Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2605.25783

Q-RAIL: A Reliability-Aware Framework for Quantum Federated Learning on Heterogeneous Noisy Hardware

Walid El Maouaki, Muhammad Shafique

On Aqora:Muhammad ShafiqueMuhammad Shafique
quant-phSubmitted May 25, 2026• Announced May 26, 2026• 0 citations
v1 · May 25, 2026v2 · Oct 3, 2026
arXivHTMLPDF

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 papers

Q-ANCHOR: Federated Quantum Learning with ZNE-guided Correction

Hoang M. Ngo, Quan Nguyen, Wanli Xing +1 more

Quantum Federated Learning (QFL) offers a promising framework to train quantum models across distributed clients while keeping data strictly local. Due to its simplicity and low communication overhead, Federated Averaging (FedAvg) is the standard aggregation choice in QFL literature. However, deploying QFL on practical hardware exposes a severe double-drift phenomenon: the global model is simultaneously derailed by client drift from non-IID data and hardware bias from noisy quantum gradient estimates. In this work, we first analyze the convergence of FedAvg under these realistic conditions, mathematically demonstrating that quantum hardware bias creates a persistent error floor that standard averaging cannot correct. To overcome this limitation, we propose Q-ANCHOR, a quantum-aware federated aggregation architecture that anchors server updates with zero-noise extrapolation while applying stateful client correction to suppress both client drift and hardware-induced bias. Our convergence theory proves that Q-ANCHOR successfully mitigates classical client drift while actively reducing the hardware-bias floor. Experimental results demonstrate that Q-ANCHOR achieves significantly more stable training than conventional FL baselines.

arXiv:2605.30075•May 28, 2026•0 citations

A Stable Aggregation Method for Quantum Federated Learning

Shanika Iroshi Nanayakkara, Shiva Raj Pokhrel

Abstract—Quantum federated learning (QFL) enables clients to train quantum neural network (QNN) models without sharing private data. We find that aggregation in QFL is unstable under heterogeneous data, unreliable communication, variable fidelity, latency, and quantum hardware noise. Moreover, QFL is non-trivial to address because several QNN parameters are periodic angles, and Euclidean averaging often fails to capture the inherent dynamics. We develop a novel self-consistent midpoint aggregation method for the stable design and implementation of QFLs. We combine QoS-aware client weighting, circular parameter aggregation, and bounded midpoint-based update control. We perform several angular tests and experiments on IBM's real Quantum machines for validation, confirming our approach. Extensive evaluations and experiments on medical and financial datasets show improved stability, lower volatility, and competitive accuracy. Index Terms—Quantum federated learning, adaptive aggregation, geometry-aware aggregation, self-consistent midpoint, quality of service, angular aggregation, quantum neural networks.

arXiv:2609.00356•Jun 25, 2026•0 citations

RobQFL: Robust Quantum Federated Learning in Adversarial Environment

Walid El Maouaki, Nouhaila Innan, Alberto Marchisio +3 more

Quantum Federated Learning (QFL) merges privacypreserving federation with quantum computing gains, yet its resilience to adversarial noise is unknown. We first show that QFL is as fragile as centralized quantum learning. We propose Robust Quantum Federated Learning (RobQFL), embedding adversarial training directly into the federated loop. RobQFL exposes tunable axes: client coverage$\gamma$(0 100 %), perturbation scheduling (fixed-$\varepsilon$vs$\varepsilon$-mixes), and optimization (fine-tune vs scratch), and distils the resulting$\gamma \times \varepsilon$surface into two metrics: Accuracy-Robustness Area and Robustness Volume. On 15client simulations with MNIST and Fashion-MNIST, IID and Non-IID conditions, training only$\mathbf{2 0} \boldsymbol{-} \mathbf{5 0 \%}$clients adversarially boosts$\varepsilon \leq 0.1$accuracy$\sim \mathbf{1 5} \mathbf{~ p p}$at$<2 \mathbf{~ p p}$clean-accuracy cost; fine-tuning adds$\mathbf{3 - 5}$pp. With$\geq 75 \%$coverage, a moderate$\varepsilon$-mix is optimal, while high-$\varepsilon$schedules help only at 100 % coverage. Label-sorted non-IID splits halve robustness, underscoring data heterogeneity as a dominant risk.

arXiv:2509.04914•IEEE International Conference on Quantum Artificial Intelligence (QAI)•Nov 2, 2025•4 citations

