英文论文
-
文献类型
-
Journal article (JA)
-
题名
-
Quantum-based subgraph convolutional neural networks
-
作者
-
Zhang, Zhihong (1); Chen, Dongdong (1); Wang, Jianjia (3); Bai, Lu (2); Hancock, Edwin R. (3)
-
作者单位
-
(1) Xiamen University, Xiamen, China (2) Central University of Finance and Economics, Beijing, China (3) University of York, York, United Kingdom
-
通讯作者地址
-
Cent Univ Finance & Econ, Beijing, Peoples R China.
-
Email
-
-
ResearchID
-
-
ORCID
-
-
期刊名称
-
Pattern Recognition
-
出版社
-
Elsevier Ltd
-
ISSN
-
0031-3203
-
出版信息
-
2019-04, 88:38-49.
-
JCR
-
2
-
影响因子
-
7.196
-
ISBN
-
-
基金
-
National Natural Science Foundation of China [61402389, 61503422, 11401499]; Natural Science Foundation of Fujian Province [2015J05016]; Fundamental Research Funds for the Central Universities in China [20720160073]
-
会议名称
-
-
会议地点
-
-
会议开始日期
-
-
会议结束日期
-
-
关键词
-
Classification (of information); Convolution; Graphic methods; Network architecture; Neural networks
-
摘要
-
This paper proposes a new graph convolutional neural network architecture based on a depth-based representation of graph structure deriving from quantum walks, which we refer to as the quantum-based subgraph convolutional neural network (QS-CNNs). This new architecture captures both the global topological structure and the local connectivity structure within a graph. Specifically, we commence by establishing a family of K-layer expansion subgraphs for each vertex of a graph by quantum walks, which captures the global topological arrangement information for substructures contained within a graph. We then design a set of fixed-size convolution filters over the subgraphs, which helps to characterise multi-scale patterns residing in the data. The idea is to apply convolution filters sliding over the entire set of subgraphs rooted at a vertex to extract the local features analogous to the standard convolution operation on grid data. Experiments on eight graph-structured datasets demonstrate that QS-CNNs architecture is capable of outperforming fourteen state-of-the-art methods for the tasks of node classification and graph classification. ? 2018 Elsevier Ltd
-
一级学科
-
Computer Science, Artificial Intelligence; Engineering, Electrical & Electronic
-
WOS入藏号
-
WOS:000457666900004
-
EI收录号
-
20184606067353
-
DOI
-
10.1016/j.patcog.2018.11.002
-
ESI
-
ENGINEERING
-
收录于
-
SCIE, EI
-
返回