Practical application of quantum neural network to materials informatics: prediction of the melting points of metal oxides

TL;DR

This paper demonstrates that quantum neural networks can effectively predict melting points of metal oxides in materials informatics, outperforming classical models and showing no overfitting with proper design.

Contribution

It presents the first practical application of QNN to a multivariate regression task in materials informatics, exploring architectures and encoding methods for optimal performance.

Findings

QNN models outperform classical neural networks in melting point prediction.

Shallow-depth ansatzs with entangled circuits are sufficient for expressibility.

Proper encoder design prevents overfitting in QNN models.

Abstract

Quantum neural network (QNN) models have received increasing attention owing to their strong expressibility and resistance to overfitting. It is particularly useful when the size of the training data is small, making it a good fit for materials informatics (MI) problems. However, there are only a few examples of the application of QNN to multivariate regression models, and little is known about how these models are constructed. This study aims to construct a QNN model to predict the melting points of metal oxides as an example of a multivariate regression task for the MI problem. Different architectures (encoding methods and entangler arrangements) are explored to create an effective QNN model. Shallow-depth ansatzs could achieve sufficient expressibility using sufficiently entangled circuits. The "linear" entangler was adequate for providing the necessary entanglement. The expressibility of the QNN model could be further improved by increasing the circuit width. The generalization performance could also be improved, outperforming the classical NN model. No overfitting was observed in the QNN models with a well-designed encoder. These findings suggest that QNN can be a useful tool for MI.