Learning Graph Convolutional Networks based on Quantum Vertex Information Propagation

Bai，Lu1; Jiao，Yuhang2; Cui，Lixin3; Rossi，Luca4; Wang，Yue5; Yu，Philip6; Hancock，Edwin7

2021

10.1109/TKDE.2021.3106804

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING   影响因子和分区

1041-4347

1558-2191

This paper proposes a new Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes. Unlike state-of-the-art Graph Convolutional Neural Network (GCNN) models, the proposed QSGCNN model incorporates the process of identifying transitive aligned vertices between graphs and transforms arbitrary sized graphs into fixed-sized aligned vertex grid structures. In order to learn representative graph characteristics, a new quantum spatial graph convolution is proposed and employed to extract multi-scale vertex features, in terms of quantum information propagation between grid vertices of each graph. Since the quantum spatial convolution preserves the grid structures of the input vertices (i.e., the convolution layer does not change the original spatial sequence of vertices), the proposed QSGCNN model allows to directly employ the traditional convolutional neural network architecture to further learn from the global graph topology, providing an end-to-end deep learning architecture that integrates the graph representation and learning in the quantum spatial graph convolution layer and the traditional convolutional layer for graph classifications. We demonstrate the effectiveness of the proposed QSGCNN model in relation to existing state-of-the-art methods. Experiments on benchmark graph classification datasets demonstrate the effectiveness of the proposed QSGCNN model.

Convolution Convolutional neural networks Data mining Feature extraction Graph Neural Networks Kernel Periodic structures Quantum Graph Convolution Quantum Propagation Quantum Walks Standards

EI

英语

其他

20213710887467

Backpropagation ; Classification (of information) ; Convolution ; Convolutional neural networks ; Deep learning ; Information dissemination ; Multilayer neural networks ; Network architecture

Information Theory and Signal Processing:716.1 ; Artificial Intelligence:723.4 ; Information Dissemination:903.2 ; Combinatorial Mathematics, Includes Graph Theory, Set Theory:921.4

ENGINEERING

2-s2.0-85114650652

Scopus

1.School of Information, Central University of Finance and Economics, 12647 Beijing, Beijing, China, 100081 (e-mail: bailucs@cufe.edu.cn)
2.School of Information, Central University of Finance and Economics, 12647 Beijing, Beijing, China, (e-mail: jiaoyuhang@email.cufe.edu.cn)
3.School of Information, Central University of Finance and Economics, 12647 Beijing, Beijing, China, (e-mail: cuilixin@cufe.edu.cn)
4.Department of Computer Science, Southern University of Science and Technology, 255310 Shenzhen, Guangdong, China, (e-mail: rossil@sustech.edu.cn)
5.Department of Computer Science, Central University of Finance and Economics, 12647 Beijing, Beijing, China, (e-mail: wangyuecs@cufe.edu.cn)
6.Computer Science, UIC, Chicago, Illinois, United States, 60607 (e-mail: psyu@uic.edu)
7.computer science department, the university of York, York, York, United Kingdom of Great Britain and Northern Ireland, (e-mail: edwin.hancock@york.ac.uk)

Bai，Lu,Jiao，Yuhang,Cui，Lixin,et al. Learning Graph Convolutional Networks based on Quantum Vertex Information Propagation[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,2021,PP(99):1-1.

Bai，Lu.,Jiao，Yuhang.,Cui，Lixin.,Rossi，Luca.,Wang，Yue.,...&Hancock，Edwin.(2021).Learning Graph Convolutional Networks based on Quantum Vertex Information Propagation.IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,PP(99),1-1.

Bai，Lu,et al."Learning Graph Convolutional Networks based on Quantum Vertex Information Propagation".IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING PP.99(2021):1-1.