.85 percentage points respectively compared to the original VGAE, and deep OSA-GAE improves AP and AUC by 6.82 and 4.39 percentage points respectively compared to the original GAE.

Key words: AutoEncoder (AE), Graph AutoEncoder (GAE), Graph Convolutional Network (GCN), One-Shot Aggregation (OSA), link prediction

中图分类号: