基于深度学习的多样化复杂网络影响力节点识别

马玉磊; 郭莎莎

doi:10.11959/j.issn.1000-0801.2025107

您当前的位置：

首页 >

文章列表页 >

基于深度学习的多样化复杂网络影响力节点识别

研究与开发 | 更新时间：2025-06-28

- 基于深度学习的多样化复杂网络影响力节点识别
- Influential nodes recognition of diverse complex network based on deep learning
- 电信科学 2025年41卷第6期页码：154-165
- 作者机构：
  
  新乡学院计算机与信息工程学院，河南新乡 453000
- 作者简介：
  
  [ "马玉磊（1982- ），男，新乡学院计算机与信息工程学院副教授，主要研究方向为计算机网络与网络分析。" ]
  郭莎莎（1993- ），女，新乡学院计算机与信息工程学院助教，主要研究方向为图像处理。
- 基金信息：
  
  河南省科技厅重点研发与推广专项（科技攻关）(212102210405);新乡学院教育教学改革研究与实践项目(31);Xinxiang University’s Teaching Reform Research and Practice Project (No.31)
- DOI：10.11959/j.issn.1000-0801.2025107
  中图分类号： TP391
- 收稿：2024-11-05，
  
  修回：2025-04-07，
  
  纸质出版：2025-06-20
- 稿件说明：
移动端阅览
马玉磊,郭莎莎.基于深度学习的多样化复杂网络影响力节点识别[J].电信科学,2025,41(06):154-165.

MA Yulei,GUO Shasha.Influential nodes recognition of diverse complex network based on deep learning[J].Telecommunications Science,2025,41(06):154-165.
马玉磊,郭莎莎.基于深度学习的多样化复杂网络影响力节点识别[J].电信科学,2025,41(06):154-165. DOI： 10.11959/j.issn.1000-0801.2025107.

MA Yulei,GUO Shasha.Influential nodes recognition of diverse complex network based on deep learning[J].Telecommunications Science,2025,41(06):154-165. DOI： 10.11959/j.issn.1000-0801.2025107.

摘要

为提高多样化复杂网络中影响力节点识别的准确性和鲁棒性，提出一种基于深度学习的多样化复杂网络影响力节点识别方法。首先，采用多个中心性指标从不同方面评估节点在网络拓扑结构中的重要性，通过可学习权重向量自适应地决定不同复杂网络中各指标的权重；接着，提出一种支持不同特征维度的Transformer框架；最后，利用Transformer模型对不同距离的邻居信息进行分级聚合，以提取邻域的上下文信息。在多种复杂网络数据集上完成了验证实验，结果表明，所提方法在不同规模、不同类型的复杂网络上均取得了较好的影响力节点识别性能，有效提高了影响力节点识别的准确性和鲁棒性。

Abstract

To improve the accuracy and robustness of influential node recognition in diverse complex networks

a deep learning-based recognition method for influential nodes in diverse complex networks was proposed. Firstly

multiple centrality indexes were utilized to evaluate the importance of network topology from different perspectives

the weight of each index in different complex networks was decided adaptively through the learnable weight vector. Secondly

a new Transformer framework that could handle features of different dimensions was proposed. Finally

the Transformer model was exployed to realize hierarchical aggregation of the neighbor information in different distances

so as to extract the contextual information of the neighborhood. Validation experiments were carried on multiple complex network datasets

the results showed that the proposed method achieved a good recognition performance of influential nodes for the complex networks of different scales and different categories

effectively improving the accuracy and robustness of influential node recognition.

关键词

Keywords

references

曾祥宇 , 龙海霞 , 杨旭华 . 基于马尔可夫相似性增强和网络嵌入的社区发现 [J ] . 计算机科学 , 2023 , 50 ( 4 ): 56 - 62 .

ZENG X Y , LONG H X , YANG X H . Community detection based on Markov similarity enhancement and network embedding [J ] . Computer Science , 2023 , 50 ( 4 ): 56 - 62 .

CHEN X , ZHANG M , YIN S , et al . Construction of protein-protein interaction networks on capsicum against sepsis by regulating of molecular mechanisms: bioinformatics approaches [J ] . Journal of Biomedical Nanotechnology , 2023 , 19 ( 6 ): 1062 - 1069 .

汪亭亭 , 梁宗文 , 张若曦 . 基于信息熵与迭代因子的复杂网络节点重要性评价方法 [J ] . 物理学报 , 2023 , 72 ( 4 ): 337 - 347 .

WANG T T , LIANG Z W , ZHANG R X . Importance evaluation method of complex network nodes based on information entropyand iteration factor [J ] . Acta Physica Sinica , 2023 , 72 ( 4 ): 337 - 347 .

许星舟 . 基于节点中心性和标签传播算法的社区检测 [J ] . 计算机应用与软件 , 2024 , 41 ( 3 ): 290 - 296, 344 .

XU X Z . Community detection based on node centrality and label propagation algorithm [J ] . Computer Applications and Software , 2024 , 41 ( 3 ): 290 - 296, 344 .

WANG Y Z , WANG R , WANG Y , et al . The alterations of brain network degree centrality in patients with neovascular glaucoma: a resting-state fMRI study [J ] . Neurological Sciences , 2023 , 44 ( 8 ): 2915 - 2922 .

MA J L , WANG S Y . A closeness centrality reconnection strategy to suppress the traffic-driven epidemic spreading [J ] . International Journal of Modern Physics C , 2024 , 35 ( 5 ): 2450053 .

