Federated Quantum Machine Learning

TL;DR

This paper introduces federated training for hybrid quantum-classical machine learning models, showing it can achieve comparable accuracy with faster training, thus enhancing scalability and privacy in quantum machine learning.

Contribution

It presents the first federated learning framework for hybrid quantum-classical models, demonstrating improved training speed without sacrificing accuracy.

Findings

Federated quantum-classical training achieves similar accuracy to centralized training.

Distributed training significantly reduces training time.

Framework can be extended to pure quantum models.

Abstract

Distributed training across several quantum computers could significantly improve the training time and if we could share the learned model, not the data, it could potentially improve the data privacy as the training would happen where the data is located. However, to the best of our knowledge, no work has been done in quantum machine learning (QML) in federation setting yet. In this work, we present the federated training on hybrid quantum-classical machine learning models although our framework could be generalized to pure quantum machine learning model. Specifically, we consider the quantum neural network (QNN) coupled with classical pre-trained convolutional model. Our distributed federated learning scheme demonstrated almost the same level of trained model accuracies and yet significantly faster distributed training. It demonstrates a promising future research direction for scaling and privacy aspects.