Diffusion induced graph representation learning

doi:10.1016/j.neucom.2019.06.012

	Diffusion induced graph representation learning
	Li, Fuzhen 1,2; Zhu, Zhenfeng 1,2; Zhang, Xingxing 1,2; Cheng, Jian3 ; Zhao, Yao 1,2
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
	2019-09-30
卷号	360 页码:220-229
通讯作者	Zhu, Zhenfeng(zhfzhu@bjtu.edu.cn)
摘要	Nowadays, graph representation learning has aroused a lot of research interest, which aims to learn the latent low-dimensional representations of graph nodes, while preserving the graph structure. Based on the local smooth assumption, some existing methods have achieved significant success. However, although the structure information of data has been taken into consideration, these models fail to capture enough connectivity pattern such as high-order connections. To alleviate this issue, we propose a Graph Diffusion Network (GDN) that can dynamically preserve local and global consistency of graph. More specifically, Graph Diffusion Auto-encoder is utilized as the main framework in GDN to nonlinearly maintain global information volume. Different from simple auto-encoders, the forward propagation in our model is conducted through Graph Diffusion System which can guide the random walk of information flow to sense the high-order local relationships on graph. Furthermore, to discover a customized graph structure that reveals the similarities between nodes, the connection relationship between nodes are refined by learned metrics with the preservation of scale-free property. By the dynamically self-refining on the graph structure, it can be promoted towards learning the intrinsic node representations in a progressive way. Experimental results on node classification tasks demonstrate the effectiveness of the proposed GDN model. (C) 2019 Elsevier B.V. All rights reserved.
关键词	Graph representation learning Graph embedding Diffusion model Auto-encoder Deep learning
DOI	10.1016/j.neucom.2019.06.012
关键词[WOS]	DIMENSIONALITY ; DISTRIBUTIONS
收录类别	SCI
语种	英语
资助项目	National Key Research and Development of China[2016YFB0800404] ; National Natural Science Foundation of China[61572068] ; National Natural Science Foundation of China[61532005] ; National Key Research and Development of China[2016YFB0800404] ; National Natural Science Foundation of China[61572068] ; National Natural Science Foundation of China[61532005]
项目资助者	National Key Research and Development of China ; National Natural Science Foundation of China
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000480412700020
出版者	ELSEVIER
引用统计	被引频次：3[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/27611
专题	复杂系统认知与决策实验室_高效智能计算与学习
通讯作者	Zhu, Zhenfeng
作者单位	1.Beijing Jiaotong Univ, Inst Informat Sci, Beijing 100044, Peoples R China 2.Beijing Key Lab Adv Informat Sci & Network Techno, Beijing 100044, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Li, Fuzhen,Zhu, Zhenfeng,Zhang, Xingxing,et al. Diffusion induced graph representation learning[J]. NEUROCOMPUTING,2019,360:220-229.
APA	Li, Fuzhen,Zhu, Zhenfeng,Zhang, Xingxing,Cheng, Jian,&Zhao, Yao.(2019).Diffusion induced graph representation learning.NEUROCOMPUTING,360,220-229.
MLA	Li, Fuzhen,et al."Diffusion induced graph representation learning".NEUROCOMPUTING 360(2019):220-229.