A Multi-Class SWAP-Test Classifier

TL;DR

This paper introduces the first multi-class SWAP-Test quantum classifier that reduces model complexity and resource requirements, demonstrating effectiveness and noise robustness through analytical and simulation results.

Contribution

It presents a novel multi-class quantum classifier based on the SWAP-Test that requires fewer qubits and maintains invariance to the number of classes, unlike previous models.

Findings

Effective across diverse classification problems

Invariant resource requirements regardless of class number

Robust performance under certain noise conditions

Abstract

Multi-class classification problems are fundamental in many varied domains in research and industry. To solve multi-class classification problems, heuristic strategies such as One-vs-One or One-vs-All can be employed. However, these strategies require the number of binary classification models developed to grow with the number of classes. Recent work in quantum machine learning has seen the development of multi-class quantum classifiers that circumvent this growth by learning a mapping between the data and a set of label states. This work presents the first multi-class SWAP-Test classifier inspired by its binary predecessor and the use of label states in recent work. With this classifier, the cost of developing multiple models is avoided. In contrast to previous work, the number of qubits required, the measurement strategy, and the topology of the circuits used is invariant to the number of classes. In addition, unlike other architectures for multi-class quantum classifiers, the state reconstruction of a single qubit yields sufficient information for multi-class classification tasks. Both analytical results and numerical simulations show that this classifier is not only effective when applied to diverse classification problems but also robust to certain conditions of noise.