Cross-Graph Interaction Networks

被引:1
作者
Guo, Qihang [1 ]
Yang, Xibei [1 ]
Ding, Weiping [2 ]
Qian, Yuhua [3 ]
机构
[1] Jiangsu Univ Sci & Technol, Sch Econ & Management, Zhenjiang 212100, Peoples R China
[2] Nantong Univ, Sch Informat Sci & Technol, Nantong 226019, Peoples R China
[3] Shanxi Univ, Inst Big Data Sci & Ind, Taiyuan 030006, Peoples R China
关键词
Topology; Message passing; Graph neural networks; Unsupervised learning; Training; Computer architecture; Robustness; Network topology; Electronic mail; Contrastive learning; cross-graph interaction; inter-graph message passing;
D O I
10.1109/TKDE.2025.3543377
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Graph neural networks (GNNs) are recognized as a significant methodology for handling graph-structure data. However, with the increasing prevalence of learning scenarios involving multiple graphs, traditional GNNs mostly overlook the relationships between nodes across different graphs, mainly due to their limitation of traditional message passing within each graph. In this paper, we propose a novel GNN architecture called cross-graph interaction networks (GInterNet) to enable inter-graph message passing. Specifically, we develop a cross-graph topology construction module to uncover and learn the potential topologies between nodes across different graphs. Furthermore, we establish inter-graph message passing based on the learned cross-graph topologies, achieving cross-graph interaction by aggregating information from different graphs. Finally, we employ cross-graph construction functions involving the relationships between contextual information and cross-graph topology structure to iteratively update the cross-graph topologies. Different to existing related approaches, GInterNet is designed as a cross-graph interaction paradigm for inter-graph message passing. It enables multi-graph interaction during the message passing process. Additionally, it is a plug-and-play framework that can be easily embedded into other models. We evaluate its performance in semi-supervised and unsupervised learning scenarios involving multiple graphs. A detailed theoretical analysis and extensive experiment results have shown that GInterNet improves the performance and robustness of the base models.
引用
收藏
页码:2341 / 2355
页数:15
相关论文
共 50 条
[21]   FairAGG: Toward Fair Graph Neural Networks via Fair Aggregation [J].
Zhu, Yuchang ;
Li, Jintang ;
Chen, Liang ;
Zheng, Zibin .
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS, 2024, 11 (05) :6308-6319
[22]   Graph Rewiring and Preprocessing for Graph Neural Networks Based on Effective Resistance [J].
Shen, Xu ;
Lio, Pietro ;
Yang, Lintao ;
Yuan, Ru ;
Zhang, Yuyang ;
Peng, Chengbin .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2024, 36 (11) :6330-6343
[23]   CrossGFA: wind power prediction with a multi-scale cross-graph network via a Frequency-Enhanced Channel attention mechanism [J].
Zhang, Haoyu ;
Wang, Daoli ;
Jiang, Xuchu .
APPLIED INTELLIGENCE, 2025, 55 (01)
[24]   Integrating Multi-Label Contrastive Learning With Dual Adversarial Graph Neural Networks for Cross-Modal Retrieval [J].
Qian, Shengsheng ;
Xue, Dizhan ;
Fang, Quan ;
Xu, Changsheng .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (04) :4794-4811
[25]   Graph Neural Networks Over the Air for Decentralized Tasks in Wireless Networks [J].
Gao, Zhan ;
Gunduz, Deniz .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2025, 73 :721-737
[26]   Deploying Graph Neural Networks in Wireless Networks: A Link Stability Viewpoint [J].
Li, Jun ;
Zhang, Weiwei ;
Wei, Kang ;
Chen, Guangji ;
Shi, Long ;
Chen, Wen .
IEEE WIRELESS COMMUNICATIONS LETTERS, 2024, 13 (10) :2757-2761
[27]   Graph Neural Networks for Joint Communication and Sensing Optimization in Vehicular Networks [J].
Li, Xuefei ;
Chen, Mingzhe ;
Liu, Yuchen ;
Zhang, Zhilong ;
Liu, Danpu ;
Mao, Shiwen .
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2023, 41 (12) :3893-3907
[28]   KNIGCN: Key Node Identification in UAV Swarm Networks Using a Graph Convolutional Network [J].
Ai, Qixun ;
Hou, Changbo ;
Zhou, Zhichao ;
Wu, Xiangyu ;
Song, Zhen .
IEEE INTERNET OF THINGS JOURNAL, 2025, 12 (11) :16227-16242
[29]   The Expressive Power of Graph Neural Networks: A Survey [J].
Zhang, Bingxu ;
Fan, Changjun ;
Liu, Shixuan ;
Huang, Kuihua ;
Zhao, Xiang ;
Huang, Jincai ;
Liu, Zhong .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2025, 37 (03) :1455-1474
[30]   A Flexible Diffusion Convolution for Graph Neural Networks [J].
Zhao, Songwei ;
Yu, Bo ;
Yang, Kang ;
Zhang, Sinuo ;
Hu, Jifeng ;
Jiang, Yuan ;
Yu, Philip S. ;
Chen, Hechang .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2025, 37 (06) :3118-3131