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:2412.02293 · IEEE International Conference on Quantum Artificial Intelligence (QAI)

FL-QDSNNs: Federated Learning with Quantum Dynamic Spiking Neural Networks

Nouhaila Innan, Alberto Marchisio, Muhammad Shafique

Published Nov 2, 2025• 8 citations
arXivHTMLPDF

Abstract

We present Federated Learning-Quantum Dynamic Spiking Neural Networks (FL-QDSNNs), a privacy-preserving framework that maintains high predictive accuracy on non-IID client data. Its key innovation is a dynamic-threshold spiking mechanism that triggers quantum gates only when local data drift requires added expressiveness, limiting circuit depth and countering the accuracy loss typical of heterogeneous clients. Evaluated on different benchmark datasets, including Iris, where FL-QDSNNs reach 94% accuracy, the approach consistently surpasses state-of-the-art quantum-federated baselines; scaling analyses demonstrate that performance remains high as the federation expands to 25 clients, confirming both computational efficiency and collaboration robustness. By uniting adaptive quantum expressiveness with strict data locality, FL-QDSNNs enable regulation-compliant quantum learning for privacy-sensitive sectors and critical infrastructure.

DOI
10.1109/qai63978.2025.00025

Related papers

Toward Sustainable Edge Intelligence: Quantum-Inspired Spiking Neural Networks-Aided Federated Learning Approach

Quan Thanh Dao, Wei Yang Bryan Lim, B. D. E. McNiven +4 more

With the rapid expansion of edge devices, federated learning (FL) has emerged as a critical paradigm for enabling collaborative intelligence while preserving data privacy. However, deploying deep learning models on resource-constrained edge hardware remains challenging due to high computational and energy demands. To address this, we propose a novel quantum-inspired neuromorphic federated learning framework, called FL-quantum leaky integrate-and-fire (FL-QLIF). At the core of our approach is an enhanced QLIF neuron model that utilizes quantum rotation gates to simulate synaptic integration and membrane potential leakage simultaneously, offering a mathematically robust and computationally efficient alternative to traditional activation functions. We rigorously validate the framework through extensive experiments, demonstrating that its convergence behavior closely aligns with theoretical predictions regarding learning rates and local update steps. Extensive experiments on MNIST, KMNIST, and FashionMNIST datasets demonstrate that FL-QLIF achieves test accuracy comparable to classical artificial neural networks (ANNs) while significantly outperforming standard variational quantum neural networks (QNNs), particularly in statistically heterogeneous (non-iid) environments. Furthermore, our energy analysis reveals that the proposed framework delivers substantial efficiency gains, reducing energy consumption by$4.4\times$to$10\times$compared to ANN baselines. Finally, we validate the system's scalability, showing robust performance even under low client participation rates (10%), establishing FL-QLIF as a viable solution for sustainable, privacy-preserving edge intelligence.

IEEE Transactions on Network Science and Engineering•Jan 1, 2026•0 citations

Quantum Machine Learning-aided Personalized Federated Learning for Big Data

Nguyen Doan Hieu, Nguyen Xuan Tung, Joon-Ho Kwon +1 more

Federated learning (FL) has emerged as a compelling paradigm for big-data analytics, enabling collaborative training of a global model across distributed mobile or edge devices without centralizing raw data. Yet conventional FL is challenged by model drift under statistical heterogeneity and by the limited computational budgets of client devices, which together hinder convergence and scalability-particularly when the i.i.d. assumption is violated. To address these limitations, we propose a personalized quantum federated learning (QFL) framework that combines quantum machine learning with distributed optimization to deliver client-specific adaptation atop a compact shared representation. Empirically, our method outperforms state-of-the-art baselines on non-IID workloads while reducing computational complexity through a smaller set of trainable parameters.

IEEE International Conference on Big Data and Smart Computing (BigComp)•Feb 2, 2026•0 citations

