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

Graph Convolutional Networks Guided by Explicitly Estimated Homophily and Heterophily Degree

Zhang, Rui; Li, Xin*
Applied Sciences-Basel2022-10DOI: 10.3390/app122010579
8阅读
引用收藏
分享

摘要

Graph convolutional networks (GCNs) have been successfully applied to learning tasks on graph-structured data. However, most traditional GCNs based on graph convolutions assume homophily in graphs, which leads to a poor performance when dealing with heterophilic graphs. Although many novel methods have recently been proposed to deal with heterophily, the effect of homophily and heterophily on classifying node pairs is not clearly separated in existing approaches and inevitably influences each other. To deal with various types of graphs more accurately, in this work we propose a new GCN-based model that leverages the explicitly estimated homophily and heterophily degree between node pairs and adaptively guides the propagation and aggregation of signed messages. We also design a pre-training process to learn homophily and heterophily degree from both original node attributes that are graph-agnostic and the localized graph structure information by using Deepwalk that reflects graph topology. Extensive experiments on eight real-world benchmarks demonstrate that the new approach achieves state-of-the-art results on three homophilic graph datasets and outperforms baselines on five heterophilic graph datasets.

学科与关键词

关键词
graph convolutional networksheterophilic graphsnode classification
相关
加载中…
  • Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
    Li, Xiang*; Zhu, Renyu; Cheng, Yao; Shan, Caihua; Luo, Siqiang; Li, Dongsheng; Qian, Weining39th International Conference on Machine Learning (ICML), Baltimore, MD, 2022-07-17 To 2022-07-23.
  • Impact of Structure of Network Based Data on Performance of Graph Neural Networks
    Fang, Junyuan*; Liu, Dong; Tse, Chi K.56th IEEE International Symposium on Circuits and Systems (ISCAS), Monterey, CA, 2023-05-21 To 2023-05-25.
  • 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
Applied Sciences-Basel
发表日期
2022-10
卷期
第 12 卷, 第 20 期
页码
10579
DOI
10.3390/app122010579
语言
ENGLISH
期刊等级
4区
成果收录
SCIE
资助标注
Ministry of Science and Technology of China [2018YFC0830400]; National Natural Science Foundation of China [61802126]

作者

  • Z

    Zhang, Rui (第一作者)

  • L

    Li, Xin (通讯)

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