ARO-GNN: Adaptive relation-optimized graph neural networks

Abstract Existing Graph Neural Networks (GNNs) suffer from topological noise and attribute distortion when handling complex topology-attribute interactions. To overcome these limitations, we propose Adaptive Relation-Optimized Graph Neural Networks (ARO-GNN). ARO-GNN utilizes complementary informati...

Full description

Saved in:
Bibliographic Details
Main Authors: Yong Lu, Zhengguo Lin
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:Journal of King Saud University: Computer and Information Sciences
Subjects:
Online Access:https://doi.org/10.1007/s44443-025-00198-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849225845501067264
author Yong Lu
Zhengguo Lin
author_facet Yong Lu
Zhengguo Lin
author_sort Yong Lu
collection DOAJ
description Abstract Existing Graph Neural Networks (GNNs) suffer from topological noise and attribute distortion when handling complex topology-attribute interactions. To overcome these limitations, we propose Adaptive Relation-Optimized Graph Neural Networks (ARO-GNN). ARO-GNN utilizes complementary information from two different graph perspectives and dynamically adjusts the graph structure. Specifically, ARO-GNN transforms the original graph structure into a dual-graph representation. This representation captures high-order relationships and global topological features, thereby addressing the limitations inherent in traditional neighborhood-based structures. In addition, ARO-GNN employs an adaptive relation optimization mechanism that dynamically adjusts the adjacency relationships in the graph by eliminating unreliable edges while incorporating missing connections. This process mitigates topological noise and attribute distortion during message passing. Experimental results show that ARO-GNN significantly improves performance across multiple public datasets for downstream tasks.
format Article
id doaj-art-7963579ae1fa446e84fe40e315e36acb
institution Kabale University
issn 1319-1578
2213-1248
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series Journal of King Saud University: Computer and Information Sciences
spelling doaj-art-7963579ae1fa446e84fe40e315e36acb2025-08-24T11:53:51ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782213-12482025-08-0137711610.1007/s44443-025-00198-wARO-GNN: Adaptive relation-optimized graph neural networksYong Lu0Zhengguo Lin1School of Information Engineering, Minzu University of ChinaSchool of Information Engineering, Minzu University of ChinaAbstract Existing Graph Neural Networks (GNNs) suffer from topological noise and attribute distortion when handling complex topology-attribute interactions. To overcome these limitations, we propose Adaptive Relation-Optimized Graph Neural Networks (ARO-GNN). ARO-GNN utilizes complementary information from two different graph perspectives and dynamically adjusts the graph structure. Specifically, ARO-GNN transforms the original graph structure into a dual-graph representation. This representation captures high-order relationships and global topological features, thereby addressing the limitations inherent in traditional neighborhood-based structures. In addition, ARO-GNN employs an adaptive relation optimization mechanism that dynamically adjusts the adjacency relationships in the graph by eliminating unreliable edges while incorporating missing connections. This process mitigates topological noise and attribute distortion during message passing. Experimental results show that ARO-GNN significantly improves performance across multiple public datasets for downstream tasks.https://doi.org/10.1007/s44443-025-00198-wGraph neural networksGraph representation learningGraph structure learningSpectral convolution
spellingShingle Yong Lu
Zhengguo Lin
ARO-GNN: Adaptive relation-optimized graph neural networks
Journal of King Saud University: Computer and Information Sciences
Graph neural networks
Graph representation learning
Graph structure learning
Spectral convolution
title ARO-GNN: Adaptive relation-optimized graph neural networks
title_full ARO-GNN: Adaptive relation-optimized graph neural networks
title_fullStr ARO-GNN: Adaptive relation-optimized graph neural networks
title_full_unstemmed ARO-GNN: Adaptive relation-optimized graph neural networks
title_short ARO-GNN: Adaptive relation-optimized graph neural networks
title_sort aro gnn adaptive relation optimized graph neural networks
topic Graph neural networks
Graph representation learning
Graph structure learning
Spectral convolution
url https://doi.org/10.1007/s44443-025-00198-w
work_keys_str_mv AT yonglu arognnadaptiverelationoptimizedgraphneuralnetworks
AT zhengguolin arognnadaptiverelationoptimizedgraphneuralnetworks