Federated learning with tensor networks: a quantum AI framework for healthcare

Amandeep Singh Bhatia, David E. Bernal

Abstract The healthcare industry frequently handles sensitive and proprietary data, and due to strict privacy regulations, it is often reluctant to share it directly. In today’s context, Federated Learning (FL) stands out as a crucial remedy, facilitating the rapid advancement of distributed machine learning while effectively managing critical concerns regarding data privacy and governance. The fusion of federated learning and quantum computing represents a groundbreaking interdisciplinary approach with immense potential to revolutionize various industries, from healthcare to finance. In this work, we propose a federated learning framework based on quantum tensor networks (QTNs) that takes advantage of the principles of many-body quantum physics. Currently, there are no known classical tensor networks (TNs) implemented in federated settings. Furthermore, we investigated the effectiveness and feasibility of the proposed framework by conducting a differential privacy analysis to ensure the security of sensitive data across healthcare institutions. Experiments on popular medical image datasets show that the federated quantum tensor network (FedQTNs) model achieved a mean receiver-operator characteristic area under the curve of 91%–98%, outperforming several state-of-the-art federated learning methods. Moreover, QTN models require fewer parameters in FL settings compared to traditional classical models, which often suffer from over-parameterization. This reduction in parameters not only improves the efficiency of the communication process but also significantly decreases data consumption during training. As a result, QTN models facilitate a more effective and resource-efficient approach to training in decentralized environments with limited communication bandwidth. The FedQTN models demonstrate a smaller performance drop even when using strong differential privacy settings, maintaining higher accuracy compared to classical models under similar privacy constraints. Experimental results demonstrate that the quantum federated global model, consisting of highly entangled TN structures, showed better generalization and robustness and achieved higher testing accuracy, surpassing the performance of locally trained clients under unbalanced data distributions among healthcare institutions.

arXiv:2405.07735•Machine Learning Science and Technology•Oct 28, 2024•42 citations

Quantum Federated Learning: Bridging Quantum Computing and Distributed AI

Tariq Qayyum, Manzoor Ahmed Khan, Asadullah Tariq +4 more

In recent years, the growing demand for secure, efficient, and scalable machine learning has highlighted significant challenges in traditional Federated Learning (FL) systems. These challenges include computational inefficiencies in handling large-scale, high-dimensional data, privacy concerns, and the limitations of classical hardware in solving complex optimization problems. Additionally, the increasing complexity of data and the need for more robust privacy-preserving methods have pushed the boundaries of classical FL. To address these issues, this paper presents a detailed framework for Quantum Federated Learning (QFL), where quantum computing and FL converge to enable distributed quantum model training with enhanced privacy preservation. The system is modeled using local quantum models on clients and a global aggregation strategy at the server. We develop quantum gradient-based optimization with quantum cross-entropy loss, privacy preservation through encryption, and robustness to quantum noise. A set of theorems is provided to prove the correctness and efficiency of the model, supported by rigorous mathematical formulations. We used IBM Qiskit for the simulation and compared our proposed QFL with classical FL. The results demonstrate that our QFL outperformed classical FL in terms of accuracy, precision, recall, and F1 score.

IEEE/ACM International Conference on Utility and Cloud Computing (UCC)•Dec 16, 2024•6 citations

Federated quanvolutional neural network: a new paradigm for collaborative quantum learning

Amandeep Singh Bhatia, Sabre Kais, Muhammad Ashraful Alam

Abstract In recent years, the concept of federated machine learning has been actively driven by scientists to ease the privacy concerns of data owners. Currently, the combination of machine learning and quantum computing technologies is a hot industry topic and is positioned to be a major disruptor. It has become an effective new tool for reshaping several industries ranging from healthcare to finance. Data sharing poses a significant hurdle for large-scale machine learning in numerous industries. It is a natural goal to study the advanced quantum computing ecosystem, which will be comprised of heterogeneous federated resources. In this work, the problem of data governance and privacy is handled by developing a quantum federated learning approach, that can be efficiently executed on quantum hardware in the noisy intermediate-scale quantum era. We present the federated hybrid quantum–classical algorithm called a quanvolutional neural network with distributed training on different sites without exchanging data. The hybrid algorithm requires small quantum circuits to produce meaningful features for image classification tasks, which makes it ideal for near-term quantum computing. The primary goal of this work is to evaluate the potential benefits of hybrid quantum–classical and classical-quantum convolutional neural networks on non-independently and non-identically partitioned (Non-IID) and real-world data partitioned datasets among several healthcare institutions/clients. We investigated the performance of a collaborative quanvolutional neural network on two medical machine learning datasets, COVID-19 and MedNIST. Extensive experiments are carried out to validate the robustness and feasibility of the proposed quantum federated learning framework. Our findings demonstrate a decrease of 2%–39% times in necessary communication rounds compared to the federated stochastic gradient descent approach. The hybrid federated framework maintained a high classification testing accuracy and generalizability, even in scenarios where the medical data is unevenly distributed among clients.

