发表机构
School of IT, Deakin University（迪肯大学信息技术学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对量子联邦学习中异构客户端数据和噪声导致的问题，提出基于深度展开局部优化的DUQFL-Prox框架，客户端执行自适应更新，近端项和轻量级控制器协同作用，实验证明该框架提升了稳定性、泛化能力及客户端公平性，支持更可靠公平的智能服务。
AI 中文摘要
量子联邦学习使分布式客户端能够在不共享本地数据的情况下训练量子神经网络，对注重隐私的智能服务很有前景。此类智能服务指隐私敏感的分布式决策系统，如欺诈检测和基因组分类，可靠公平的客户端级学习与聚合模型准确性同样重要。但异构客户端数据和噪声量子优化常导致不稳定的本地更新、客户端漂移及客户端间不公平性能。本文提出DUQFL-Prox，一种基于深度展开局部优化的漂移稳定量子联邦学习框架。每个客户端执行自适应展开的SPSA更新，近端项使本地模型接近全局模型，轻量级控制器学习特定步骤的优化参数以提高聚合后性能。在金融欺诈和基因组分类任务上的实验表明，与标准QFL基线相比，DUQFL-Prox提高了稳定性、泛化能力和客户端公平性。结果表明深度展开量子联邦学习可在异构分布式环境中支持更可靠公平的智能服务。
英文摘要
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.
