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:2512.03363

A2G-QFL: Adaptive Aggregation with Two Gains in Quantum Federated learning

Shanika Iroshi Nanayakkara, Shiva Raj Pokhrel

cs.LGquant-phSubmitted Dec 3, 2025• Announced Dec 4, 2025• 0 citations
v1 · Dec 3, 2025v2 · Feb 18, 2026
arXivHTMLPDF

Abstract

Federated learning (FL) deployed over quantum enabled and heterogeneous classical networks faces significant performance degradation due to uneven client quality, stochastic teleportation fidelity, device instability, and geometric mismatch between local and global models. Classical aggregation rules assume euclidean topology and uniform communication reliability, limiting their suitability for emerging quantum federated systems. This paper introduces A2G (Adaptive Aggregation with Two Gains), a dual gain framework that jointly regulates geometric blending through a geometry gain and modulates client importance using a QoS gain derived from teleportation fidelity, latency, and instability. We develop the A2G update rule, establish convergence guarantees under smoothness and bounded variance assumptions, and show that A2G recovers FedAvg, QoS aware averaging, and manifold based aggregation as special cases. Experiments on a quantum classical hybrid testbed demonstrate improved stability and higher accuracy under heterogeneous and noisy conditions.

Comments
8 pages, 4 figures, QCNC 2026

Related papers

A2G-QFL: Adaptive Aggregation with Two Gains in Quantum Federated Learning

Shanika Iroshi Nanayakkara, Shiva Raj Pokhrel

Federated learning (FL) deployed over quantumenabled and heterogeneous classical networks can degrade under uneven client quality, modeled teleportation/link fidelity, and communication instability, while standard aggregation rules assume Euclidean topology and uniform reliability, limiting their suitability for emerging quantum federated systems. We introduce A2G (Adaptive Aggregation with Two Gains). This dualgain framework jointly regulates server-side relaxation through a geometry gain. It modulates client importance using a QoS gain derived from teleportation/link fidelity, latency, and instability (variance of the QoS signal). The proposed A2G update rule shows that A2G recovers baseline approaches such as FedAvg, Latency-only, QoS-aware averaging, and manifold-inspired aggregation as special cases. Experiments on a Qiskit Aer-based quantum-classical simulation testbed demonstrate improved stability and accuracy under heterogeneous, realistic, and simulated quantum-noisy conditions.

International Conference on Quantum Communications, Networking, and Computing (QCNC)•Apr 6, 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

Quantum Federated Aggregation using Joint Fidelity-and-Entropy Computation

Seok Bin Son, Soohyun Park

Quantum federated learning (QFL) incorporates the principles of quantum neural networks (QNN) over federated learning (FL). It updates quantum parameters to the server. However, QFL aggregation involves quantum parameters from all local QNN models, leading to performance degradation due to outlier models. Thus, a novel fair QFL algorithm is proposed to enhance learning performance by eliminating outliers using Lyapunov optimization at the QFL server. This approach is used to take care of the trade-off between accuracy and latency, where the accuracy is associated with the freshness of aggregation. Moreover, a fidelity/entropy-adaptive algorithm is proposed, which relies on the degree control to select outliers. This approach (i) quantifies the dissimilarity in quantum states between the target model and each local device using fidelity, and (ii) evaluates the imbalance of data classes in each local device using entropy. Experimental results demonstrate that the proposed fair QFL algorithm outperforms benchmarks.

IEEE International Conference on Distributed Computing Systems Workshops (ICDCSW)•Jul 21, 2025•0 citations

Toward Uniform Quantum Federated Aggregation: Heterogeneity Exclusion Using Entropy and Fidelity

Seok Bin Son, Soohyun Park

Quantum federated learning (QFL) incorporates the principles of quantum neural networks (QNNs) and federated learning (FL), ensuring privacy by updating quantum parameters to the server. However, server aggregation in general QFL involves quantum parameters from all local models, leading to performance degradation due to the participation of outlier heterogeneous local models. Inspired by this, a novel QFL algorithm is proposed to enhance learning performance by excluding outliers before aggregation using Lyapunov optimization at QFL server. This Lyapunov optimization is used to take care of the tradeoff between accuracy and latency, where the accuracy is associated with the freshness of aggregation. Additionally, an entropy-and-fidelity aware algorithm is proposed, which relies on the degree control to select outliers for exclusion comprehensively. This algorithm addresses data and quantum aspects by evaluating the imbalance of data classes in each local model using entropy and quantifying the dissimilarity in quantum states between the target model and each local model through fidelity. Experimental results demonstrate that the proposed algorithm outperforms benchmarks, effectively excluding heterogeneous local models to improve performance while ensuring stability.

IEEE Internet of Things Journal•Oct 30, 2024•8 citations

Fidelity-Aware Angular Aggregation for Quantum Federated Learning over Noisy Entanglement

Shanika Iroshi Nanayakkara, Shiva Raj Pokhrel

We propose $\text{FAAA}-\beta$ (Fidelity-Aware Angular Aggregation), a novel teleportation-conditioned aggregation framework for quantum learning (QFL) that incorporates quantum channel quality metrics into the model update process; $\beta$ is a tunable blending parameter. $\text{FAAA}-\beta$ harnesses variational parameters as angular coordinates on a torus and performs fidelity-weighted circular consensus with parameterized linear blending. Our method computes trust weights based on measured fidelity $F_{i}$, latency $\tau_{i}$, and instability $\sigma_{i}^{2}$, establishing a crosslayer coupling between the physical-layer teleportation quality and the model-layer aggregation. Experimental evaluation using SamplerQNN on binary classification tasks under synthetically degraded Bell-pair fidelities demonstrates that $\text{FAAA}-\beta$ achieves competitive accuracy with significantly reduced variance and enhanced stability.

