Q-RAIL: A Reliability-Aware Framework for Quantum Federated Learning on Heterogeneous Noisy Hardware
Abstract
Quantum federated learning (QFL) on NISQ hardware is highly sensitive to backend heterogeneity: some clients contribute informative updates, while others contribute noise-dominated drift that uniform averaging cannot distinguish. We propose Q-RAIL (Quantum Reliability-Aware Federated Inference and Learning), a circuit- and calibration-aware aggregation method for hardware-heterogeneous QFL. Q-RAIL computes a client-specific effective noise budget from backend calibration metadata together with transpiled circuit statistics. This budget is converted into stabilized aggregation weights using temperature scaling, uniform mixing, and a minimum-weight floor. Q-RAIL was evaluated across multiple experimental settings, including an ablation study, and benchmarked against state-of-the-art methods on three datasets: MNIST, Fashion-MNIST, and OrganAMNIST. On the primary MNIST benchmark under strong hardware skew, Q-RAIL improves final test accuracy from FedAvg's 0.777 to 0.877, a +10.0-point gain corresponding to about 44.8% relative error reduction, while also exceeding the strongest wpQFL baseline (0.833). At the same time, test loss drops from 0.722 to 0.585, and test AUC rises from 0.920 to 0.973. Under non-IID MNIST, Q-RAIL reaches 0.813 vs 0.722 for FedAvg. It also outperforms FedAvg in 12/12 ansatz/CX-fold stress configurations and remains stronger at 4, 10, and 15 qubit setups. Overall, the results support calibration-driven, circuit-aware aggregation as a practical path toward robust QFL on heterogeneous quantum hardware.
Related
- Quantum Federated Learning Based on Bures--Uhlmann Geometry for Heterogeneous Noisy Clients
- A quantum-assisted latent surrogate model for Bayesian inversion of heterogeneous material properties on NISQ hardware
- Quantum-hardware spectral co-design framework for multifrequency Rydberg electrometry
- Alkaid: A Compiler Framework for Ultra-Low-Latency Kernels on Hardware
- Leveraging Industrial Foundation Models at the Edge of Particle Physics Detectors via Distillation Learning and Hardware Co-design
BibTeX
@misc{maouaki2026qrail,
title = {{Q-RAIL: A Reliability-Aware Framework for Quantum Federated Learning on Heterogeneous Noisy Hardware}},
author = {Walid El Maouaki and Muhammad Shafique},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2605.25783},
eprint = {2605.25783},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.25783},
}
RIS
TY - UNPB
TI - Q-RAIL: A Reliability-Aware Framework for Quantum Federated Learning on Heterogeneous Noisy Hardware
AU - Walid El Maouaki
AU - Muhammad Shafique
PY - 2026
DA - 2026/10/03
PB - arXiv
DO - 10.48550/arxiv.2605.25783
UR - https://arxiv.org/abs/2605.25783
AB - Quantum federated learning (QFL) on NISQ hardware is highly sensitive to backend heterogeneity: some clients contribute informative updates, while others contribute noise-dominated drift that uniform averaging cannot distinguish. We propose Q-RAIL (Quantum Reliability-Aware Federated Inference and Learning), a circuit- and calibration-aware aggregation method for hardware-heterogeneous QFL. Q-RAIL computes a client-specific effective noise budget from backend calibration metadata together with transpiled circuit statistics. This budget is converted into stabilized aggregation weights using temperature scaling, uniform mixing, and a minimum-weight floor. Q-RAIL was evaluated across multiple experimental settings, including an ablation study, and benchmarked against state-of-the-art methods on three datasets: MNIST, Fashion-MNIST, and OrganAMNIST. On the primary MNIST benchmark under strong hardware skew, Q-RAIL improves final test accuracy from FedAvg's 0.777 to 0.877, a +10.0-point gain corresponding to about 44.8% relative error reduction, while also exceeding the strongest wpQFL baseline (0.833). At the same time, test loss drops from 0.722 to 0.585, and test AUC rises from 0.920 to 0.973. Under non-IID MNIST, Q-RAIL reaches 0.813 vs 0.722 for FedAvg. It also outperforms FedAvg in 12/12 ansatz/CX-fold stress configurations and remains stronger at 4, 10, and 15 qubit setups. Overall, the results support calibration-driven, circuit-aware aggregation as a practical path toward robust QFL on heterogeneous quantum hardware.
ER -