• 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:

Zheng, Lei (Zheng, Lei.) | Quan, Pei (Quan, Pei.) | Shi, Yong (Shi, Yong.) | Niu, Lingfeng (Niu, Lingfeng.)

收录:

EI Scopus

摘要:

Graph neural network is a powerful tool for solving various graph tasks, such as node classification and graph classification. However, there is increasing evidence suggesting that it is sensitive to distribution shifts and its performance is reduced by at least 10% when distribution shifts happen. In the last three years, to solve the wide existing distribution shifts, some distribution robust strategies have been designed specifically for graph neural networks. It is also one of the popular research topics in graph neural networks in recent years. Therefore, in this paper, we divide these strategies into three categories depending on the specific problems they solve: distribution shift for semi-supervised node classification, distribution shift for unsupervised node classification, and out-of-distribution shift for graph classification. Furthermore, we discuss and summarize the strategies for each type of problem. After investigating these strategies, we put forward future development direction. © 2024 The Authors.

关键词:

Neural network models Graph neural networks Graph algorithms

作者机构:

  • [ 1 ] [Zheng, Lei]The School of Mathematical Sciences, University of Chinese Academy of Sciences, Beijing; 100190, China
  • [ 2 ] [Zheng, Lei]Research Center on Fictitious Economy and Data Science, Chinese Academy of Sciences, Beijing; 100190, China
  • [ 3 ] [Zheng, Lei]Key Laboratory of Big Data Mining and Knowledge Management, Chinese Academy of Sciences, Beijing; 100190, China
  • [ 4 ] [Quan, Pei]The College of Economics and Management, Beijing University of Technology, Beijing; 100124, China
  • [ 5 ] [Shi, Yong]The School of Economics and Management, University of Chinese Academy of Sciences, Beijing; 1001090, China
  • [ 6 ] [Shi, Yong]Research Center on Fictitious Economy and Data Science, Chinese Academy of Sciences, Beijing; 100190, China
  • [ 7 ] [Shi, Yong]Key Laboratory of Big Data Mining and Knowledge Management, Chinese Academy of Sciences, Beijing; 100190, China
  • [ 8 ] [Niu, Lingfeng]The School of Economics and Management, University of Chinese Academy of Sciences, Beijing; 1001090, China
  • [ 9 ] [Niu, Lingfeng]Research Center on Fictitious Economy and Data Science, Chinese Academy of Sciences, Beijing; 100190, China
  • [ 10 ] [Niu, Lingfeng]Key Laboratory of Big Data Mining and Knowledge Management, Chinese Academy of Sciences, Beijing; 100190, 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 :

年份: 2024

卷: 242

页码: 1281-1286

语种: 英文

被引次数:

WoS核心集被引频次:

SCOPUS被引频次: 1

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:372/4879831
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