基于Transformer模型的社交网络影响力最大化算法

于树科; 姚瑶; 严晨雪

doi:10.11959/j.issn.1000-0801.2024256

您当前的位置：

首页 >

文章列表页 >

基于Transformer模型的社交网络影响力最大化算法

研究与开发 | 更新时间：2024-12-30

- 基于Transformer模型的社交网络影响力最大化算法
- Influence maximization algorithm of social networks based on Transformer model
- 电信科学 2024年40卷第12期页码：114-124
- 作者机构：
  
  江苏商贸职业学院电子与信息学院，江苏南通 226011
- 作者简介：
  
  [ "于树科（1980- ），男，江苏商贸职业学院副教授，主要研究方向为物联网技术和计算机网络。" ]
  姚瑶（1990- ），女，江苏商贸职业学院实验师，主要研究方向为计算机应用和图形图像处理。
  严晨雪（1994- ），女，江苏商贸职业学院讲师，主要研究方向为计算机应用和网络安全。
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2024256
  中图分类号： TP391
- 收稿日期：2024-09-13，
  
  修回日期：2024-11-13，
  
  纸质出版日期：2024-12-20
- 稿件说明：
移动端阅览
于树科,姚瑶,严晨雪.基于Transformer模型的社交网络影响力最大化算法[J].电信科学,2024,40(12):114-124.

YU Shuke,YAO Yao,YAN Chenxue.Influence maximization algorithm of social networks based on Transformer model[J].Telecommunications Science,2024,40(12):114-124.
于树科,姚瑶,严晨雪.基于Transformer模型的社交网络影响力最大化算法[J].电信科学,2024,40(12):114-124. DOI： 10.11959/j.issn.1000-0801.2024256.

YU Shuke,YAO Yao,YAN Chenxue.Influence maximization algorithm of social networks based on Transformer model[J].Telecommunications Science,2024,40(12):114-124. DOI： 10.11959/j.issn.1000-0801.2024256.

摘要

基于网络拓扑结构的社交网络影响力最大化算法受网络结构影响大，导致在不同规模、不同拓扑结构的社交网络上的性能不稳定。针对此问题，提出一种基于改进Transformer模型的社交网络影响力最大化算法。首先，基于K-shell分解法筛选社交网络中影响力高的节点；然后，运用随机游走策略发现候选节点的拓扑结构信息和连接框架信息；最终，对Transformer模型进行改进，使其支持可扩展的节点特征序列，利用改进Transformer模型预测社交网络中的种子节点。在6个不同规模的真实社交网络上完成了验证实验。结果表明，所提算法在不同规模、不同拓扑结构的社交网络上均实现了较好的影响力最大化性能，且大幅提高了种子节点识别的时间效率。

Abstract

The network topology structure based influence maximization algorithms are greatly influenced by the network structure

which leads to unstable performance of social networks of different scales and different topology structures. In view of this problem

a improved Transformer model based social network influence maximization algorithm was proposed. Firstly

the high influential nodes of the society network were selected based on the k-shell decomposition method. Seconcly

the topology structure information and connection framework information of the candidate nodes were discovered by use of the random walk strategy. Finally

the Transformer model was improved

in order to support scalable node feature sequences

and the improved Transformer model was taken advantage to predict the seed nodes of the social network. Validation experiments were carried on six real social networks of different scales. The results show that the proposed algorithm realizes a good influence maximization performance on social networks of different scales and topology structures

and the time efficiency of the seed node recognition has been increased significantly.

关键词

Keywords

references

孔芳 , 李奇之 , 李帅 . 在线影响力最大化研究综述 [J ] . 计算机科学 , 2020 , 47 ( 5 ): 7 - 13 .

KONG F , LI Q Z , LI S . Survey on online influence maximization [J ] . Computer Science , 2020 , 47 ( 5 ): 7 - 13 .

CHEN W N , TAN D Z , YANG Q , et al . Ant colony optimization for the control of pollutant spreading on social networks [J ] . IEEE Transactions on Cybernetics , 2020 , 50 ( 9 ): 4053 - 4065 .

李美玲 , 钱付兰 , 徐涛 , 等 . 基于种子候选的贪心策略影响力最大化算法 [J ] . 模式识别与人工智能 , 2020 , 33 ( 11 ): 1033 - 1042 .

LI M L , QIAN F L , XU T , et al . Greedy strategy influence maximization algorithm based on seed candidates [J ] . Pattern Recognition and Artificial Intelligence , 2020 , 33 ( 11 ): 1033 - 1042 .

VENUNATH M , SUJATHA P , KOTI P , et al . Efficient community-based influence maximization in large-scale social networks [J ] . Multimedia Tools and Applications , 2024 , 83 ( 15 ): 44397 - 44424 .

王璿 , 张瑜 , 周军锋 , 等 . 基于社交网络的影响力最大化算法 [J ] . 通信学报 , 2022 , 43 ( 8 ): 151 - 163 .

WANG X , ZHANG Y , ZHOU J F , et al . Influence maximization algorithm based on social network [J ] . Journal on Communications , 2022 , 43 ( 8 ): 151 - 163 .

