Node classification of complex network based on enhanced graph neural network and contrastive learning

XU Peiling; WANG Yu; TAN Yanli

doi:10.11959/j.issn.1000-0801.2025128

您当前的位置：

首页 >

文章列表页 >

Node classification of complex network based on enhanced graph neural network and contrastive learning

Research and Development | 更新时间：2025-09-04

- Node classification of complex network based on enhanced graph neural network and contrastive learning
- Telecommunications Science Vol. 41, Issue 8, Pages: 127-138(2025)
- 作者机构：
  
  1.山西经贸职业学院电子信息系，山西太原 030024
  2.中北大学信息与通信工程学院，山西太原 030051
  3.太原工业学院电子工程系，山西太原 030000
- 作者简介：
- 基金信息：
  
  The Ministry of Education’s Industry-University Cooperation and Synergistic Education Project(220606517245903)
- DOI：10.11959/j.issn.1000-0801.2025128
  CLC： TP393
- Received：22 December 2024，
  
  Revised：2025-03-21，
  
  Published：20 August 2025
- 稿件说明：
移动端阅览
徐培玲,王玉,谭艳丽.基于增强图神经网络和对比学习的复杂网络节点分类[J].电信科学,2025,41(08):127-138.

XU Peiling,WANG Yu,TAN Yanli.Node classification of complex network based on enhanced graph neural network and contrastive learning[J].Telecommunications Science,2025,41(08):127-138.
徐培玲,王玉,谭艳丽.基于增强图神经网络和对比学习的复杂网络节点分类[J].电信科学,2025,41(08):127-138. DOI： 10.11959/j.issn.1000-0801.2025128.

XU Peiling,WANG Yu,TAN Yanli.Node classification of complex network based on enhanced graph neural network and contrastive learning[J].Telecommunications Science,2025,41(08):127-138. DOI： 10.11959/j.issn.1000-0801.2025128.

摘要

复杂网络节点分类大多基于图神经网络学习节点表示而实现，图神经网络通过邻域聚合对复杂网络局部结构信息进行编码。然而，图神经网络的过平滑问题导致复杂网络节点分类性能受限。基于此，提出一种基于增强图神经网络和对比学习的复杂网络节点分类方法。该方法不仅为邻域节点引入注意力来区分各邻居节点的重要性，而且采用局部邻域重叠度和全局邻域重叠度构造边的特征，从而扩大节点表示的信息量。最后，引入对比学习对神经网络进行训练，从而利用网络全局节点分类先验信息对节点表示进行联合优化。在Cora、Citeseer、PubMed和Chameleon公开网络数据集上进行了实验，结果表明，相较于其他先进方法，所提方法的节点分类性能更好，并通过消融实验验证了所提方法的有效性。

Abstract

Node classification methods of complex network are mostly realized based on node representation learned by the graph neural network

the graph neural network encodes local structure information of complex networks through neighborhood aggregation. However

the over-smoothing problem of the graph neural network limits the node classification performance of complex network. In view of this problem

a node classification method of complex networks based on enhanced graph neural networks and contrastive learning was proposed. In the proposed method

not only the attention was introduced to the neighborhood nodes

in order to differentiate the importance of each neighbor node

but also the feature of each edge was constructed with combination of the local neighborhood overlap and the global neighborhood overlap

so as to expand the information of the node representation. Finally

contrastive learning was introduced to train the neural networks

so that the network’s global node priori information was utilized to jointly optimize the node representation. Experiments were performed on Cora

Citeseer

PubMed and Chameleon public network datasets. The results demonstrate that compared to the other advanced methods

the proposed method achieves better node classification performance

moreover

the effectiveness of the proposed method is verified through ablation study.

关键词

Keywords

references

肖国庆 , 李雪琪 , 陈玥丹 , 等 . 大规模图神经网络研究综述 [J ] . 计算机学报 , 2024 , 47 ( 1 ): 148 - 171 .

XIAO G Q , LI X Q , CHEN Y D , et al . A survey of large-scale graph neural networks [J ] . Chinese Journal of Computers , 2024 , 47 ( 1 ): 148 - 171 .

