SDHGCN: A Heterogeneous Graph Convolutional Neural Network Combined With Shadowed Set

被引:0
作者
Yu, Bin [1 ]
Xie, Hengjie [1 ]
Chen, Jingxuan [2 ]
Cai, Mingjie [3 ,4 ,5 ]
Fujita, Hamido [6 ,7 ,8 ]
Ding, Weiping [9 ]
机构
[1] Hunan Normal Univ, Coll Informat Sci & Engn, Changsha 410081, Peoples R China
[2] Warwick Business Sch, Coventry CV4 7AL, England
[3] Hunan Univ, Coll Math, Changsha 410082, Peoples R China
[4] Hunan Univ, Shenzhen Res Inst, Shenzhen 518000, Peoples R China
[5] Hunan Key Lab Intelligent Decis Making Technol Eme, Changsha 410082, Hunan, Peoples R China
[6] Univ Teknol Malaysia, Int Inst Technol MJIIT, Kuala Lumpur 54100, Malaysia
[7] Princess Nourah bint Abdulrahman Univ PNU, Coll Sci, Riyadh 13412, Saudi Arabia
[8] Iwate Prefectural Univ, Reg Res Ctr, Iwate 0200693, Japan
[9] Nantong Univ, Sch Artificial Intelligence & Comp Sci, Nantong 226019, Peoples R China
基金
中国国家自然科学基金;
关键词
Information systems; Graph convolutional networks; Euclidean distance; Entropy; Convolution; Uncertainty; Symmetric matrices; Fuzzy systems; STEM; Feature extraction; Classification; graph neural network; heterogeneous graph; information system (IS); graph convolutional neural network based on shadowed deviation relationship (SDHGCN); shadowed set; INFORMATION GAIN;
D O I
10.1109/TFUZZ.2024.3494864
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Graph convolutional neural networks (GCNs) have demonstrated effectiveness in processing graph structure. Due to the diversity and complexity of real-world graph data, heterogeneous GCN have attracted significant attention. However, existing research predominantly relies on explicit connections to explore graph heterogeneity. In the case of edgeless graphs, such as information systems, the absence of direct edges poses a significant challenge for employing GCNs to analyze the latent heterogeneity within these graphs. Traditional approaches overlook the topological features of information systems, resulting in information loss. This article introduces a heterogeneous graph convolutional neural network based on shadowed deviation relationship (SDHGCN) to investigate the heterogeneity of information systems, thereby improving the generalizability of heterogeneous GCNs. First, shadow deviation relationship and attribute deviation relationship are constructed derived from shadow sets and information gain, respectively. Then, dexterously integrated with the feature matrix of the information system (the relationship between objects and attributes), a highly expressive heterogeneous graph is constructed. Second, by performing graph convolution operations on the heterogeneous graph, effective node representations can be obtained to complete node classification tasks. Finally, the effectiveness and nonrandomness of SDHGCN are validated by extensive comparison and ablation experiments.
引用
收藏
页码:881 / 893
页数:13
相关论文
共 44 条
[31]  
Xu Keyulu., 2018, POWERFUL ARE GRAPH N
[32]  
Yang XC, 2023, AAAI CONF ARTIF INTE, P10816
[33]   Interpretable and Efficient Heterogeneous Graph Convolutional Network [J].
Yang, Yaming ;
Guan, Ziyu ;
Li, Jianxin ;
Zhao, Wei ;
Cui, Jiangtao ;
Wang, Quan .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (02) :1637-1650
[34]  
Yao L, 2019, AAAI CONF ARTIF INTE, P7370
[35]   PN-GCN: Positive-negative graph convolution neural network in information system to classification [J].
Yu, Bin ;
Xie, Hengjie ;
Xu, Zeshui .
INFORMATION SCIENCES, 2023, 632 :411-423
[36]   A graph convolutional network based on object relationship method under linguistic environment applied to film evaluation [J].
Yu, Bin ;
Cai, Ruipeng ;
Fu, Yu ;
Xu, Zeshui .
INFORMATION SCIENCES, 2022, 608 :1283-1300
[37]   Heterogeneous Graph Representation Learning With Relation Awareness [J].
Yu, Le ;
Sun, Leilei ;
Du, Bowen ;
Liu, Chuanren ;
Lv, Weifeng ;
Xiong, Hui .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (06) :5935-5947
[38]   Heterogeneous Graph Neural Network [J].
Zhang, Chuxu ;
Song, Dongjin ;
Huang, Chao ;
Swami, Ananthram ;
Chawla, Nitesh V. .
KDD'19: PROCEEDINGS OF THE 25TH ACM SIGKDD INTERNATIONAL CONFERENCCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2019, :793-803
[39]   Knowledge graph embedding by logical-default attention graph convolution neural network for link prediction [J].
Zhang, Jiarui ;
Huang, Jian ;
Gao, Jialong ;
Han, Runhai ;
Zhou, Cong .
INFORMATION SCIENCES, 2022, 593 :201-215
[40]  
Zhang L., 2023, ACM Transactions on the Web, V18, P1