International Conference on Information Networking•Jan 14, 2026•1 citation

Communication-Efficient Adaptive Model-Driven Quantum Federated Learning

Dev Gurung, Shiva Raj Pokhrel

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.

arXiv:2506.04548•IEEE Transactions on Networking•Jan 1, 2026•3 citations
Federated learning (FL) deployed over quantum enabled and heterogeneous classical networks faces significant performance degradation due to uneven client quality, stochastic teleportation fidelity, device instability, and geometric mismatch between local and global models. Classical aggregation rules assume euclidean topology and uniform communication reliability, limiting their suitability for emerging quantum federated systems. This paper introduces A2G (Adaptive Aggregation with Two Gains), a dual gain framework that jointly regulates geometric blending through a geometry gain and modulates client importance using a QoS gain derived from teleportation fidelity, latency, and instability. We develop the A2G update rule, establish convergence guarantees under smoothness and bounded variance assumptions, and show that A2G recovers FedAvg, QoS aware averaging, and manifold based aggregation as special cases. Experiments on a quantum classical hybrid testbed demonstrate improved stability and higher accuracy under heterogeneous and noisy conditions.
Federated learning (FL) deployed over quantumenabled and heterogeneous classical networks can degrade under uneven client quality, modeled teleportation/link fidelity, and communication instability, while standard aggregation rules assume Euclidean topology and uniform reliability, limiting their suitability for emerging quantum federated systems. We introduce A2G (Adaptive Aggregation with Two Gains). This dualgain framework jointly regulates server-side relaxation through a geometry gain. It modulates client importance using a QoS gain derived from teleportation/link fidelity, latency, and instability (variance of the QoS signal). The proposed A2G update rule shows that A2G recovers baseline approaches such as FedAvg, Latency-only, QoS-aware averaging, and manifold-inspired aggregation as special cases. Experiments on a Qiskit Aer-based quantum-classical simulation testbed demonstrate improved stability and accuracy under heterogeneous, realistic, and simulated quantum-noisy conditions.
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) incorporates the principles of quantum neural networks (QNN) over federated learning (FL). It updates quantum parameters to the server. However, QFL aggregation involves quantum parameters from all local QNN models, leading to performance degradation due to outlier models. Thus, a novel fair QFL algorithm is proposed to enhance learning performance by eliminating outliers using Lyapunov optimization at the QFL server. This approach is used to take care of the trade-off between accuracy and latency, where the accuracy is associated with the freshness of aggregation. Moreover, a fidelity/entropy-adaptive algorithm is proposed, which relies on the degree control to select outliers. This approach (i) quantifies the dissimilarity in quantum states between the target model and each local device using fidelity, and (ii) evaluates the imbalance of data classes in each local device using entropy. Experimental results demonstrate that the proposed fair QFL algorithm outperforms benchmarks.
Quantum federated learning (QFL) incorporates the principles of quantum neural networks (QNNs) and federated learning (FL), ensuring privacy by updating quantum parameters to the server. However, server aggregation in general QFL involves quantum parameters from all local models, leading to performance degradation due to the participation of outlier heterogeneous local models. Inspired by this, a novel QFL algorithm is proposed to enhance learning performance by excluding outliers before aggregation using Lyapunov optimization at QFL server. This Lyapunov optimization is used to take care of the tradeoff between accuracy and latency, where the accuracy is associated with the freshness of aggregation. Additionally, an entropy-and-fidelity aware algorithm is proposed, which relies on the degree control to select outliers for exclusion comprehensively. This algorithm addresses data and quantum aspects by evaluating the imbalance of data classes in each local model using entropy and quantifying the dissimilarity in quantum states between the target model and each local model through fidelity. Experimental results demonstrate that the proposed algorithm outperforms benchmarks, effectively excluding heterogeneous local models to improve performance while ensuring stability.
We propose FAAA−β\text{FAAA}-\betaFAAA−β (Fidelity-Aware Angular Aggregation), a novel teleportation-conditioned aggregation framework for quantum learning (QFL) that incorporates quantum channel quality metrics into the model update process; β\betaβ is a tunable blending parameter. FAAA−β\text{FAAA}-\betaFAAA−β harnesses variational parameters as angular coordinates on a torus and performs fidelity-weighted circular consensus with parameterized linear blending. Our method computes trust weights based on measured fidelity FiF_{i}Fi​, latency τi\tau_{i}τi​, and instability σi2\sigma_{i}^{2}σi2​, establishing a crosslayer coupling between the physical-layer teleportation quality and the model-layer aggregation. Experimental evaluation using SamplerQNN on binary classification tasks under synthetically degraded Bell-pair fidelities demonstrates that FAAA−β\text{FAAA}-\betaFAAA−β achieves competitive accuracy with significantly reduced variance and enhanced stability.
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.