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
Description
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]
ISSN:09259902
DOI:10.1007/s10844-025-00993-x