Quantum-based subgraph convolutional neural networks

Zhihong Zhang, Dongdong Chen, Jianjia Wang, Lu Bai*, Edwin R. Hancock

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

47 Citations (Scopus)


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.

Original languageEnglish
Pages (from-to)38-49
Number of pages12
JournalPattern Recognition
Publication statusPublished - Apr 2019
Externally publishedYes


  • Graph convolutional neural networks
  • Quantum walks
  • Spatial construction
  • Subgraph


Dive into the research topics of 'Quantum-based subgraph convolutional neural networks'. Together they form a unique fingerprint.

Cite this