A Multi-Class SWAP-Test Classifier
arXiv:2302.02994 · doi:10.1002/qute.202300249
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.
arXiv comment13 pages, 9 figures
References in corpus (8)
- Supervised learning with quantum enhanced feature spaces
- Quantum support vector machine for big data classification
- Quantum machine learning in feature Hilbert spaces
- Data re-uploading for a universal quantum classifier
- IBM Q Experience as a versatile experimental testbed for simulating open quantum systems
- Multiclass classification using quantum convolutional neural networks with hybrid quantum-classical learning
- The theory of the quantum kernel-based binary classifier
- Robust quantum classifier with minimal overhead