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
  • [21] Attribute preserving recommendation system based on graph attention mechanism
    Sangeetha, M.
    Thiagarajan, Meera Devi
    JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2023, 44 (06) : 9419 - 9430
  • [22] Graph Clustering based on Structural Attribute Neighborhood Similarity (SANS)
    Parimala, M.
    Lopez, Daphne
    2015 IEEE INTERNATIONAL CONFERENCE ON ELECTRICAL, COMPUTER AND COMMUNICATION TECHNOLOGIES, 2015,
  • [23] Consistency knowledge distillation based on similarity attribute graph guidance
    Ma, Jiaqi
    Yang, Jinfu
    Fu, Fuji
    Zhang, Jiahui
    EXPERT SYSTEMS WITH APPLICATIONS, 2025, 269
  • [24] Managing Big Data by Directed Graph Node Similarity
    Pap, Endre
    Jocic, Marko
    Szakal, Aniko
    Obradovic, Djordje
    Konjovic, Zora
    2016 17TH IEEE INTERNATIONAL SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE AND INFORMATICS (CINTI 2016), 2016, : 25 - 29
  • [25] AEGraph: Node attribute-enhanced graph encoder method
    Sun, Kang
    Qiu, Liqing
    Zhao, Wenxiu
    EXPERT SYSTEMS WITH APPLICATIONS, 2024, 236
  • [26] Knowledge based attribute completion for heterogeneous graph node classification
    Yu, Haibo
    Zheng, Zhangkai
    Xue, Yun
    Song, Yiping
    Liang, Zhuoming
    NEUROCOMPUTING, 2025, 619
  • [27] Social network node pricing based on graph autoencoder in data marketplaces
    Sun, Yongjiao
    Li, Boyang
    Bi, Xin
    Feng, Qiang
    EXPERT SYSTEMS WITH APPLICATIONS, 2024, 243
  • [28] Continuous Encoding for Community Detection in Attribute Networks with Preserving Node Information
    Zheng, Wei
    Liu, Xin
    Sun, Jianyong
    2021 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC 2021), 2021, : 2031 - 2038
  • [29] Graph clustering using k-Neighbourhood Attribute Structural similarity
    Boobalan, M. Parimala
    Lopez, Daphne
    Gao, X. Z.
    APPLIED SOFT COMPUTING, 2016, 47 : 216 - 223
  • [30] A graph autoencoder network to measure the geometric similarity of drainage networks in scaling transformation
    Yu, Huafei
    Ai, Tinghua
    Yang, Min
    Huang, Weiming
    Harrie, Lars
    INTERNATIONAL JOURNAL OF DIGITAL EARTH, 2023, 16 (01) : 1828 - 1852