Quantum evolution kernel : Machine learning on graphs with programmable arrays of qubits

TL;DR

This paper introduces a quantum-based method for measuring graph similarity using quantum evolution, demonstrating its effectiveness on benchmarks and exploring implementation on neutral-atom quantum processors.

Contribution

It presents a novel quantum evolution kernel for graph data, linking quantum dynamics to classical graph kernels and showing practical implementation prospects.

Findings

Performs well compared to classical graph kernels on benchmarks

Provides a quantum approach to graph similarity measurement

Analyzes potential implementation on neutral-atom quantum processors

Abstract

The rapid development of reliable Quantum Processing Units (QPU) opens up novel computational opportunities for machine learning. Here, we introduce a procedure for measuring the similarity between graph-structured data, based on the time-evolution of a quantum system. By encoding the topology of the input graph in the Hamiltonian of the system, the evolution produces measurement samples that retain key features of the data. We study analytically the procedure and illustrate its versatility in providing links to standard classical approaches. We then show numerically that this scheme performs well compared to standard graph kernels on typical benchmark datasets. Finally, we study the possibility of a concrete implementation on a realistic neutral-atom quantum processor.