BAGHERI E , MIRTALAEI R S . Community-based influence maximization in social networks under a competitive linear threshold model considering positive and negative user views [J ] . International Journal of Modern Physics C , 2024 , 35 ( 1 ): 89 - 96 .

QIU L Q , YANG Z Q , ZHU S W , et al . ComIM: a community-based algorithm for influence maximization under the weighted cascade model on social networks [J ] . Intell Data Anal , 2022 , 26 : 205 - 220 .

QIN X , ZHONG C , LIN H X . Community-based influence maximization using network embedding in dynamic heterogeneous social networks [J ] . ACM Transactions on Knowledge Discovery from Data , 2023 , 17 ( 8 ): 1 - 21 .

邓帆 , 曾渊 , 刘博文 , 等 . 基于Transformer时间特征聚合的步态识别模型 [J ] . 计算机应用 , 2023 , 43 ( S1 ): 15 - 18 .

DENG F , ZENG Y , LIU B W , et al . Gait recognition model based on temporal feature aggregation with Transformer [J ] . Journal of Computer Applications , 2023 , 43 ( S1 ): 15 - 18 .

席颖 , 邬学猛 , 崔晓晖 . 基于Transformer的节点影响力排序模型 [J ] . 计算机科学 , 2024 , 51 ( 4 ): 106 - 116 .

XI Y , WU X M , CUI X H . Node influence ranking model based on transformer [J ] . Computer Science , 2024 , 51 ( 4 ): 106 - 116 .

熊才权 , 古小惠 , 吴歆韵 . 基于K-shell位置和两阶邻居的复杂网络节点重要性评估方法 [J ] . 计算机应用研究 , 2023 , 40 ( 3 ): 738 - 742 .

XIONG C Q , GU X H , WU X Y . Evaluation method of node importance in complex networks based on K-shell position and neighborhood within two steps [J ] . Application Research of Computers , 2023 , 40 ( 3 ): 738 - 742 .

邹晓红 , 许成伟 , 陈晶 , 等 . 大规模时序图中种子节点挖掘算法研究 [J ] . 通信学报 , 2022 , 43 ( 9 ): 157 - 168 .

ZOU X H , XU C W , CHEN J , et al . Research on seed node mining algorithm in large-scale temporal graph [J ] . Journal on Communications , 2022 , 43 ( 9 ): 157 - 168 .

唐建荣 , 鲍佳彤 . 基于改进SIR模型的反转事件舆情传播控制研究 [J ] . 系统仿真学报 , 2022 , 34 ( 11 ): 2406 - 2415 .

TANG J R , BAO J T . Research on network public opinion transmission mechanism of inversion event based on integrating improved SIR model [J ] . Journal of System Simulation , 2022 , 34 ( 11 ): 2406 - 2415 .

吴亚丽 , 任远光 , 董昂 , 等 . 基于邻域K-shell分布的关键节点识别方法 [J ] . 计算机工程与应用 , 2024 , 60 ( 2 ): 87 - 95 .

WU Y L , REN Y G , DONG A , et al . Key nodes identification method based on neighborhood K-shell distribution [J ] . Computer Engineering and Applications , 2024 , 60 ( 2 ): 87 - 95 .

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 recognition of influential nodes based on K-shell entropy [J ] . Computer Science , 2022 , 49 ( S2 ): 226 - 230 .

崔朝阳 , 江爱文 , 陈思航 , 等 . 基于BERT模型的多层语义粒度视觉对话算法 [J ] . 中文信息学报 , 2023 , 37 ( 11 ): 120 - 130 .

CUI Z Y , JIANG A W , CHEN S H , et al . Bert based visual dialogue algorithm with multi-level semantic context [J ] . Journal of Chinese Information Processing , 2023 , 37 ( 11 ): 120 - 130 .

WU X , MA Z H . Traveling waves for a nonlocal dispersal susceptible–infected–recovered epidemic model with the mass action infection mechanism [J ] . Mathematical Methods in the Applied Sciences , 2021 ( 46 ): 18837 - 18860 .

BARABÁSI A , BONABEAU E . Scale-free networks [J ] . Scientific American , 2003 , 288 ( 5 ): 60 - 70 .

邵玉 , 陈崚 , 刘维 . 独立级联模型下基于最大似然的负影响力源定位方法 [J ] . 计算机科学 , 2022 , 49 ( 2 ): 204 - 215 .

SHAO Y , CHEN L , LIU W . Maximum likelihood-based method for locating source of negative influence spreading under independent cascade model [J ] . Computer Science , 2022 , 49 ( 2 ): 204 - 215 .

KAZEMZADEH F , ASGHAR S A , MIRZAREZAEE M , et al . Determination of influential nodes based on the Communities’ structure to maximize influence in social networks [J ] . Neurocomputing , 2023 , 534 : 18 - 28 .

浏览量

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GRW和FastText模型的电信用户投诉文本分类应用

基于多层感知机模型的天线方位角诊断

基于机器学习的光纤窃听检测方法

融入词汇共现的社交网络用户情感Biterm主题模型

融入用户合作与领导激励的社交网络知识传播模型