TY - GEN
T1 - Learning Graph Convolutional Networks based on Quantum Vertex Information Propagation (Extended Abstract)
AU - Bai, Lu
AU - Jiao, Yuhang
AU - Cui, Lixin
AU - Rossi, Luca
AU - Wang, Yue
AU - Yu, Philip S.
AU - Hancock, Edwin R.
N1 - Funding Information:
Corresponding Author: Lixin Cui ([email protected]). This work is supported by the National Natural Science Foundation of China (Grant no. T2122020, 61976235, and 61602535).
Publisher Copyright:
© 2022 IEEE.
PY - 2022/5
Y1 - 2022/5
N2 - This paper proposes a novel Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes. The main idea is to define a new quantum-inspired spatial graph convolution associated with pre-transformed fixed-sized aligned grid structures of graphs, in terms of quantum information propagation between grid vertices of each graph. We show that the proposed QSGCNN model can significantly reduce either the information loss or the notorious tottering problem arising in existing spatially-based Graph Convolutional Network (GCN) models. Experiments on benchmark graph datasets demonstrate the effectiveness of the proposed QSGCNN model.
AB - This paper proposes a novel Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes. The main idea is to define a new quantum-inspired spatial graph convolution associated with pre-transformed fixed-sized aligned grid structures of graphs, in terms of quantum information propagation between grid vertices of each graph. We show that the proposed QSGCNN model can significantly reduce either the information loss or the notorious tottering problem arising in existing spatially-based Graph Convolutional Network (GCN) models. Experiments on benchmark graph datasets demonstrate the effectiveness of the proposed QSGCNN model.
UR - http://www.scopus.com/inward/record.url?scp=85136355108&partnerID=8YFLogxK
U2 - 10.1109/ICDE53745.2022.00280
DO - 10.1109/ICDE53745.2022.00280
M3 - Conference article published in proceeding or book
AN - SCOPUS:85136355108
T3 - Proceedings - International Conference on Data Engineering
SP - 3132
EP - 3133
BT - Proceedings - 2022 IEEE 38th International Conference on Data Engineering, ICDE 2022
PB - IEEE Computer Society
T2 - 38th IEEE International Conference on Data Engineering, ICDE 2022
Y2 - 9 May 2022 through 12 May 2022
ER -