Entanglement Aware Federated Quantum Learning in NISQ Era Edge Systems

Suresh Kumar Jha, Ashok Kumar Pasi, Muddada Murali Krishna +1 more

The convergence of quantum computing and distributed edge intelligence presents new possibilities for advancing federated learning in NISQ-era settings. Conventional federated learning, however, becomes increasingly vulnerable to decoherence, communication noise, and heterogeneous client data when extended to quantum-enabled systems. This work proposes an Entanglement-Aware Federated Quantum Learning (EAFQL) framework that couples local variational quantum circuit (VQC) training with a fidelity-weighted aggregation rule at the server. The use of entanglement fidelity as a weighting factor allows the aggregation process to compensate for noise-induced degradation in the client-server links. A corresponding theoretical model is developed, and the framework is implemented in a hybrid simulation environment using Qiskit and PennyLane. Experimental results show that EAFQL attains accuracy comparable to classical FedAvg while offering improved stability. The method remains effective under non-IID data distributions, synthetic depolarizing and amplitude-damping noise, and varying entanglement-distribution topologies. These findings indicate that fidelity-aware aggregation can enhance the reliability of federated learning in emerging quantum-classical edge networks.

IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI)•Mar 12, 2026•0 citations

Kernel-Weighted Aggregation for Hyperparameter-Free Quantum Federated Learning

Rui Huang

Quantum federated learning (QFL) enables collaborative training of variational quantum circuits across decentralized clients, but client drift under non-IID data distributions degrades standard Federated Averaging (FedAvg). Existing aggregation methods either introduce tunable hyperparameters that depend on unknown data heterogeneity or incur structural costs such as order-dependent error propagation. We propose Kernel-Weighted Aggregation (KWA), a hyperparameter-free aggregation strategy that constructs a non-parametric kernel density estimate over the received client parameter vectors at each communication round. Clients in high-density regions receive greater voting power, and isolated clients are automatically attenuated. The kernel bandwidth is the median of all pairwise squared distances. We evaluate KWA against six state-of-the-art QFL methods and five classical robust baselines on five binary MNIST digit-pair tasks under IID, Dir(0.5), and Dir(0.1) distributions with a unified four-qubit benchmark. Under IID data, KWA recovers the performance of FedAvg. Under Dir(0.5), KWA attains the highest average accuracy (0.7120), followed by FedAvg (0.7093). The margin at N=4 clients is not statistically significant. It grows to +0.023 at N=16 in the client scaling experiment. Under this distribution, the five classical robust baselines also rank below FedAvg. Under Dir(0.1), KWA exceeds FedAvg by 0.028 on average, with a pooled paired t-test p=0.068. Larger-circuit and three-class experiments show that the advantage does not yet transfer consistently beyond the four-qubit binary setting. KWA thus provides a hyperparameter-free aggregation strategy that recovers FedAvg under IID conditions, adapts to client drift, and requires no manually tuned hyperparameters.

Entropy•Aug 26, 2026•0 citations

A Drift-Stable Quantum Federated Learning for Intelligent Services

Shanika Iroshi Nanayakkara, Shiva Raj Pokhrel

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 oftencause 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 aproximal 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 fairnesscompared 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.