刘宽 , 刘海员 , 张雷 . 一种基于特征向量中心性的基因调控网络结构推测算法 [J ] . 南开大学学报(自然科学版) , 2023 , 56 ( 4 ): 40 - 44 .

LIU K , LIU H Y , ZHANG L . An algorithm for gene regulatory network structure inference based on eigenvector centrality [J ] . Acta Scientiarum Naturalium Universitatis Nankaiensis , 2023 , 56 ( 4 ): 40 - 44 .

李静 , 路庆昌 , 徐鹏程 , 等 . 考虑站点耦合关系的大型城市轨道交通网络级联失效分析 [J ] . 浙江大学学报(工学版) , 2024 , 58 ( 9 ): 1945 - 1955 .

LI J , LU Q C , XU P C , et al . Cascading failure analysis of large-scale urban rail transit network considering station coupling relationship [J ] . Journal of Zhejiang University (Engineering Science) , 2024 , 58 ( 9 ): 1945 - 1955 .

WANG X H , YANG Q , LIU M Z , et al . Comprehensive influence of topological location and neighbor information on identifying influential nodes in complex networks [J ] . PLoS One , 2021 , 16 ( 5 ): e0251208 .

原慧琳 , 冯宠 . 基于k-shell熵的影响力节点的排序与识别 [J ] . 计算机科学 , 2022 , 49 ( S2 ): 226 - 230 .

YUAN H L , FENG C . Ranking and identification of influence nodes based on k-shell entropy [J ] . Computer Science , 2022 , 49 ( S2 ): 226 - 230 .

龚志豪 , 蒋沅 , 代冀阳 , 等 . 基于交叉熵的节点重要性排序算法 [J ] . 电子科技大学学报 , 2023 , 52 ( 6 ): 944 - 953 .

GONG Z H , JIANG Y , DAI J Y , et al . Node importance ranking algorithm based on cross entropy [J ] . Journal of University of Electronic Science and Technology of China , 2023 , 52 ( 6 ): 944 - 953 .

孙轩宇 , 史艳翠 . 融合项目影响力的图神经网络会话推荐模型 [J ] . 计算机应用 , 2023 , 43 ( 12 ): 3689 - 3696 .

SUN X Y , SHI Y C . Session-based recommendation model by graph neural network fused with item influence [J ] . Journal of Computer Applications , 2023 , 43 ( 12 ): 3689 - 3696 .

臧玑珣 , 徐鑫航 . 基于网络嵌入的农产品销售推荐系统 [J ] . 计算机技术与发展 , 2022 , 32 ( 10 ): 209 - 214 .

ZANG J X , XU X H . Recommendation system for agricultural products marketing channels based on network embedding [J ] . Computer Technology and Development , 2022 , 32 ( 10 ): 209 - 214 .

RASHID Y , BHAT J I . OlapGN: a multi-layered graph convolution network-based model for locating influential nodes in graph networks [J ] . Knowledge-Based Systems , 2024 , 283 : 111163 .

WU Y H , HU Y M , YIN S Y , et al . A graph convolutional network model based on regular equivalence for identifying influential nodes in complex networks [J ] . Knowledge-Based Systems , 2024 , 301 : 112235 .

GUIMERÀ R , DANON L , DÍAZ-GUILERA A , et al . Self-similar community structure in a network of human interactions [J ] . Physical Review E , 2003 , 68 ( 6 ): 065103 .

GLEISER P M , DANON L . Community structure in Jazz [J ] . Advances in Complex Systems , 2003 , 6 ( 4 ): 565 - 573 .

SPRING N , MAHAJAN R , WETHERALL D , et al . Measuring ISP topologies with rocketfuel [J ] . IEEE/ACM Transactions on Networking , 2004 , 12 ( 1 ): 2 - 16 .

袁榕 , 宋玉蓉 , 孟繁荣 . 一种基于加权网络拓扑权重的链路预测方法 [J ] . 计算机科学 , 2020 , 47 ( 5 ): 265 - 270 .

YUAN R , SONG Y R , MENG F R . Link prediction method based on weighted network topology weight [J ] . Computer Science , 2020 , 47 ( 5 ): 265 - 270 .

PASTOR-SATORRAS R , CASTELLANO C , VAN MIEGHEM P , et al . Epidemic processes in complex networks [J ] . Reviews of Modern Physics , 2015 , 87 ( 3 ): 925 - 979 .

BARABÁSI A L , BONABEAU E . Scale-free networks [J ] . Scientific American , 2003 , 288 ( 5 ): 60 - 69 .

ZHANG M , WANG X J , JIN L , et al . A new approach for evaluating node importance in complex networks via deep learning methods [J ] . Neurocomputing , 2022 , 497 : 13 - 27 .

CHAKRAVARTHY T S , SELVARAJ L . HIKS: a K-shell-weighted hybrid approach method for detecting influential nodes in complex networks using possible edge weights [J ] . International Journal of Communication Systems , 2024 , 37 ( 7 ): e5722 .

浏览量

453

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于自注意力机制的大规模MIMO信道状态信息特征向量反馈方法

DGSF-AOT：动态门控与自注意力融合增强的人脸图像修复

基于GPT网络的日志文本故障关联规则挖掘研究

基于SDL-YOLO的红外图像人车检测算法

水声通信物理层技术综述：从模型驱动到数据驱动