ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2022, Vol. 59 ›› Issue (1): 47-80.doi: 10.7544/issn1000-1239.20201055

• 人工智能 • 上一篇    下一篇



  1. (中国石油大学(北京)信息科学与工程学院 北京 102249) (
  • 出版日期: 2022-01-01
  • 基金资助: 

Survey on Graph Neural Network

Ma Shuai, Liu Jianwei, Zuo Xin   

  1. (College of Information Science and Engineering, China University of Petroleum (Beijing), Beijing 102249)
  • Online: 2022-01-01
  • Supported by: 
    This work was supported by the Scientific Research Foundation of China University of Petroleum(Beijing)(2462020YXZZ023).

摘要: 近几年来,将深度学习应用到处理和图结构数据相关的任务中越来越受到人们的关注.图神经网络的出现使其在上述任务中取得了重大突破,比如在社交网络、自然语言处理、计算机视觉甚至生命科学等领域得到了非常广泛的应用.图神经网络可以把实际问题看作图中节点之间的连接和消息传播问题,对节点之间的依赖关系进行建模,从而能够很好地处理图结构数据.鉴于此,系统综述了图神经网络模型以及应用.首先从谱域、空间域和池化3方面对图卷积神经网络进行了阐述.然后,描述了基于注意力机制和自编码器的图神经网络模型,并补充了一些其他方法实现的图神经网络.其次,总结了针对图神经网络能不能做大做深等问题的讨论分析.进而,概括了图神经网络的4个框架.还详细说明了在图神经网络在自然语言处理、计算机视觉等方面的应用.最后,对图神经网络未来的研究进行了展望和总结.相较于已有的图神经网络综述文章,详细阐述了谱理论知识,并对基于谱域的图卷积神经网络体系进行全面总结.同时,给出了针对空间域图卷积神经网络效率低的改进模型这一新的分类标准.并总结了针对图神经网络表达能力、理论保障等的讨论分析,增加了新的框架模型.在应用部分,阐述了图神经网络的最新应用.

关键词: 图结构数据, 图神经网络, 图卷积神经网络, 谱域, 空间域和池化

Abstract: In recent years, the application of deep learning related to graph structure data has attracted more and more attention. The emergence of graph neural network has made major breakthroughs in the above tasks, such as social networking, natural language processing, computer vision, even life sciences and other fields. The graph neural network can treat the actual problem as the connection between nodes in the graph and the message propagation problem, and the dependence between nodes can be modeled, so that the graph structure data can be handled well. In view of this, the graph neural network model and its application are systematically reviewed. Firstly, the graph convolutional neural network is explained from three aspects: spectral domain, spatial domain and pooling. Then, the graph neural network model based on the attention mechanism and autoencoder is described, and some graph neural network implemented by other methods are supplemented. Secondly, it summarizes the discussion and analysis on whether the graph neural network can be bigger and deeper. Furthermore, four frameworks of graph neural network are summarized. It also explains in detail the application of graph neural network in natural language processing and computer vision, etc. Finally, the future research of graph neural network is prospected and summarized. Compared with existing review articles on graph neural network, it elaborates the knowledge of spectral theory in detail, and comprehensively summarizes the development history of graph convolutional neural network based on the spectral domain. At the same time, a new classification standard, an improved model for the low efficiency of the spatial domain graph convolutional neural network, is given. And for the first time, it summarizes the discussion and analysis of graph neural network expression ability, theoretical guarantee, etc., and adds a new framework model. In the application part, the latest application of graph neural network is explained.

Key words: graph structure data, graph neural network, graph convolutional neural network, spectral domain, spatial domain and pooling