DGCNN: Disordered graph convolutional neural network based on the Gaussian mixture model

被引:50
|
作者
Wu, Bo [1 ]
Liu, Yang [1 ]
Lang, Bo [1 ]
Huang, Lei [1 ]
机构
[1] Beihang Univ, State Key Lab Software Dev Environm, Beijing, Peoples R China
关键词
Disordered graph convolutional neural network; The disordered graph convolutional layer; Mixed gaussian model; Node neighborhood structure; Graph classification; Graph retrieval;
D O I
10.1016/j.neucom.2018.09.008
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Convolutional neural networks (CNNs) can be applied to graph similarity matching, in which case they are called graph CNNs. Graph CNNs are attracting increasing attention due to their effectiveness and efficiency. However, the existing convolution approaches focus only on regular data forms and require the transfer of the graph or key node neighborhoods of the graph into the same fixed form. During this transfer process, structural information of the graph can be lost, and some redundant information can be incorporated. To overcome this problem, we propose the disordered graph convolutional neural network (DGCNN) based on the mixed Gaussian model, which extends the CNN by adding a preprocessing layer called the disordered graph convolutional layer (DGCL). The DGCL uses a mixed Gaussian function to realize the mapping between the convolution kernel and the nodes in the neighborhood of the graph. The output of the DGCL is the input of the CNN. We further implement a backward-propagation optimization process of the convolutional layer by which we incorporate the feature-learning model of the irregular node neighborhood structure into the network. Thereafter, the optimization of the convolution kernel becomes part of the neural network learning process. The DGCNN can accept arbitrary scaled and disordered neighborhood graph structures as the receptive fields of CNNs, which reduces information loss during graph transformation. Finally, we perform experiments on multiple standard graph datasets. The results show that the proposed method outperforms the state-of-the-art methods in graph classification and retrieval. (C) 2018 Elsevier B.V. All rights reserved.
引用
收藏
页码:346 / 356
页数:11
相关论文
共 50 条
  • [41] Community detection based on BernNet graph convolutional neural network
    Hui Xie
    Yixin Ning
    Journal of the Korean Physical Society, 2023, 83 : 386 - 395
  • [42] Graph Convolutional Neural Network Algorithm Based on Rough Graphs
    Pan B.
    Ding W.
    Ju H.
    Huang J.
    Cheng C.
    Shen X.
    Geng Y.
    Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence, 2022, 35 (09): : 827 - 838
  • [43] Community detection based on BernNet graph convolutional neural network
    Xie, Hui
    Ning, Yixin
    JOURNAL OF THE KOREAN PHYSICAL SOCIETY, 2023, 83 (05) : 386 - 395
  • [44] Convolutional Neural Network Outperforms Graph Neural Network on the Spatially Variant Graph Data
    Boronina, Anna
    Maksimenko, Vladimir
    Hramov, Alexander E. E.
    MATHEMATICS, 2023, 11 (11)
  • [45] Cellular Network Fault Diagnosis Method Based on a Graph Convolutional Neural Network
    Amuah, Ebenezer Ackah
    Wu, Mingxiao
    Zhu, Xiaorong
    SENSORS, 2023, 23 (16)
  • [46] Drainage Pattern Recognition of River Network Based on Graph Convolutional Neural Network
    Xu, Xiaofeng
    Liu, Pengcheng
    Guo, Mingwu
    ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION, 2023, 12 (07)
  • [47] A graph-convolutional neural network model for the prediction of chemical reactivity
    Coley, Connor W.
    Jin, Wengong
    Rogers, Luke
    Jamison, Timothy F.
    Jaakkola, Tommi S.
    Green, William H.
    Barzilay, Regina
    Jensen, Klavs F.
    CHEMICAL SCIENCE, 2019, 10 (02) : 370 - 377
  • [48] Hyperspectral Image Classification Based on Fusion of Convolutional Neural Network and Graph Network
    Gao, Luyao
    Xiao, Shulin
    Hu, Changhong
    Yan, Yang
    APPLIED SCIENCES-BASEL, 2023, 13 (12):
  • [49] Prediction of chemical reactivity with a graph-convolutional neural network model
    Coley, Connor
    Jin, Wengong
    Rogers, Luke
    Jamison, Timothy
    Jaakkola, Tommi
    Green, William
    Barzilay, Regina
    Jensen, Klavs
    ABSTRACTS OF PAPERS OF THE AMERICAN CHEMICAL SOCIETY, 2019, 257
  • [50] Essential genes identification model based on sequence feature map and graph convolutional neural network
    Hu, Wenxing
    Li, Mengshan
    Xiao, Haiyang
    Guan, Lixin
    BMC GENOMICS, 2024, 25 (01)