Sporadic Federated Learning Approach in Quantum Environment to Tackle Quantum Noise

TL;DR

This paper introduces SpoQFL, a sporadic federated learning framework in quantum environments that dynamically adapts to quantum noise heterogeneity, significantly improving training robustness and convergence stability.

Contribution

The paper presents a novel sporadic federated learning approach for quantum systems that effectively mitigates quantum noise heterogeneity, enhancing model performance and stability.

Findings

SpoQFL outperforms traditional QFL in training accuracy.

It achieves more stable convergence under quantum noise.

The approach improves robustness in real-world quantum datasets.

Abstract

Quantum Federated Learning (QFL) is an emerging paradigm that combines quantum computing and federated learning (FL) to enable decentralized model training while maintaining data privacy over quantum networks. However, quantum noise remains a significant barrier in QFL, since modern quantum devices experience heterogeneous noise levels due to variances in hardware quality and sensitivity to quantum decoherence, resulting in inadequate training performance. To address this issue, we propose SpoQFL, a novel QFL framework that leverages sporadic learning to mitigate quantum noise heterogeneity in distributed quantum systems. SpoQFL dynamically adjusts training strategies based on noise fluctuations, enhancing model robustness, convergence stability, and overall learning efficiency. Extensive experiments on real-world datasets demonstrate that SpoQFL significantly outperforms conventional QFL approaches, achieving superior training performance and more stable convergence.