ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Are Graph Convolutional Networks With Random Weights Feasible?

Huang, Changqin; Li, Ming*; Cao, Feilong; Fujita, Hamido; Li, Zhao; Wu, Xindong合肥工业大学; 浙江师范大学
IEEE Transactions on Pattern Analysis and Machine Intelligence2023-3-1DOI: 10.1109/TPAMI.2022.3183143
20被引11阅读
引用收藏
分享

摘要

Graph Convolutional Networks (GCNs), as a prominent example of graph neural networks, are receiving extensive attention for their powerful capability in learning node representations on graphs. There are various extensions, either in sampling and/or node feature aggregation, to further improve GCNs' performance, scalability and applicability in various domains. Still, there is room for further improvements on learning efficiency because performing batch gradient descent using the full dataset for every training iteration, as unavoidable for training (vanilla) GCNs, is not a viable option for large graphs. The good potential of random features in speeding up the training phase in large-scale problems motivates us to consider carefully whether GCNs with random weights are feasible. To investigate theoretically and empirically this issue, we propose a novel model termed Graph Convolutional Networks with Random Weights (GCN-RW) by revising the convolutional layer with random filters and simultaneously adjusting the learning objective with regularized least squares loss. Theoretical analyses on the model's approximation upper bound, structure complexity, stability and generalization, are provided with rigorous mathematical proofs. The effectiveness and efficiency of GCN-RW are verified on semi-supervised node classification task with several benchmark datasets. Experimental results demonstrate that, in comparison with some state-of-the-art approaches, GCN-RW can achieve better or matched accuracies with less training time cost.

学科与关键词

关键词
TrainingAnalytical modelsUpper boundStability analysisNeural networksConvolutionConvolutional neural networksGraph convolutional networksrandom weightsstability and generalizationapproximation upper bound
相关
加载中…
  • Efficient Nodes Representation Learning with Residual Feature Propagation
    Wu, Fan; Li, Duantengchuan*; Lin, Ke; Zhang, Huawei25th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), Int Inst Informat Technol Hyderabad, ELECTR NETWORK, 2021-05-11 To 2021-05-14.被引 2
  • Graph Convolutional Networks Guided by Explicitly Estimated Homophily and Heterophily Degree
    Zhang, Rui; Li, Xin*Applied Sciences-Basel, 2022, 12(20): 10579.
  • Graph deconvolutional networks
    Zhang, Chun-Yang; Hu, Junfeng*; Yang, Lin*; Chen, C. L. Philip; Yao, ZhiliangInformation Sciences, 2020, 518: 330-340.被引 12
查看全部 →

发表信息

论文状态
公开发表
期刊
IEEE Transactions on Pattern Analysis and Machine Intelligence
发表日期
2023-03-01
卷期
第 45 卷, 第 3 期
页码
2751-2768
DOI
10.1109/TPAMI.2022.3183143
语言
ENGLISH
成果收录
SCIE
资助标注
National Natural Science Foundation of China [62037001, U21A20473, 62172370, 62176244]; Grants-in-Aid for Scientific Research [20K11955] Funding Source: KAKEN

作者

  • H

    Huang, Changqin (第一作者)

    zhejiang normal univ

  • L

    Li, Ming (通讯)

    zhejiang normal univ

查看全部 6 位作者收起作者
  • C

    Cao, Feilong

    china jiliang univ

  • F

    Fujita, Hamido

  • L

    Li, Zhao

  • W

    Wu, Xindong

    hefei univ technol

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417