Federated Quantum-Train with Batched Parameter Generation

TL;DR

This paper presents a federated quantum training framework that reduces qubit requirements and overfitting in distributed quantum machine learning, without needing quantum hardware during inference.

Contribution

It introduces a novel federated quantum training method with batched parameter generation, significantly lowering qubit usage and improving model generalization.

Findings

Reduces qubit usage from 19 to 8 in quantum models

Mitigates overfitting in quantum federated learning

Improves accuracy in highly compressed models

Abstract

In this work, we introduce the Federated Quantum-Train (QT) framework, which integrates the QT model into federated learning to leverage quantum computing for distributed learning systems. Quantum client nodes employ Quantum Neural Networks (QNNs) and a mapping model to generate local target model parameters, which are updated and aggregated at a central node. Testing with a VGG-like convolutional neural network on the CIFAR-10 dataset, our approach significantly reduces qubit usage from 19 to as low as 8 qubits while reducing generalization error. The QT method mitigates overfitting observed in classical models, aligning training and testing accuracy and improving performance in highly compressed models. Notably, the Federated QT framework does not require a quantum computer during inference, enhancing practicality given current quantum hardware limitations. This work highlights the potential of integrating quantum techniques into federated learning, paving the way for advancements in quantum machine learning and distributed learning systems.