LIU C , LI Y X , LIN H , et al . GNNRec: gated graph neural network for session-based social recommendation model [J ] . Journal of Intelligent Information Systems , 2023 , 60 ( 1 ): 137 - 156 .

曹汉童 , 陈璟 . 融合Doc2vec与GCN的多类型蛋白质相互作用预测方法 [J ] . 智能系统学报 , 2023 , 18 ( 6 ): 1165 - 1172 .

CAO H T , CHEN J . Prediction of multitype protein interactions combining Doc2vec and GCN [J ] . CAAI Transactions on Intelligent Systems , 2023 , 18 ( 6 ): 1165 - 1172 .

LIU Z W , YANG P L , HAO Q B , et al . Exploring implicit influence for social recommendation based on GNN [J ] . Soft Computing , 2024 , 28 ( 19 ): 11001 - 11014 .

郑文萍 , 葛慧琳 , 刘美麟 , 等 . 融合二连通模体结构信息的节点分类算法 [J ] . 计算机应用 , 2024 , 44 ( 5 ): 1464 - 1470 .

ZHENG W P , GE H L , LIU M L , et al . Node classification algorithm fusing 2-connected motif-structure information [J ] . Journal of Computer Applications , 2024 , 44 ( 5 ): 1464 - 1470 .

曹磊亮 , 谢瑾奎 , 郭天晟 . 结合残差网络和噪声处理的节点分类模型 [J ] . 小型微型计算机系统 , 2024 , 45 ( 6 ): 1331 - 1338 .

CAO L L , XIE J K , GUO T S . Node classification model combining residual network and noise processing [J ] . Journal of Chinese Computer Systems , 2024 , 45 ( 6 ): 1331 - 1338 .

郑诚 , 倪显虎 , 张苏航 , 等 . 结合GNN的信息融合用于归纳式文本分类 [J ] . 小型微型计算机系统 , 2023 , 44 ( 6 ): 1170 - 1176 .

ZHENG C , NI X H , ZHANG S H , et al . Information fusion combined with GNN is used for inductive text classification [J ] . Journal of Chinese Computer Systems , 2023 , 44 ( 6 ): 1170 - 1176 .

ZHANG P L , CHEN J T , CHE C , et al . IEA-GNN: anchor-aware graph neural network fused with information entropy for node classification and link prediction [J ] . Information Sciences , 2023 , 634 : 665 - 676 .

YONG C , XIAOZHU X , WEI W . Graph convolutional network combined with random walks and graph attention network for node classification [J ] . The Journal of China Universities of Posts and Telecommunications , 2024 , 31 ( 3 ): 1 - 14 .

ABBAS M A , ALI W , SMARANDACHE F , et al . Residual attention augmentation graph neural network for improved node classification [J ] . Engineering , Technology & Applied Science Research, 2024 , 14 ( 2 ): 13238 - 13242 .

李希 , 刘喜平 , 李旺才 , 等 . 对比学习研究综述 [J ] . 小型微型计算机系统 , 2023 , 44 ( 4 ): 787 - 797 .

LI X , LIU X P , LI W C , et al . Survey on contrastive learning research [J ] . Journal of Chinese Computer Systems , 2023 , 44 ( 4 ): 787 - 797 .

KIPF T N , WELLING M . Semi-supervised classication with graph convolutional networks [C ] // Proceedings of the 5th International Conference on Learning Representations . London : Computer Science Bibliography , 2017 : 1 - 14 .

XIE F , CHEN J Q , CHEN K J . Extractive text-image summarization with relation-enhanced graph attention network [J ] . Journal of Intelligent Information Systems , 2023 , 61 ( 2 ): 325 - 341 .

LI M , MIAO Z J , LU Y Y . LabanFormer: multi-scale graph attention network and transformer with gated recurrent positional encoding for labanotation generation [J ] . Neurocomputing , 2023 , 539 : 126203 .

HAMILTON W L , YING R , LESKOVEC J . Inductive representation learning on large graphs [C ] // Proceedings of the 31st International Conference on Neural Information Processing Systems . Red Hook : Curran Associates Inc. , 2017 : 1025 - 1035 .

YING R , HE R N , CHEN K F , et al . Graph convolutional neural networks for web-scale recommender systems [J ] . Association for Computing Machinery , 2018 , 3 ( 2 ): 955 - 964 .

