QESK: Quantum-based Entropic Subtree Kernels for Graph Classification

TL;DR

This paper introduces QESK, a quantum-inspired graph kernel that leverages entropic subtree representations and quantum walks to improve graph classification accuracy over existing methods.

Contribution

The paper presents a novel quantum-based entropic subtree kernel (QESK) that captures complex graph structures and addresses limitations of traditional graph kernels.

Findings

QESK outperforms state-of-the-art graph kernels in classification tasks.

QESK effectively captures quantum structural characteristics of graphs.

The method theoretically discriminates isomorphic subtrees in global graph contexts.

Abstract

In this paper, we propose a novel graph kernel, namely the Quantum-based Entropic Subtree Kernel (QESK), for Graph Classification. To this end, we commence by computing the Average Mixing Matrix (AMM) of the Continuous-time Quantum Walk (CTQW) evolved on each graph structure. Moreover, we show how this AMM matrix can be employed to compute a series of entropic subtree representations associated with the classical Weisfeiler-Lehman (WL) algorithm. For a pair of graphs, the QESK kernel is defined by computing the exponentiation of the negative Euclidean distance between their entropic subtree representations, theoretically resulting in a positive definite graph kernel. We show that the proposed QESK kernel not only encapsulates complicated intrinsic quantum-based structural characteristics of graph structures through the CTQW, but also theoretically addresses the shortcoming of ignoring the effects of unshared substructures arising in state-of-the-art R-convolution graph kernels. Moreover, unlike the classical R-convolution kernels, the proposed QESK can discriminate the distinctions of isomorphic subtrees in terms of the global graph structures, theoretically explaining the effectiveness. Experiments indicate that the proposed QESK kernel can significantly outperform state-of-the-art graph kernels and graph deep learning methods for graph classification problems.