A Drift Stable Quantum Federated Learning for Intelligent Services

2026-07-21

AI Summary

This work addresses the challenges of unstable local updates, client drift, and performance unfairness in quantum federated learning, which are exacerbated by heterogeneous client data and optimization noise inherent to quantum systems. To mitigate these issues, we propose DUQFL-Prox, a novel framework that introduces deep-unfolded optimization into quantum federated learning for the first time. Our approach integrates adaptive SPSA-based local updates, a proximal regularization term, and a lightweight controller that dynamically adjusts the step size. This design effectively suppresses client drift and enhances the stability of model aggregation, generalization capability, and fairness across clients. Empirical evaluations on financial fraud detection and genomic classification tasks demonstrate that DUQFL-Prox significantly outperforms existing quantum federated learning baselines.

Abstract

Quantum federated learning enables distributed clients to train quantum neural networks without sharing local data, making it promising for privacy-aware intelligent services. Intelligent services in this context refer to privacy-sensitive distributed decision systems, such as fraud detection and genomic classification, where reliable and fair client-level learning is as important as the accuracy of the aggregate model. However, heterogeneous client data and noisy quantum optimization often cause unstable local updates, client drift, and unfair performance between clients. This paper proposes DUQFL-Prox, a drift-stable quantum federated learning framework based on deep-unfolded local optimization. Instead of using a fixed local optimizer, each client performs adaptive unfolded SPSA updates, while a proximal term keeps the local model close to the global model. A lightweight controller learns step-specific optimization parameters to improve post-aggregation performance. Experiments on financial fraud and genomic classification tasks show that DUQFL-Prox improves stability, generalization, and client fairness compared with standard QFL baselines. The results suggest that deep-unfolded quantum federated learning can support more reliable and fair intelligent services in heterogeneous distributed environments.

Problem

• quantum federated learning
• client drift
• heterogeneous data
• unfair performance
• noisy quantum optimization

Innovation

• Quantum Federated Learning
• Client Drift Mitigation
• Deep-Unfolded Optimization
• Proximal Regularization
• Adaptive SPSA