Open Access

ARTICLE

A Quantum Spatial Graph Convolutional Network for Text Classification

by Syed Mustajar Ahmad Shah¹, Hongwei Ge^1,*, Sami Ahmed Haider², Muhammad Irshad³, Sohail M. Noman⁴, Jehangir Arshad⁵, Asfandeyar Ahmad⁶, Talha Younas⁷

1 College of Computer Science and Technology, Dalian University of Technology, Dalian, 116024, China
2 Department of Computing, University of Worcester, UK
3 Department of Information Engineering, Chang’an University, Xi’an, 710054, China
4 Department of Cell Biology and Genetics, Shantou University Medical College, Shantou, 515041, China
5 Electrical and Computer Engineering Department, COMSATS University Islamabad, Lahore Campus, Pakistan
6 School of Information & Communication Engineering Dalian University of Technology, Dalian, 116024, China
7 Electrical and Computer Engineering Department, COMSATS University Islamabad, Sahiwal Campus, Pakistan

* Corresponding Author: Hongwei Ge. Email:

Computer Systems Science and Engineering 2021, 36(2), 369-382. https://doi.org/10.32604/csse.2021.014234

Received 08 September 2020; Accepted 08 November 2020; Issue published 05 January 2021

Abstract

The data generated from non-Euclidean domains and its graphical representation (with complex-relationship object interdependence) applications has observed an exponential growth. The sophistication of graph data has posed consequential obstacles to the existing machine learning algorithms. In this study, we have considered a revamped version of a semi-supervised learning algorithm for graph-structured data to address the issue of expanding deep learning approaches to represent the graph data. Additionally, the quantum information theory has been applied through Graph Neural Networks (GNNs) to generate Riemannian metrics in closed-form of several graph layers. In further, to pre-process the adjacency matrix of graphs, a new formulation is established to incorporate high order proximities. The proposed scheme has shown outstanding improvements to overcome the deficiencies in Graph Convolutional Network (GCN), particularly, the information loss and imprecise information representation with acceptable computational overhead. Moreover, the proposed Quantum Graph Convolutional Network (QGCN) has significantly strengthened the GCN on semi-supervised node classification tasks. In parallel, it expands the generalization process with a significant difference by making small random perturbations of the graph during the training process. The evaluation results are provided on three benchmark datasets, including Citeseer, Cora, and PubMed, that distinctly delineate the superiority of the proposed model in terms of computational accuracy against state-of-the-art GCN and three other methods based on the same algorithms in the existing literature.

---

Keywords

---

Citations