张陶 , 廖彬 , 于炯 , 等 . 图神经网络节点分类任务基准测试及分析 [J ] . 计算机科学 , 2024 , 51 ( 4 ): 132 - 150 .

ZHANG T , LIAO B , YU J , et al . Benchmarking and analysis for graph neural network node classification task [J ] . Computer Science , 2024 , 51 ( 4 ): 132 - 150 .

YIN L H , CHEN W Z , LUO X , et al . Efficient large-scale IoT botnet detection through GraphSAINT-based subgraph sampling and graph isomorphism network [J ] . Mathematics , 2024 , 12 ( 9 ): 1315 .

CHEN Y F , ZHU H Q , CHEN Z Y . Multi-DGI: multi-head pooling deep graph infomax for human activity recognition [J ] . Mobile Networks and Applications , 2024 , 29 ( 3 ): 647 - 658 .

陈娜 , 黄金诚 , 李平 . 结合对比学习的图神经网络防御方法 [J ] . 计算机科学与探索 , 2023 , 17 ( 8 ): 1949 - 1960 .

CHEN N , HUANG J C , LI P . Graph neural network defense combined with contrastive learning [J ] . Journal of Frontiers of Computer Science and Technology , 2023 , 17 ( 8 ): 1949 - 1960 .

卢敏 , 原子婷 . 结合图对比学习的多图神经网络会话推荐方法 [J ] . 计算机科学 , 2024 , 51 ( 5 ): 54 - 61 .

LU M , YUAN Z T . Graph contrast learning based multi-graph neural network for session-based recommendation method [J ] . Computer Science , 2024 , 51 ( 5 ): 54 - 61 .

吴琳 , 许茹玉 , 粟兴旺 , 等 . 基于结构误差的图卷积网络 [J ] . 计算机应用研究 , 2023 , 40 ( 1 ): 155 - 159 .

WU L , XU R Y , SU X W , et al . Graph convolutional networks based on structural errors [J ] . Application Research of Computers , 2023 , 40 ( 1 ): 155 - 159 .

AMBILY PRAMITHA P , ABRAHAM J T . Hybrid classifier for sentiment analysis in Malayalam with modified TF-IDF features [J ] . International Journal of Modeling, Simulation, and Scientific Computing , 2023 , 14 ( 5 ): 2350038 .

郑文萍 , 刘美麟 , 杨贵 . 一种基于节点稳定性和邻域相似性的社区发现算法 [J ] . 计算机科学 , 2022 , 49 ( 9 ): 83 - 91 .

ZHENG W P , LIU M L , YANG G . Community detection algorithm based on node stability and neighbor similarity [J ] . Computer Science , 2022 , 49 ( 9 ): 83 - 91 .

XIA R T , ZHANG C X , ZHANG Y , et al . A novel graph oversampling framework for node classification in class-imbalanced graphs [J ] . Science China Information Sciences , 2024 , 67 ( 6 ): 162101 .

WANG J F , YANG J Y , Lidun . Wacml: based on graph neural network for imbalanced node classification algorithm [J ] . Multimedia Systems , 2024 , 30 ( 5 ): 258 .

ZHOU M T , GONG Z G . GraphSR: a data augmentation algorithm for imbalanced node classification [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2023 , 37 ( 4 ): 4954 - 4962 .

Views

432

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Multi-head graph attention driven feature aggregation for large-scale remote-sening constellation mission planning algorithm

Heterogeneous graph neural network algorithm based on topology information enhancement

Cross-view contrastive learning and multi-channel hypergraph convolution for session-based recommendation

A decomposable and interpretable cellular network traffic prediction model based on graph convolutional neural network

Related Author

Xiao Lixia

Zhou Jiaxi

Wei Zixiang

Dai Ao

Zhou Kangyan

She Yuxuan

LIU Xingyan

WU Tong

Related Institution

School of Electronic Engineering, Xidian University

School of Cyber Science and Engineering, 6G Research Center, Huazhong University of Science and Technology

College of Artificial Intelligence and Information Engineering, East China University of Technology

Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems, Jiaxing University

College of Information Science and Engineering, Jiaxing University

⁰