Graph Autoencoder with Preserving Node Attribute Similarity

被引:8
|
作者
Lin, Mugang [1 ,2 ]
Wen, Kunhui [1 ]
Zhu, Xuanying [1 ]
Zhao, Huihuang [1 ,2 ]
Sun, Xianfang [3 ]
机构
[1] Hengyang Normal Univ, Coll Comp Sci & Technol, Hengyang 421002, Peoples R China
[2] Hunan Prov Key Lab Intelligent Informat Proc & App, Hengyang 421002, Peoples R China
[3] Cardiff Univ, Sch Comp Sci & Informat, Cardiff CF24 4AG, Wales
基金
中国国家自然科学基金;
关键词
graph representation learning; graph autoencoder; unsupervised learning; k-nearest neighbor;
D O I
10.3390/e25040567
中图分类号
O4 [物理学];
学科分类号
0702 ;
摘要
The graph autoencoder (GAE) is a powerful graph representation learning tool in an unsupervised learning manner for graph data. However, most existing GAE-based methods typically focus on preserving the graph topological structure by reconstructing the adjacency matrix while ignoring the preservation of the attribute information of nodes. Thus, the node attributes cannot be fully learned and the ability of the GAE to learn higher-quality representations is weakened. To address the issue, this paper proposes a novel GAE model that preserves node attribute similarity. The structural graph and the attribute neighbor graph, which is constructed based on the attribute similarity between nodes, are integrated as the encoder input using an effective fusion strategy. In the encoder, the attributes of the nodes can be aggregated both in their structural neighborhood and by their attribute similarity in their attribute neighborhood. This allows performing the fusion of the structural and node attribute information in the node representation by sharing the same encoder. In the decoder module, the adjacency matrix and the attribute similarity matrix of the nodes are reconstructed using dual decoders. The cross-entropy loss of the reconstructed adjacency matrix and the mean-squared error loss of the reconstructed node attribute similarity matrix are used to update the model parameters and ensure that the node representation preserves the original structural and node attribute similarity information. Extensive experiments on three citation networks show that the proposed method outperforms state-of-the-art algorithms in link prediction and node clustering tasks.
引用
收藏
页数:22
相关论文
共 50 条
  • [1] Node Similarity Preserving Graph Convolutional Networks
    Jin, Wei
    Derr, Tyler
    Wang, Yiqi
    Ma, Yao
    Liu, Zitao
    Tang, Jiliang
    WSDM '21: PROCEEDINGS OF THE 14TH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING, 2021, : 148 - 156
  • [2] Preserving node similarity adversarial learning graph representation with graph neural network
    Yang, Shangying
    Zhang, Yinglong
    Jiawei, E.
    Xia, Xuewen
    Xu, Xing
    ENGINEERING REPORTS, 2024, 6 (10)
  • [3] An Uncertain Graph Privacy Preserving Scheme Based on Node Similarity in Social Networks
    Xu, Jiayu
    Zhang, Hongyan
    Xu, Li
    2022 IEEE 19TH INTERNATIONAL CONFERENCE ON MOBILE AD HOC AND SMART SYSTEMS (MASS 2022), 2022, : 108 - 114
  • [4] Graph convolutional network with multi-similarity attribute matrices fusion for node classification
    Youquan Wang
    Jie Cao
    Haicheng Tao
    Neural Computing and Applications, 2023, 35 : 13135 - 13145
  • [5] Graph convolutional network with multi-similarity attribute matrices fusion for node classification
    Wang, Youquan
    Cao, Jie
    Tao, Haicheng
    NEURAL COMPUTING & APPLICATIONS, 2023, 35 (18): : 13135 - 13145
  • [6] Node Similarity Preserving Graph Convolutional Network Based on Full-frequency Information for Node Classification
    Li, Yuqiang
    Liao, Jing
    Liu, Chun
    Wang, YingJie
    Li, Lin
    NEURAL PROCESSING LETTERS, 2023, 55 (05) : 5473 - 5498
  • [7] Node Similarity Preserving Graph Convolutional Network Based on Full-frequency Information for Node Classification
    Yuqiang Li
    Jing Liao
    Chun Liu
    YingJie Wang
    Lin Li
    Neural Processing Letters, 2023, 55 : 5473 - 5498
  • [8] Node similarity in the citation graph
    Wangzhong Lu
    J. Janssen
    E. Milios
    N. Japkowicz
    Yongzheng Zhang
    Knowledge and Information Systems, 2007, 11 : 105 - 129
  • [9] Node similarity in the citation graph
    Lu, Wangzhong
    Janssen, J.
    Milios, E.
    Japkowicz, N.
    Zhang, Yongzheng
    KNOWLEDGE AND INFORMATION SYSTEMS, 2007, 11 (01) : 105 - 129
  • [10] Attribute and Structure Preserving Graph Contrastive Learning
    Chen, Jialu
    Kou, Gang
    THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 6, 2023, : 7024 - 7032