Variational Quantum Kernels with Task-Specific Quantum Metric Learning

TL;DR

This paper introduces a method for creating task-specific quantum embeddings using variational quantum kernels and quantum metric learning, enhancing quantum machine learning performance and demonstrating potential quantum advantage.

Contribution

It proposes a novel approach to optimize quantum embeddings tailored to specific machine learning tasks, improving quantum kernel methods and transfer learning capabilities.

Findings

Quantum embeddings can be optimized for specific tasks.

Task-specific embeddings support feature selection.

Quantum advantage demonstrated with classically-intractable embeddings.

Abstract

Quantum kernel methods, i.e., kernel methods with quantum kernels, offer distinct advantages as a hybrid quantum-classical approach to quantum machine learning (QML), including applicability to Noisy Intermediate-Scale Quantum (NISQ) devices and usage for solving all types of machine learning problems. Kernel methods rely on the notion of similarity between points in a higher (possibly infinite) dimensional feature space. For machine learning, the notion of similarity assumes that points close in the feature space should be close in the machine learning task space. In this paper, we discuss the use of variational quantum kernels with task-specific quantum metric learning to generate optimal quantum embeddings (a.k.a. quantum feature encodings) that are specific to machine learning tasks. Such task-specific optimal quantum embeddings, implicitly supporting feature selection, are valuable not only to quantum kernel methods in improving the latter's performance, but they can also be valuable to non-kernel QML methods based on parameterized quantum circuits (PQCs) as pretrained embeddings and for transfer learning. This further demonstrates the quantum utility, and quantum advantage (with classically-intractable quantum embeddings), of quantum kernel methods.