View in EDS

GAWF: Influence maximization method based on graph attention weight fusion.

Saved in:
Bibliographic Details
Title: GAWF: Influence maximization method based on graph attention weight fusion.
Authors: Liu, Xiaoyang1 (AUTHOR) lxy3103@cqut.edu.cn, Han, Qi1 (AUTHOR) hanki2022@stu.cqut.edu.cn, Wang, Wei2 (AUTHOR) wwzqbx@hotmail.com, Zhan, Xiuxiu3,4 (AUTHOR) zhanxiuxiu@hznu.edu.cn, Lu, Ling1 (AUTHOR) ll@cqut.edu.cn, Ye, Zhijing5 (AUTHOR) zhijingye@microsoft.com
Source: International Journal of Modern Physics C: Computational Physics & Physical Computation. Jun2026, Vol. 37 Issue 6, p1-24. 24p.
Subjects: Graph neural networks, Sparse graphs, Communication network analysis, Mathematical optimization, Comparative studies
Abstract: Influence Maximization (IM) involves identifying a limited number of high-influence nodes within a network to maximize the number of influenced nodes. Although graph neural network-based IM methods have significantly improved generalization capability and propagation effect compared to traditional methods, they face challenges in capturing features of sparse graph networks and difficulties in computing gradient descent, leading to suboptimal diffusion effects and difficult model training. To address these issues, a Graph Attention Weight Fusion-based Influence Maximization method (GAWF) is proposed. First, the GAWF integrates adaptive weight decay optimization using AdamW with graph attention weight fusion. Second, inspired by the Beta-VAE in the CV field, an IM-VAE encoder method tailored for the IM problem is introduced. Finally, extensive comparative analysis experiments are conducted on four real datasets, including Jazz, Cora_ML and Power_Grid, to evaluate three traditional and four learning-based IM algorithms. Experimental results consistently show that the proposed GAWF method achieves a 0.1% ∼ 6% improvement across various datasets, with more significant enhancements on sparser datasets, indicating that GAWF is reasonable and effective. Additionally, the proposed GAWF method holds promising applications in real-world scenarios such as social networks and public opinion analysis. [ABSTRACT FROM AUTHOR]
Copyright of International Journal of Modern Physics C: Computational Physics & Physical Computation is the property of World Scientific Publishing Company and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 189732908
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: GAWF: Influence maximization method based on graph attention weight fusion.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Liu%2C+Xiaoyang%22">Liu, Xiaoyang</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> lxy3103@cqut.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Han%2C+Qi%22">Han, Qi</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> hanki2022@stu.cqut.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Wang%2C+Wei%22">Wang, Wei</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> wwzqbx@hotmail.com</i><br /><searchLink fieldCode="AR" term="%22Zhan%2C+Xiuxiu%22">Zhan, Xiuxiu</searchLink><relatesTo>3,4</relatesTo> (AUTHOR)<i> zhanxiuxiu@hznu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Lu%2C+Ling%22">Lu, Ling</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> ll@cqut.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Ye%2C+Zhijing%22">Ye, Zhijing</searchLink><relatesTo>5</relatesTo> (AUTHOR)<i> zhijingye@microsoft.com</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22International+Journal+of+Modern+Physics+C%3A+Computational+Physics+%26+Physical+Computation%22">International Journal of Modern Physics C: Computational Physics & Physical Computation</searchLink>. Jun2026, Vol. 37 Issue 6, p1-24. 24p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Graph+neural+networks%22">Graph neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Sparse+graphs%22">Sparse graphs</searchLink><br /><searchLink fieldCode="DE" term="%22Communication+network+analysis%22">Communication network analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematical+optimization%22">Mathematical optimization</searchLink><br /><searchLink fieldCode="DE" term="%22Comparative+studies%22">Comparative studies</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Influence Maximization (IM) involves identifying a limited number of high-influence nodes within a network to maximize the number of influenced nodes. Although graph neural network-based IM methods have significantly improved generalization capability and propagation effect compared to traditional methods, they face challenges in capturing features of sparse graph networks and difficulties in computing gradient descent, leading to suboptimal diffusion effects and difficult model training. To address these issues, a Graph Attention Weight Fusion-based Influence Maximization method (GAWF) is proposed. First, the GAWF integrates adaptive weight decay optimization using AdamW with graph attention weight fusion. Second, inspired by the Beta-VAE in the CV field, an IM-VAE encoder method tailored for the IM problem is introduced. Finally, extensive comparative analysis experiments are conducted on four real datasets, including Jazz, Cora_ML and Power_Grid, to evaluate three traditional and four learning-based IM algorithms. Experimental results consistently show that the proposed GAWF method achieves a 0.1% ∼ 6% improvement across various datasets, with more significant enhancements on sparser datasets, indicating that GAWF is reasonable and effective. Additionally, the proposed GAWF method holds promising applications in real-world scenarios such as social networks and public opinion analysis. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of International Journal of Modern Physics C: Computational Physics & Physical Computation is the property of World Scientific Publishing Company and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=189732908
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1142/S0129183125420021
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 24
        StartPage: 1
    Subjects:
      – SubjectFull: Graph neural networks
        Type: general
      – SubjectFull: Sparse graphs
        Type: general
      – SubjectFull: Communication network analysis
        Type: general
      – SubjectFull: Mathematical optimization
        Type: general
      – SubjectFull: Comparative studies
        Type: general
    Titles:
      – TitleFull: GAWF: Influence maximization method based on graph attention weight fusion.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Liu, Xiaoyang
      – PersonEntity:
          Name:
            NameFull: Han, Qi
      – PersonEntity:
          Name:
            NameFull: Wang, Wei
      – PersonEntity:
          Name:
            NameFull: Zhan, Xiuxiu
      – PersonEntity:
          Name:
            NameFull: Lu, Ling
      – PersonEntity:
          Name:
            NameFull: Ye, Zhijing
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: Jun2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 01291831
          Numbering:
            – Type: volume
              Value: 37
            – Type: issue
              Value: 6
          Titles:
            – TitleFull: International Journal of Modern Physics C: Computational Physics & Physical Computation
              Type: main
ResultId 1