发表机构
DePaul University(德保罗大学)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
针对客户端数据异质性下量子联邦学习的固定 ansatz 性能缺陷,提出 PAS-QFL 框架,分解 ansatz 为共享与私有部分,通过 Macro-F1 选择私有 ansatz 结构,提升了平均 Macro-F1。
AI 中文摘要
量子联邦学习(QFL)允许多个量子客户端在不共享私有本地数据的情况下协同训练量子神经网络(QNN)。然而,现有 QFL 方法通常假设所有客户端使用相同的 ansatz,忽略了客户端异质性数据对 ansatz 适用性的影响。在类别不平衡的非独立同分布(non-IID)数据场景下,不同客户端可能偏好不同的 ansatz 结构,因此固定 ansatz 会导致客户端之间性能不稳定且不公平。本文提出 PAS-QFL,即客户端数据异质性下量子联邦学习的个性化 ansatz 选择框架。PAS-QFL 不将 ansatz 视为整体结构,而是将每个客户端的 QNN 分解为全局共享 ansatz 和客户端专属私有 ansatz,不仅个性化私有 ansatz 的参数,还个性化其结构。共享 ansatz 置于首位,通过感知稳定性的跨客户端准则进行选择,以确保其参数可可靠聚合;私有 ansatz 作为个性化决策头,由每个客户端通过本地 Macro-F1 选择,以适配共享表示到其本地数据。训练期间,每个客户端在本地更新共享和私有参数,但仅上传共享参数,因此联邦聚合保持明确,同时每个客户端保留自身私有结构。PAS-QFL 采用 Macro-F1 作为主要选择指标,以避免类别不平衡下的误导性准确率。在异质性 QFL 任务上的实验表明,PAS-QFL 相比现有固定 ansatz 的 QFL 基线提升了平均 Macro-F1,证明了个性化 ansatz 结构在实用 QFL 中的价值。
英文摘要
Quantum federated learning (QFL) lets multiple quantum clients collaboratively train quantum neural networks (QNNs) without sharing private local data. However, existing QFL methods commonly assume that all clients use the same ansatz, overlooking how heterogeneous client data affects ansatz suitability. Under class-imbalanced non-IID data, different clients may favor different ansatz structures, so a fixed ansatz can lead to unstable and unfair performance across clients. In this paper, we propose PAS-QFL, a Personalized Ansatz Selection framework for QFL under client data heterogeneity. Rather than treating the ansatz as a monolithic structure, PAS-QFL decomposes each client QNN into a globally shared ansatz and a client-specific private ansatz, and personalizes the structure of the private ansatz rather than only its parameters. The shared ansatz is placed first and selected by a stability-aware cross-client criterion so that its parameters can be reliably aggregated, while the private ansatz serves as a personalized decision head, selected per client by local Macro-F1 to adapt the shared representation to its local data. During training, each client updates both its shared and private parameters locally but uploads only the shared parameters, so federated aggregation stays well-defined while each client keeps its own private structure. PAS-QFL uses Macro-F1 as the primary selection metric to avoid misleading accuracy under class imbalance. Experiments on heterogeneous QFL tasks show that PAS-QFL improves average Macro-F1 over the existing fixed-ansatz QFL baselines, demonstrating the value of personalizing the ansatz structure for practical QFL.