Quantum Federated Learning (QFL) extends Federated Learning (FL) by training Variational Quantum Circuits (VQCs) across distributed clients. However, its scalability is hindered by two critical bottlenecks: the communication overhead of synchronizing parameter sets and the trainability degradation caused by hardware noise on Noisy Intermediate-Scale Quantum (NISQ) devices. We propose FedQ-Sparse, a framework that incorporates magnitude-based unstructured pruning into the QFL workflow. Rather than claiming a quantum advantage over classical models, FedQ-Sparse utilizes pruning as an active noise mitigation strategy. By physically removing near-identity rotation gates, the framework reduces effective circuit depth and limits exposure to depolarizing noise. Experimental results on MNIST, FashionMNIST, and Pneumonia indicate that FedQ-Sparse achieves up to a 1.71× compression ratio while exposing noise-dependent regimes where sparse models systematically outperform dense baselines under high noise.
Quantum Federated Learning (QFL) extends Federated Learning (FL) by training Variational Quantum Circuits (VQCs) across distributed clients. However, its scalability is hindered by two critical bottlenecks: the communication overhead of synchronizing parameter sets and the trainability degradation caused by hardware noise on Noisy Intermediate-Scale Quantum (NISQ) devices. We propose FedQ-Sparse, a framework that incorporates magnitude-based unstructured pruning into the QFL workflow. Rather than claiming a quantum advantage over classical models, FedQ-Sparse utilizes pruning as an active noise mitigation strategy. By physically removing near-identity rotation gates, the framework reduces effective circuit depth and limits exposure to depolarizing noise. Experimental results on MNIST, FashionMNIST, and Pneumonia indicate that FedQ-Sparse achieves up to a 1.71× compression ratio while exposing noise-dependent regimes where sparse models systematically outperform dense baselines under high noise.
Advanced Driver Assistance Systems (ADAS) increasingly employ Federated Learning (FL) to collaboratively train models across distributed vehicular nodes while preserving data privacy. Yet, conventional FL aggregation remains susceptible to noise, latency, and security constraints inherent to real-time vehicular networks. This paper introduces Noise-Resilient Quantum Federated Learning (NR-QFL), a hybrid quantum-classical framework that enables secure, low-latency aggregation through variational quantum circuits (VQCs) operating under Noisy Intermediate-Scale Quantum (NISQ) conditions. The framework encodes model parameters as quantum states with adaptive gate reparameterization, ensuring bounded-error convergence and provable resilience under Completely Positive Trace-Preserving (CPTP) dynamics. NR-QFL employs quantum entropy-based client selection and multi-server coordination for fairness and stability. Empirical validation shows consistent convergence with reduced gradient variance, lower communication overhead, and enhanced noise tolerance under constrained edge conditions. The framework establishes a scalable foundation for quantum-enhanced federated learning, enabling secure, efficient, and dynamically stable ADAS intelligence at the vehicular edge
AI-driven medical diagnostics increasingly requires collaborative model training across institutions, yet centralizing patient data conflicts with privacy regulations. Federated Learning enables distributed training without raw data sharing, but remains vulnerable to gradient inversion and model leakage attacks. Furthermore, harvest-now-decrypt-later attacks render computationally secure protocols insufficient for protecting long-lived medical records. Quantum communication offers information-theoretic security immune to such threats, making Quantum Federated Learning (QFL) a compelling framework for healthcare. However, practical deployment is constrained by communication overhead and quantum channel noise. We present a systematic quantitative study of communication, convergence, and noise trade-offs in QFL, introducing two complementary strategies to reduce quantum transmissions: (1) structured parameter reduction via light-cone feature selection in parameterized quantum circuits, and (2) a Hybrid QFL architecture that dynamically switches between centralized and decentralized aggregation. We show that Hybrid QFL reduces total quantum transmissions from 3TNMP, the cost of pure Centralized QFL, to {3t+2(T−t)}NMP over T rounds while preserving near-centralized convergence. We further demonstrate that decentralized aggregation is more noise-resilient under depolarizing noise, and evaluate Steane code-based quantum error correction in high-noise regimes. Our results provide an integrated design framework for communication-efficient, noise-aware QFL, clarifying practical trade-offs for scalable quantum-secure distributed learning in healthcare.