Quantum Science and Technology•Sep 22, 2023•43 citations

Enhancing Quantum Federated Learning with Fisher Information-Based Optimization

Amandeep Singh Bhatia, Sabre Kais

Federated Learning (FL) has become increasingly popular across different sectors, offering a way for clients to work together to train a global model without sharing sensitive data. It involves multiple rounds of communication between the global model and participating clients, which introduces several challenges like high communication costs, heterogeneous client data, prolonged processing times, and increased vulnerability to privacy threats. In recent years, the convergence of federated learning and parameterized quantum circuits has sparked significant research interest, with promising implications for fields such as healthcare and finance. By enabling decentralized training of quantum models, it allows clients or institutions to collaboratively enhance model performance and outcomes while preserving data privacy. Recognizing that Fisher information can quantify the amount of information that a quantum state carries under parameter changes, thereby providing insight into its geometric and statistical properties. We intend to leverage this property to address the aforementioned challenges. In this work, we propose a Quantum Federated Learning (QFL) algorithm that makes use of the Fisher information computed on local client models, with data distributed across heterogeneous partitions. This approach identifies the critical parameters that significantly influence the quantum model's performance, ensuring they are preserved during the aggregation process. Our research assessed the effectiveness and feasibility of QFL by comparing its performance against other variants, and exploring the benefits of incorporating Fisher information in QFL settings. Experimental results on ADNI and MNIST datasets demonstrate the effectiveness of our approach in achieving better performance and robustness against the quantum federated averaging method.

