Dynamic Graph Learning Convolutional Networks for Semi-supervised Classification

doi:10.1145/3412846

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 多媒体计算与图形学团队

	Dynamic Graph Learning Convolutional Networks for Semi-supervised Classification
	Fu, Sichao 4; Liu, Weifeng 4; Guan, Weili 1; Zhou, Yicong 3; Tao, Dapeng 2; Xu, Changsheng 5
刊名	ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
	2021-04-01
卷号	17 期号:1 页码:13
关键词	Graph representation learning graph convolutional networks semisupervised classification
ISSN号	1551-6857
DOI	10.1145/3412846
通讯作者	Liu, Weifeng(liuwf@upc.edu.cn)
英文摘要	Over the past few years, graph representation learning (GRL) has received widespread attention on the feature representations of the non-Euclidean data. As a typical model of GRL, graph convolutional networks (GCN) fuse the graph Laplacian-based static sample structural information. GCN thus generalizes convolutional neural networks to acquire the sample representations with the variously high-order structures. However, most of existing GCN-based variants depend on the static data structural relationships. It will result in the extracted data features lacking of representativeness during the convolution process. To solve this problem, dynamic graph learning convolutional networks (DGLCN) on the application of semi-supervised classification are proposed. First, we introduce a definition of dynamic spectral graph convolution operation. It constantly optimizes the high-order structural relationships between data points according to the loss values of the loss function, and then fits the local geometry information of data exactly. After optimizing our proposed definition with the one-order Chebyshev polynomial, we can obtain a single-layer convolution rule of DGLCN. Due to the fusion of the optimized structural information in the learning process, multi-layer DGLCN can extract richer sample features to improve classification performance. Substantial experiments are conducted on citation network datasets to prove the effectiveness of DGLCN. Experiment results demonstrate that the proposed DGLCN obtains a superior classification performance compared to several existing semi-supervised classification models.
资助项目	Major Scientific and Technological Projects of CNPC[ZD2019-183008] ; Open Project Program of the National Laboratory of Pattern Recognition (NLPR)[202000009] ; Science and Technology Development Fund, Macau SAR[189/2017/A3]
WOS研究方向	Computer Science
语种	英语
出版者	ASSOC COMPUTING MACHINERY
WOS记录号	WOS:000646396900004
资助机构	Major Scientific and Technological Projects of CNPC ; Open Project Program of the National Laboratory of Pattern Recognition (NLPR) ; Science and Technology Development Fund, Macau SAR
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/44663]
专题	自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
通讯作者	Liu, Weifeng
作者单位	1.Monash Univ, Fac Informat Technol, Clayton Campus, Melbourne, Vic, Australia 2.Yunnan Univ, Sch Informat Sci & Engn, Kunming 650091, Yunnan, Peoples R China 3.Univ Macau, Fac Sci & Technol, Macau 999078, Peoples R China 4.China Univ Petr East China, Coll Control Sci & Engn, Qingdao 266580, Peoples R China 5.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Fu, Sichao,Liu, Weifeng,Guan, Weili,et al. Dynamic Graph Learning Convolutional Networks for Semi-supervised Classification[J]. ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,2021,17(1):13.
APA	Fu, Sichao,Liu, Weifeng,Guan, Weili,Zhou, Yicong,Tao, Dapeng,&Xu, Changsheng.(2021).Dynamic Graph Learning Convolutional Networks for Semi-supervised Classification.ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,17(1),13.
MLA	Fu, Sichao,et al."Dynamic Graph Learning Convolutional Networks for Semi-supervised Classification".ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 17.1(2021):13.