• 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:

Peng, Tianhao (Peng, Tianhao.) | Wu, Wenjun (Wu, Wenjun.) | Yuan, Haitao (Yuan, Haitao.) | Bao, Zhifeng (Bao, Zhifeng.) | Pengru, Zhao (Pengru, Zhao.) | Yu, Xin (Yu, Xin.) | Lin, Xuetao (Lin, Xuetao.) | Liang, Yu (Liang, Yu.) | Pu, Yanjun (Pu, Yanjun.)

收录:

EI Scopus

摘要:

Graph neural networks (GNNs) have shown ad-vantages in graph-based analysis tasks. However, most existing methods have the homogeneity assumption and show poor performance on heterophilic graphs, where the linked nodes have dissimilar features and different class labels, and the semantically related nodes might be multi-hop away. To address this limitation, this paper presents GraphRARE, a general framework built upon node relative entropy and deep reinforcement learning, to strengthen the expressive capability of GNNs. An innovative node relative entropy, which considers node features and structural similarity, is used to measure mutual information between node pairs. In addition, to avoid the sub-optimal solutions caused by mixing useful information and noises of remote nodes, a deep reinforcement learning-based algorithm is developed to optimize the graph topology. This algorithm selects informative nodes and discards noisy nodes based on the defined node relative en-tropy. Extensive experiments are conducted on seven real-world datasets. The experimental results demonstrate the superiority of GraphRARE in node classification and its capability to optimize the original graph topology. © 2024 IEEE.

关键词:

Entropy Graph theory Graphic methods Graph neural networks Graph structures Deep learning Reinforcement learning

作者机构:

  • [ 1 ] [Peng, Tianhao]Beihang University, China
  • [ 2 ] [Wu, Wenjun]Beihang University, China
  • [ 3 ] [Yuan, Haitao]Nanyang Technological University, Singapore
  • [ 4 ] [Bao, Zhifeng]RMIT University, Australia, Australia
  • [ 5 ] [Pengru, Zhao]Beihang University, China
  • [ 6 ] [Yu, Xin]Beihang University, China
  • [ 7 ] [Lin, Xuetao]Beihang University, China
  • [ 8 ] [Liang, Yu]Beijing University of Technology, China
  • [ 9 ] [Pu, Yanjun]Beihang University, 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:

相关文章:

来源 :

ISSN: 1084-4627

年份: 2024

页码: 2489-2502

语种: 英文

被引次数:

WoS核心集被引频次:

SCOPUS被引频次: 3

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:419/4953005
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