• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Yang, Yachao (Yang, Yachao.) | Sun, Yanfeng (Sun, Yanfeng.) | Wang, Shaofan (Wang, Shaofan.) | Guo, Jipeng (Guo, Jipeng.) | Gao, Junbin (Gao, Junbin.) | Ju, Fujiao (Ju, Fujiao.) | Yin, Baocai (Yin, Baocai.)

收录:

EI Scopus

摘要:

Graph Neural Networks (GNNs) have shown great performance in learning representations for graph-structured data. However, recent studies have found that the interference between topology and attribute can lead to distorted node representations. Most GNNs are designed based on homophily assumptions, thus they cannot be applied to graphs with heterophily. This research critically analyzes the propagation principles of various GNNs and the corresponding challenges from an optimization perspective. A novel GNN called Graph Neural Networks with Soft Association between Topology and Attribute (GNN-SATA) is proposed. Different embeddings are utilized to gain insights into attributes and structures while establishing their interconnections through soft association. Further as integral components of the soft association, a Graph Pruning Module (GPM) and Graph Augmentation Module (GAM) are developed. These modules dynamically remove or add edges to the adjacency relationships to make the model better fit with graphs with homophily or heterophily. Experimental results on homophilic and heterophilic graph datasets convincingly demonstrate that the proposed GNN-SATA effectively captures more accurate adjacency relationships and outperforms state-of-the-art approaches. Especially on the heterophilic graph dataset Squirrel, GNN-SATA achieves a 2.81% improvement in accuracy, utilizing merely 27.19% of the original number of adjacency relationships. Our code is released at https://github.com/wwwfadecom/GNN-SATA. Copyright © 2024, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

关键词:

Topology Graph neural networks Backpropagation

作者机构:

  • [ 1 ] [Yang, Yachao]Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, Faculty of Information Technology, Beijing University of Technology, Beijing, China
  • [ 2 ] [Sun, Yanfeng]Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, Faculty of Information Technology, Beijing University of Technology, Beijing, China
  • [ 3 ] [Wang, Shaofan]Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, Faculty of Information Technology, Beijing University of Technology, Beijing, China
  • [ 4 ] [Guo, Jipeng]College of Information Science and Technology, Beijing University of Chemical Technology, China
  • [ 5 ] [Gao, Junbin]Discipline of Business Analytics, The University of Sydney Business School, The University of Sydney, Camperdown; NSW; 2006, Australia
  • [ 6 ] [Ju, Fujiao]Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, Faculty of Information Technology, Beijing University of Technology, Beijing, China
  • [ 7 ] [Yin, Baocai]Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, Faculty of Information Technology, Beijing University of Technology, Beijing, China

通讯作者信息:

电子邮件地址:

查看成果更多字段

相关关键词:

来源 :

ISSN: 2159-5399

年份: 2024

期: 8

卷: 38

页码: 9260-9268

语种: 英文

被引次数:

WoS核心集被引频次:

SCOPUS被引频次: 7

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 1

归属院系:

在线人数/总访问数:426/4899700
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司