•Jul 14, 2026•0 citations
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.
Quantum Federated Learning (QFL) offers a promising framework to train quantum models across distributed clients while keeping data strictly local. Due to its simplicity and low communication overhead, Federated Averaging (FedAvg) is the standard aggregation choice in QFL literature. However, deploying QFL on practical hardware exposes a severe double-drift phenomenon: the global model is simultaneously derailed by client drift from non-IID data and hardware bias from noisy quantum gradient estimates. In this work, we first analyze the convergence of FedAvg under these realistic conditions, mathematically demonstrating that quantum hardware bias creates a persistent error floor that standard averaging cannot correct. To overcome this limitation, we propose Q-ANCHOR, a quantum-aware federated aggregation architecture that anchors server updates with zero-noise extrapolation while applying stateful client correction to suppress both client drift and hardware-induced bias. Our convergence theory proves that Q-ANCHOR successfully mitigates classical client drift while actively reducing the hardware-bias floor. Experimental results demonstrate that Q-ANCHOR achieves significantly more stable training than conventional FL baselines.
Abstract—Quantum federated learning (QFL) enables clients to train quantum neural network (QNN) models without sharing private data. We find that aggregation in QFL is unstable under heterogeneous data, unreliable communication, variable fidelity, latency, and quantum hardware noise. Moreover, QFL is non-trivial to address because several QNN parameters are periodic angles, and Euclidean averaging often fails to capture the inherent dynamics. We develop a novel self-consistent midpoint aggregation method for the stable design and implementation of QFLs. We combine QoS-aware client weighting, circular parameter aggregation, and bounded midpoint-based update control. We perform several angular tests and experiments on IBM's real Quantum machines for validation, confirming our approach. Extensive evaluations and experiments on medical and financial datasets show improved stability, lower volatility, and competitive accuracy. Index Terms—Quantum federated learning, adaptive aggregation, geometry-aware aggregation, self-consistent midpoint, quality of service, angular aggregation, quantum neural networks.
Quantum Federated Learning (QFL) merges privacypreserving federation with quantum computing gains, yet its resilience to adversarial noise is unknown. We first show that QFL is as fragile as centralized quantum learning. We propose Robust Quantum Federated Learning (RobQFL), embedding adversarial training directly into the federated loop. RobQFL exposes tunable axes: client coverageγ\gammaγ(0 100 %), perturbation scheduling (fixed-ε\varepsilonεvsε\varepsilonε-mixes), and optimization (fine-tune vs scratch), and distils the resultingγ×ε\gamma \times \varepsilonγ×εsurface into two metrics: Accuracy-Robustness Area and Robustness Volume. On 15client simulations with MNIST and Fashion-MNIST, IID and Non-IID conditions, training only20−50%\mathbf{2 0} \boldsymbol{-} \mathbf{5 0 \%}20−50%clients adversarially boostsε≤0.1\varepsilon \leq 0.1ε≤0.1accuracy∼15 pp\sim \mathbf{1 5} \mathbf{~ p p}∼15 ppat<2 pp<2 \mathbf{~ p p}<2 ppclean-accuracy cost; fine-tuning adds3−5\mathbf{3 - 5}3−5pp. With≥75%\geq 75 \%≥75%coverage, a moderateε\varepsilonε-mix is optimal, while high-ε\varepsilonεschedules help only at 100 % coverage. Label-sorted non-IID splits halve robustness, underscoring data heterogeneity as a dominant risk.
The convergence of quantum computing and distributed edge intelligence presents new possibilities for advancing federated learning in NISQ-era settings. Conventional federated learning, however, becomes increasingly vulnerable to decoherence, communication noise, and heterogeneous client data when extended to quantum-enabled systems. This work proposes an Entanglement-Aware Federated Quantum Learning (EAFQL) framework that couples local variational quantum circuit (VQC) training with a fidelity-weighted aggregation rule at the server. The use of entanglement fidelity as a weighting factor allows the aggregation process to compensate for noise-induced degradation in the client-server links. A corresponding theoretical model is developed, and the framework is implemented in a hybrid simulation environment using Qiskit and PennyLane. Experimental results show that EAFQL attains accuracy comparable to classical FedAvg while offering improved stability. The method remains effective under non-IID data distributions, synthetic depolarizing and amplitude-damping noise, and varying entanglement-distribution topologies. These findings indicate that fidelity-aware aggregation can enhance the reliability of federated learning in emerging quantum-classical edge networks.
Quantum federated learning (QFL) enables collaborative training of variational quantum circuits across decentralized clients, but client drift under non-IID data distributions degrades standard Federated Averaging (FedAvg). Existing aggregation methods either introduce tunable hyperparameters that depend on unknown data heterogeneity or incur structural costs such as order-dependent error propagation. We propose Kernel-Weighted Aggregation (KWA), a hyperparameter-free aggregation strategy that constructs a non-parametric kernel density estimate over the received client parameter vectors at each communication round. Clients in high-density regions receive greater voting power, and isolated clients are automatically attenuated. The kernel bandwidth is the median of all pairwise squared distances. We evaluate KWA against six state-of-the-art QFL methods and five classical robust baselines on five binary MNIST digit-pair tasks under IID, Dir(0.5), and Dir(0.1) distributions with a unified four-qubit benchmark. Under IID data, KWA recovers the performance of FedAvg. Under Dir(0.5), KWA attains the highest average accuracy (0.7120), followed by FedAvg (0.7093). The margin at N=4 clients is not statistically significant. It grows to +0.023 at N=16 in the client scaling experiment. Under this distribution, the five classical robust baselines also rank below FedAvg. Under Dir(0.1), KWA exceeds FedAvg by 0.028 on average, with a pooled paired t-test p=0.068. Larger-circuit and three-class experiments show that the advantage does not yet transfer consistently beyond the four-qubit binary setting. KWA thus provides a hyperparameter-free aggregation strategy that recovers FedAvg under IID conditions, adapts to client drift, and requires no manually tuned hyperparameters.
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 oftencause 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 aproximal 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 fairnesscompared 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.