Training quantum machine learning models on cloud without uploading the data

TL;DR

This paper introduces a method for training quantum machine learning models on cloud platforms without data upload, leveraging quantum linearity to enhance data security and reduce encoding complexity.

Contribution

It proposes a novel approach that allows dataset owners to train models without exposing data, significantly reducing circuit depth and easing gate precision requirements.

Findings

Enables training without data upload to quantum cloud platforms

Reduces circuit depth from exponential to linear in data size

Maintains model functionality on classical computers

Abstract

Based on the linearity of quantum unitary operations, we propose a method that runs the parameterized quantum circuits before encoding the input data. This enables a dataset owner to train machine learning models on quantum cloud computation platforms, without the risk of leaking the information about the data. It is also capable of encoding a vast amount of data effectively at a later time using classical computations, thus saving runtime on quantum computation devices. The trained quantum machine learning models can be run completely on classical computers, meaning the dataset owner does not need to have any quantum hardware, nor even quantum simulators. Moreover, our method mitigates the encoding bottleneck by reducing the required circuit depth from $O(2^{n})$ to $O(n)$, and relax the tolerance on the precision of the quantum gates for the encoding. These results demonstrate yet another advantage of quantum and quantum-inspired machine learning models over existing classical neural networks, and broaden the approaches to data security.