View in EDS

Redefining edge representations for enhanced information propagation on GNNs.

Saved in:
Bibliographic Details
Title: Redefining edge representations for enhanced information propagation on GNNs.
Authors: Zhuo, Shengda1 (AUTHOR) zhuosd96@gmail.com, Wang, Tianbo2 (AUTHOR) 201907010111@stu.bucea.edu.cn, Li, Lichun3 (AUTHOR) lilichun2021@126.com, Zhou, Zifeng1 (AUTHOR) zacharychow1999@gmail.com, Guan, Zelin1 (AUTHOR) a508954254@gmail.com, Tang, Yin3 (AUTHOR) ytang@jnu.edu.cn, Chen, Min4 (AUTHOR) minchen2012@hust.edu.cn, Huang, Shuqiang1 (AUTHOR) hsq@jnu.edu.cn
Source: Journal of Intelligent Information Systems. Jun2026, Vol. 64 Issue 3, p1175-1199. 25p.
Subjects: Graph neural networks, Message passing (Computer science), Clustering algorithms, Information dissemination
Abstract: Graph Neural Networks (GNNs) have achieved great success in learning node representations from graph-structured data. Most GNNs adopt a message-passing paradigm, where nodes act as information carriers and edges serve as communication channels. However, existing models typically represent edges using scalar weights, which only modulate the overall strength of messages and fail to distinguish the importance of individual feature dimensions. This coarse-grained formulation limits the expressiveness of information propagation. To address this issue, we propose to represent edges as vectors, enabling fine-grained, dimension-specific control over the message-passing process. We refer to these edge vectors as relation representations, as they capture the semantic relations between connected nodes. Building on this idea, we present a novel model, Relation-Enhanced Feature Preference Network (ReFPN), which integrates relation representation learning into the message-passing framework. ReFPN dynamically adjusts the contribution of each feature dimension based on the learned relation representations, thereby enhancing the effectiveness of information aggregation. Extensive experiments on five benchmark datasets demonstrate that ReFPN consistently outperforms strong baselines in both node classification and clustering tasks, validating the superiority of fine-grained relation-aware propagation. [ABSTRACT FROM AUTHOR]
Copyright of Journal of Intelligent Information Systems is the property of Springer Nature 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: 193810072
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Redefining edge representations for enhanced information propagation on GNNs.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Zhuo%2C+Shengda%22">Zhuo, Shengda</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> zhuosd96@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Wang%2C+Tianbo%22">Wang, Tianbo</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> 201907010111@stu.bucea.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Li%2C+Lichun%22">Li, Lichun</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> lilichun2021@126.com</i><br /><searchLink fieldCode="AR" term="%22Zhou%2C+Zifeng%22">Zhou, Zifeng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> zacharychow1999@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Guan%2C+Zelin%22">Guan, Zelin</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> a508954254@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Tang%2C+Yin%22">Tang, Yin</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> ytang@jnu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Chen%2C+Min%22">Chen, Min</searchLink><relatesTo>4</relatesTo> (AUTHOR)<i> minchen2012@hust.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Huang%2C+Shuqiang%22">Huang, Shuqiang</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> hsq@jnu.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Journal+of+Intelligent+Information+Systems%22">Journal of Intelligent Information Systems</searchLink>. Jun2026, Vol. 64 Issue 3, p1175-1199. 25p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Graph+neural+networks%22">Graph neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Message+passing+%28Computer+science%29%22">Message passing (Computer science)</searchLink><br /><searchLink fieldCode="DE" term="%22Clustering+algorithms%22">Clustering algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Information+dissemination%22">Information dissemination</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Graph Neural Networks (GNNs) have achieved great success in learning node representations from graph-structured data. Most GNNs adopt a message-passing paradigm, where nodes act as information carriers and edges serve as communication channels. However, existing models typically represent edges using scalar weights, which only modulate the overall strength of messages and fail to distinguish the importance of individual feature dimensions. This coarse-grained formulation limits the expressiveness of information propagation. To address this issue, we propose to represent edges as vectors, enabling fine-grained, dimension-specific control over the message-passing process. We refer to these edge vectors as relation representations, as they capture the semantic relations between connected nodes. Building on this idea, we present a novel model, Relation-Enhanced Feature Preference Network (ReFPN), which integrates relation representation learning into the message-passing framework. ReFPN dynamically adjusts the contribution of each feature dimension based on the learned relation representations, thereby enhancing the effectiveness of information aggregation. Extensive experiments on five benchmark datasets demonstrate that ReFPN consistently outperforms strong baselines in both node classification and clustering tasks, validating the superiority of fine-grained relation-aware propagation. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Journal of Intelligent Information Systems is the property of Springer Nature 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=193810072
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s10844-025-00993-x
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 25
        StartPage: 1175
    Subjects:
      – SubjectFull: Graph neural networks
        Type: general
      – SubjectFull: Message passing (Computer science)
        Type: general
      – SubjectFull: Clustering algorithms
        Type: general
      – SubjectFull: Information dissemination
        Type: general
    Titles:
      – TitleFull: Redefining edge representations for enhanced information propagation on GNNs.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Zhuo, Shengda
      – PersonEntity:
          Name:
            NameFull: Wang, Tianbo
      – PersonEntity:
          Name:
            NameFull: Li, Lichun
      – PersonEntity:
          Name:
            NameFull: Zhou, Zifeng
      – PersonEntity:
          Name:
            NameFull: Guan, Zelin
      – PersonEntity:
          Name:
            NameFull: Tang, Yin
      – PersonEntity:
          Name:
            NameFull: Chen, Min
      – PersonEntity:
          Name:
            NameFull: Huang, Shuqiang
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: Jun2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 09259902
          Numbering:
            – Type: volume
              Value: 64
            – Type: issue
              Value: 3
          Titles:
            – TitleFull: Journal of Intelligent Information Systems
              Type: main
ResultId 1