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 deconvolutional networks

Zhang, Chun-Yang; Hu, Junfeng*; Yang, Lin*; Chen, C. L. Philip; Yao, Zhiliang福州大学
Information Sciences2020-5DOI: 10.1016/j.ins.2020.01.028
12被引6阅读
引用收藏
分享

摘要

Graphs and networks are very common data structure for modelling complex systems that are composed of a number of nodes and topologies, such as social networks, citation networks, biological protein-protein interactions networks, etc. In recent years, machine learning has become an efficient technique to obtain representation of graph for downstream graph analysis tasks, including node classification, link prediction, and community detection. Different with traditional graph analytical models, the representation learning on graph tries to learn low dimensional embeddings by means of machine learning models that could be trained in supervised, unsupervised or semi-supervised manners. Compared with traditional approaches that directly use input node attributes, these embeddings are much more informative and helpful for graph analysis. There are a number of developed models in this respect, that are different in the ways of measuring similarity of vertexes in both original space and feature space. In order to learn more efficient node representation with better generalization property, we propose a task-independent graph representation model, called as graph deconvolutional network (GDN), and corresponding unsupervised learning algorithm in this paper. Different with graph convolution network (GCN) from the scratch, which produces embeddings by convolving input attribute vectors with learned filters, the embeddings of the proposed GDN model are desired to be convolved with filters so that reconstruct the input node attribute vectors as far as possible. The embeddings and filters are alternatively optimized in the learning procedure. The correctness of the proposed GDN model is verified by multiple tasks over several datasets. The experimental results show that the GDN model outperforms existing alternatives with a big margin.

学科与关键词

关键词
Graph representationRepresentation learningUnsupervised learningNode embeddingMachine learning
相关
加载中…
  • A Comprehensive Survey on Deep Graph Representation Learning Methods
    Chikwendu, Ijeoma Amuche*; Zhang, Xiaoling; Agyemang, Isaac Osei; Adjei-Mensah, Isaac; Chima, Ukwuoma Chiagoziem; Ejiyi, Chukwuebuka JosephJournal of Artificial Intelligence Research, 2023, 78: 287-356.被引 13
  • Graph Convolutional Networks Guided by Explicitly Estimated Homophily and Heterophily Degree
    Zhang, Rui; Li, Xin*Applied Sciences-Basel, 2022, 12(20): 10579.
  • Graph representation learning via simple jumping knowledge networks
    Yang, Fei; Zhang, Huyin*; Tao, Shiming; Hao, ShengApplied Intelligence, 2022, 52(10): 11324-11342.被引 3
查看全部 →

发表信息

论文状态
公开发表
期刊
Information Sciences
发表日期
2020-05
卷期
第 518 卷
页码
330-340
DOI
10.1016/j.ins.2020.01.028
语言
MULTI-LANGUAGE
期刊收录
NSL.SCIE
期刊等级
1区
成果收录
SCIE
资助标注
National Natural Science Foundation of China [61603096, 61751202, 61751205, 61572540, U1813203, U1801262]; Natural Science Foundation of Fujian Province [2017J01750]

作者

  • Z

    Zhang, Chun-Yang (第一作者)

    fuzhou univ

  • H

    Hu, Junfeng (通讯)

    fuzhou univ

查看全部 5 位作者收起作者
  • Y

    Yang, Lin (通讯)

    fuzhou univ

  • C

    Chen, C. L. Philip

  • Y

    Yao, Zhiliang

    fuzhou univ

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