arXiv:2507.17580•IEEE International Conference on Quantum Computing and Engineering (QCE)•Aug 30, 2025•3 citations
We present Federated Learning-Quantum Dynamic Spiking Neural Networks (FL-QDSNNs), a privacy-preserving framework that maintains high predictive accuracy on non-IID client data. Its key innovation is a dynamic-threshold spiking mechanism that triggers quantum gates only when local data drift requires added expressiveness, limiting circuit depth and countering the accuracy loss typical of heterogeneous clients. Evaluated on different benchmark datasets, including Iris, where FL-QDSNNs reach 94% accuracy, the approach consistently surpasses state-of-the-art quantum-federated baselines; scaling analyses demonstrate that performance remains high as the federation expands to 25 clients, confirming both computational efficiency and collaboration robustness. By uniting adaptive quantum expressiveness with strict data locality, FL-QDSNNs enable regulation-compliant quantum learning for privacy-sensitive sectors and critical infrastructure.
With the rapid expansion of edge devices, federated learning (FL) has emerged as a critical paradigm for enabling collaborative intelligence while preserving data privacy. However, deploying deep learning models on resource-constrained edge hardware remains challenging due to high computational and energy demands. To address this, we propose a novel quantum-inspired neuromorphic federated learning framework, called FL-quantum leaky integrate-and-fire (FL-QLIF). At the core of our approach is an enhanced QLIF neuron model that utilizes quantum rotation gates to simulate synaptic integration and membrane potential leakage simultaneously, offering a mathematically robust and computationally efficient alternative to traditional activation functions. We rigorously validate the framework through extensive experiments, demonstrating that its convergence behavior closely aligns with theoretical predictions regarding learning rates and local update steps. Extensive experiments on MNIST, KMNIST, and FashionMNIST datasets demonstrate that FL-QLIF achieves test accuracy comparable to classical artificial neural networks (ANNs) while significantly outperforming standard variational quantum neural networks (QNNs), particularly in statistically heterogeneous (non-iid) environments. Furthermore, our energy analysis reveals that the proposed framework delivers substantial efficiency gains, reducing energy consumption by4.4×4.4\times4.4×to10×10\times10×compared to ANN baselines. Finally, we validate the system's scalability, showing robust performance even under low client participation rates (10%), establishing FL-QLIF as a viable solution for sustainable, privacy-preserving edge intelligence.
Federated learning (FL) has emerged as a compelling paradigm for big-data analytics, enabling collaborative training of a global model across distributed mobile or edge devices without centralizing raw data. Yet conventional FL is challenged by model drift under statistical heterogeneity and by the limited computational budgets of client devices, which together hinder convergence and scalability-particularly when the i.i.d. assumption is violated. To address these limitations, we propose a personalized quantum federated learning (QFL) framework that combines quantum machine learning with distributed optimization to deliver client-specific adaptation atop a compact shared representation. Empirically, our method outperforms state-of-the-art baselines on non-IID workloads while reducing computational complexity through a smaller set of trainable parameters.
Abstract The healthcare industry frequently handles sensitive and proprietary data, and due to strict privacy regulations, it is often reluctant to share it directly. In today’s context, Federated Learning (FL) stands out as a crucial remedy, facilitating the rapid advancement of distributed machine learning while effectively managing critical concerns regarding data privacy and governance. The fusion of federated learning and quantum computing represents a groundbreaking interdisciplinary approach with immense potential to revolutionize various industries, from healthcare to finance. In this work, we propose a federated learning framework based on quantum tensor networks (QTNs) that takes advantage of the principles of many-body quantum physics. Currently, there are no known classical tensor networks (TNs) implemented in federated settings. Furthermore, we investigated the effectiveness and feasibility of the proposed framework by conducting a differential privacy analysis to ensure the security of sensitive data across healthcare institutions. Experiments on popular medical image datasets show that the federated quantum tensor network (FedQTNs) model achieved a mean receiver-operator characteristic area under the curve of 91%–98%, outperforming several state-of-the-art federated learning methods. Moreover, QTN models require fewer parameters in FL settings compared to traditional classical models, which often suffer from over-parameterization. This reduction in parameters not only improves the efficiency of the communication process but also significantly decreases data consumption during training. As a result, QTN models facilitate a more effective and resource-efficient approach to training in decentralized environments with limited communication bandwidth. The FedQTN models demonstrate a smaller performance drop even when using strong differential privacy settings, maintaining higher accuracy compared to classical models under similar privacy constraints. Experimental results demonstrate that the quantum federated global model, consisting of highly entangled TN structures, showed better generalization and robustness and achieved higher testing accuracy, surpassing the performance of locally trained clients under unbalanced data distributions among healthcare institutions.
In recent years, the growing demand for secure, efficient, and scalable machine learning has highlighted significant challenges in traditional Federated Learning (FL) systems. These challenges include computational inefficiencies in handling large-scale, high-dimensional data, privacy concerns, and the limitations of classical hardware in solving complex optimization problems. Additionally, the increasing complexity of data and the need for more robust privacy-preserving methods have pushed the boundaries of classical FL. To address these issues, this paper presents a detailed framework for Quantum Federated Learning (QFL), where quantum computing and FL converge to enable distributed quantum model training with enhanced privacy preservation. The system is modeled using local quantum models on clients and a global aggregation strategy at the server. We develop quantum gradient-based optimization with quantum cross-entropy loss, privacy preservation through encryption, and robustness to quantum noise. A set of theorems is provided to prove the correctness and efficiency of the model, supported by rigorous mathematical formulations. We used IBM Qiskit for the simulation and compared our proposed QFL with classical FL. The results demonstrate that our QFL outperformed classical FL in terms of accuracy, precision, recall, and F1 score.
Abstract In recent years, the concept of federated machine learning has been actively driven by scientists to ease the privacy concerns of data owners. Currently, the combination of machine learning and quantum computing technologies is a hot industry topic and is positioned to be a major disruptor. It has become an effective new tool for reshaping several industries ranging from healthcare to finance. Data sharing poses a significant hurdle for large-scale machine learning in numerous industries. It is a natural goal to study the advanced quantum computing ecosystem, which will be comprised of heterogeneous federated resources. In this work, the problem of data governance and privacy is handled by developing a quantum federated learning approach, that can be efficiently executed on quantum hardware in the noisy intermediate-scale quantum era. We present the federated hybrid quantum–classical algorithm called a quanvolutional neural network with distributed training on different sites without exchanging data. The hybrid algorithm requires small quantum circuits to produce meaningful features for image classification tasks, which makes it ideal for near-term quantum computing. The primary goal of this work is to evaluate the potential benefits of hybrid quantum–classical and classical-quantum convolutional neural networks on non-independently and non-identically partitioned (Non-IID) and real-world data partitioned datasets among several healthcare institutions/clients. We investigated the performance of a collaborative quanvolutional neural network on two medical machine learning datasets, COVID-19 and MedNIST. Extensive experiments are carried out to validate the robustness and feasibility of the proposed quantum federated learning framework. Our findings demonstrate a decrease of 2%–39% times in necessary communication rounds compared to the federated stochastic gradient descent approach. The hybrid federated framework maintained a high classification testing accuracy and generalizability, even in scenarios where the medical data is unevenly distributed among clients.
Federated Learning (FL) has become increasingly popular across different sectors, offering a way for clients to work together to train a global model without sharing sensitive data. It involves multiple rounds of communication between the global model and participating clients, which introduces several challenges like high communication costs, heterogeneous client data, prolonged processing times, and increased vulnerability to privacy threats. In recent years, the convergence of federated learning and parameterized quantum circuits has sparked significant research interest, with promising implications for fields such as healthcare and finance. By enabling decentralized training of quantum models, it allows clients or institutions to collaboratively enhance model performance and outcomes while preserving data privacy. Recognizing that Fisher information can quantify the amount of information that a quantum state carries under parameter changes, thereby providing insight into its geometric and statistical properties. We intend to leverage this property to address the aforementioned challenges. In this work, we propose a Quantum Federated Learning (QFL) algorithm that makes use of the Fisher information computed on local client models, with data distributed across heterogeneous partitions. This approach identifies the critical parameters that significantly influence the quantum model's performance, ensuring they are preserved during the aggregation process. Our research assessed the effectiveness and feasibility of QFL by comparing its performance against other variants, and exploring the benefits of incorporating Fisher information in QFL settings. Experimental results on ADNI and MNIST datasets demonstrate the effectiveness of our approach in achieving better performance and robustness against the quantum federated averaging method.