With the rapid development of quantum computing and federated learning, achieving efficient distributed model training while ensuring data privacy has become a significant challenge. Quantum Federated Learning (QFL) aims to leverage quantum computing to enhance training efficiency while preserving data privacy in federated learning. However, existing methods typically rely on real data, require multiple communication rounds, and depend on client-side quantum capabilities, which limits their practical application in the noisy intermediate-scale quantum (NISQ) era. To address these challenges, we propose a One-Shot Data-Free Quantum Federated Learning (OD-QFL) framework. In this approach, clients train lightweight classical models locally and upload them in a single round. Subsequently, the server leverages these uploaded models to synthesize a global quantum student model via data-free pseudo-data generation and knowledge distillation, thereby enabling collaborative training without accessing real client data. Experimental results on MNIST, FMNIST, and NotMNIST demonstrate that OD-QFL achieves stable and competitive performance while significantly reducing communication overhead, validating its effectiveness under realistic NISQ constraints.
ABSTRACT Background Quantum federated learning presents a promising paradigm for privacy‐preserving collaborative training across distributed quantum devices. However, its scalability is hindered by the significant communication overhead associated with transmitting high‐dimensional, high‐precision quantum model parameters over classical networks. Methods To address this bottleneck, this paper proposes QFI‐Opt (Quantum Fisher Information‐guided Adaptive Optimization), a quantum adaptive communication optimization framework based on Quantum Fisher Information. QFI‐Opt establishes a “sensing‐compression‐regulation” pipeline that achieves communication efficiency while preserving quantum model fidelity. The framework uses QFI as a physically interpretable metric to dynamically assess quantum state sensitivity to parameter perturbations, enabling a progressive pruning strategy that removes low‐sensitivity parameters during training while retaining critical quantum features. Additionally, a dynamic bit‐width quantization mechanism adapts precision based on parameter importance, maximizing compression without compromising numerical stability. This is further complemented by a physics‐aware aggregation method that weighs client updates based on both local data volume and quantum information quality derived from QFI scores, improving global model robustness. Results Extensive evaluation on quantum convolutional neural networks demonstrates that QFI‐Opt significantly reduces per‐round communication overhead compared to baseline methods. Conclusions Simultaneously, the proposed framework maintains competitive model accuracy and convergence performance across diverse quantum architectures.
Training federated learning (FL) at scale suffers from severe communication and heterogeneity constraints. These challenges are amplified in quantum federated learning (QFL), especially under non-IID data. We propose a model-driven QFL (mdQFL) framework that addresses communication overhead, scalability, and client drift through adaptive clustering and representative aggregation. The framework enables structured personalization and efficient update compression across rounds. mdQFL is the first QFL approach to jointly analyze training efficiency, personalization, and test generalization under heterogeneous conditions. Experiments across multiple datasets and quantum platforms show 50% communication reduction while maintaining or improving accuracy over standard QFL base-lines. We provide convergence guarantees and communication complexity bounds to establish scalability and robustness.
Quantum Federated Learning (QFL) is an emerging field that harnesses advances in Quantum Computing (QC) to improve the scalability and efficiency of decentralized Federated Learning (FL) models. This paper provides a systematic and comprehensive survey of the emerging problems and solutions when FL meets QC, from research protocol to a novel taxonomy, particularly focusing on both quantum and federated limitations, such as their architectures, Noisy Intermediate Scale Quantum (NISQ) devices, and privacy preservation, so on. With the introduction of two novel metrics, qubit utilization efficiency and quantum model training strategy, we present a thorough analysis of the current status of the QFL research. This work explores key developments and integration strategies, along with the impact of QC on FL, keeping a sharp focus on hybrid quantum-classical approaches. The paper offers an in-depth understanding of how the strengths of QC, such as gradient hiding, state entanglement, quantum key distribution, quantum security, and quantum-enhanced differential privacy, have been integrated into FL to ensure the privacy of participants in an enhanced, fast, and secure framework. Finally, this study proposes potential future directions to address the identified research gaps and challenges, aiming to inspire faster and more secure QFL models for practical use.