中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 人工智能与机器学习
PKGCN: prior knowledge enhanced graph convolutional network for graph-based semi-supervised learning

文献类型：期刊论文

作者Yu, Shaowei1,2; Yang, Xuebing2; Zhang, Wensheng2
刊名INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
出版日期2019-11-01
卷号10期号:11页码:3115-3127
关键词Graph convolutional network Semi-supervised learning Prior knowledge Node classification
ISSN号1868-8071
DOI10.1007/s13042-019-01003-7
通讯作者Yu, Shaowei(yushaowei2017@ia.ac.cn)
英文摘要Graph is a widely existed data structure in many real world scenarios, such as social networks, citation networks and knowledge graphs. Recently, Graph Convolutional Network (GCN) has been proposed as a powerful method for graph-based semi-supervised learning, which has the similar operation and structure as Convolutional Neural Networks (CNNs). However, like many CNNs, it is often necessary to go through a lot of laborious experiments to determine the appropriate network structure and parameter settings. Fully exploiting and utilizing the prior knowledge that nearby nodes have the same labels in graph-based neural network is still a challenge. In this paper, we propose a model which utilizes the prior knowledge on graph to enhance GCN. To be specific, we decompose the objective function of semi-supervised learning on graphs into a supervised term and an unsupervised term. For the unsupervised term, we present the concept of local inconsistency and devise a loss term to describe the property in graphs. The supervised term captures the information from the labeled data while the proposed unsupervised term captures the relationships among both labeled data and unlabeled data. Combining supervised term and unsupervised term, our proposed model includes more intrinsic properties of graph-structured data and improves the GCN model with no increase in time complexity. Experiments on three node classification benchmarks show that our proposed model is superior to GCN and seven existing graph-based semi-supervised learning methods.
WOS关键词PERFORMANCE
资助项目National Natural Science Foundation of China[U1636220] ; National Natural Science Foundation of China[61532006] ; Beijing Municipal Natural Science Foundation[4172063]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000494802500009
出版者SPRINGER HEIDELBERG
资助机构National Natural Science Foundation of China ; Beijing Municipal Natural Science Foundation
源URL[http://ir.ia.ac.cn/handle/173211/28866]  
专题精密感知与控制研究中心_人工智能与机器学习
通讯作者Yu, Shaowei
作者单位1.Univ Chinese Acad Sci, Beijing, Peoples R China
2.Chinese Acad Sci, Inst Automat, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Yu, Shaowei,Yang, Xuebing,Zhang, Wensheng. PKGCN: prior knowledge enhanced graph convolutional network for graph-based semi-supervised learning[J]. INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS,2019,10(11):3115-3127.
APA Yu, Shaowei,Yang, Xuebing,&Zhang, Wensheng.(2019).PKGCN: prior knowledge enhanced graph convolutional network for graph-based semi-supervised learning.INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS,10(11),3115-3127.
MLA Yu, Shaowei,et al."PKGCN: prior knowledge enhanced graph convolutional network for graph-based semi-supervised learning".INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 10.11(2019):3115-3127.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。