Location-aware convolutional neural networks for graph classification

doi:10.1016/j.neunet.2022.07.035

	Location-aware convolutional neural networks for graph classification
	Wang, Zhaohui 1,3; Cao, Qi 1; Shen, Huawei 1,3,4; Xu, Bingbing 1; Cen, Keting 1,3; Cheng, Xueqi 2,3
	2022-11-01
发表期刊	NEURAL NETWORKS
ISSN	0893-6080
卷号	155 页码:74-83
摘要	Graph patterns play a critical role in various graph classification tasks, e.g., chemical patterns often determine the properties of molecular graphs. Researchers devote themselves to adapting Convolutional Neural Networks (CNNs) to graph classification due to their powerful capability in pattern learning. The varying numbers of neighbor nodes and the lack of canonical order of nodes on graphs pose challenges in constructing receptive fields for CNNs. Existing methods generally follow a heuristic ranking-based framework, which constructs receptive fields by selecting a fixed number of nodes and dropping the others according to predetermined rules. However, such methods may lose important structure information through dropping nodes, and they also cannot learn task-oriented graph patterns. In this paper, we propose a Location learning-based Convolutional Neural Networks (LCNN) for graph classification. LCNN constructs receptive fields by learning the location of each node according to its embedding that contains structures and features information, then standard CNNs are applied to capture graph patterns. Such a location learning mechanism not only retains the information of all nodes, but also provides the ability for task-oriented pattern learning. Experimental results show the effectiveness of the proposed LCNN, and visualization results further illustrate the valid pattern learning ability of our method for graph classification. (c) 2022 Elsevier Ltd. All rights reserved.
关键词	Graph classification Convolutional neural networks Location-aware
DOI	10.1016/j.neunet.2022.07.035
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[U21B2046] ; National Natural Science Foundation of China[62102402] ; National Key R&D Program of China[2020AAA0105200]
WOS研究方向	Computer Science ; Neurosciences & Neurology
WOS类目	Computer Science, Artificial Intelligence ; Neurosciences
WOS记录号	WOS:000884681600005
出版者	PERGAMON-ELSEVIER SCIENCE LTD
引用统计	被引频次：6[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/19861
专题	中国科学院计算技术研究所期刊论文
通讯作者	Shen, Huawei
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Data Intelligence Syst Res Ctr, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, CAS Key Lab Network Data Sci & Technol, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Beijing, Peoples R China 4.Beijing Acad Artificial Intelligence, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Wang, Zhaohui,Cao, Qi,Shen, Huawei,et al. Location-aware convolutional neural networks for graph classification[J]. NEURAL NETWORKS,2022,155:74-83.
APA	Wang, Zhaohui,Cao, Qi,Shen, Huawei,Xu, Bingbing,Cen, Keting,&Cheng, Xueqi.(2022).Location-aware convolutional neural networks for graph classification.NEURAL NETWORKS,155,74-83.
MLA	Wang, Zhaohui,et al."Location-aware convolutional neural networks for graph classification".NEURAL NETWORKS 155(2022):74-83.