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

IEEE Transactions on Network Science and Engineering

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

Quan Thanh Dao, Wei Yang Bryan Lim, B. D. E. McNiven, Berk Canberk, Nguyen‐Son Vo, Hyundong Shin, Trung Q. Duong

Published Jan 1, 2026• 0 citations
Publisher

Abstract

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.

DOI
10.1109/tnse.2026.3742943

Related papers

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

Nouhaila Innan, Alberto Marchisio, Muhammad Shafique

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.

arXiv:2412.02293•IEEE International Conference on Quantum Artificial Intelligence (QAI)•Nov 2, 2025•8 citations

Quantum Integration of Spiking Leaky Integrate-and-Fire Neurons and Variational Circuits for Enhanced Multiclass Classification

Mandeep Kaur Saggi, Amandeep Singh Bhatia, Sabre Kais

Quantum-AI is Ushering in a new scientific revolution, where Quantum Spiking Neural Networks (QSNN) with Quantum Leaky Integrate-and-Fire (QLIF) neurons propel advancements in the modeling of complex biological systems and neural networks. Inspired by the remarkable synergy between quantum mechanics and biological spiking neurons, we present a novel QSNN architecture that leverages QLIF to tackle complex AI tasks. Leveraging entanglement, the quantum variant of SNNs acts as a game-changer, offering faster computation, enhanced accuracy. QLIF Spiking Neurons provide a powerful solution to scalability issues, advancing the potential of AI and quantum technologies in neural networks and complex problem-solving across industries and science. Our approach presents the QLIF model, where neurons integrate incoming signals and fire upon a threshold crossing, creating spikes that interact with quantum circuits to form a quantum-spiking neural network. Our work aims to: (i) enhance computational time and (ii) enrich the learning capabilities of the training model. Our results highlight that QSNN not only accelerates training but also improves accuracy, particularly in deeper quantum circuits. This demonstrates the effectiveness of integrating spiking neural dynamics into quantum models, paving the way for more efficient and biologically inspired quantum learning systems. The proposed approach holds promise for future applications in neuromorphic quantum computing and real-time edge intelligence.

IEEE International Conference on Quantum Computing and Engineering (QCE)•Aug 30, 2025•1 citation

A quantum leaky integrate-and-fire spiking neuron and network

Dean Brand, Francesco Petruccione

Abstract Quantum machine learning is in a period of rapid development and discovery, however it still lacks the resources and diversity of computational models of its classical complement. With the growing difficulties of classical models requiring extreme hardware and power solutions, and quantum models being limited by noisy intermediate-scale quantum (NISQ) hardware, there is an emerging opportunity to solve both problems together. Here we introduce a new software model for quantum neuromorphic computing — a quantum leaky integrate-and-fire (QLIF) neuron, implemented as a compact high-fidelity quantum circuit, requiring only 2 rotation gates and no CNOT gates. We use these neurons as building blocks in the construction of a quantum spiking neural network (QSNN), and a quantum spiking convolutional neural network (QSCNN), as the first of their kind. We apply these models to the MNIST, Fashion-MNIST, and KMNIST datasets for a full comparison with other classical and quantum models. We find that the proposed models perform competitively, with comparative accuracy, with efficient scaling and fast computation in classical simulation as well as on quantum devices.

arXiv:2407.16398•npj Quantum Information•Dec 2, 2024•21 citations

Quantum-Guided Federated Transformers for Privacy–Preserving Large-Scale Analytics

D. Jayasutha

The proliferation of large-scale analytics across distributed edge–cloud environments has raised critical challenges related to data privacy, communication overhead, and computational efficiency. To address these issues, this paper proposes a Quantum-Guided Federated Transformer (QGFT) framework for privacy-preserving large-scale analytics, integrating quantum-inspired optimization with federated transformer learning. In the proposed model, a quantum-guided variational optimizer leverages superposition-driven exploration and entanglement-inspired correlation modeling to adaptively optimize transformer attention weights during decentralized training, without sharing raw data. Federated aggregation is enhanced using privacy-aware adaptive parameter fusion, enabling robust convergence under heterogeneous and non-IID client data distributions. Extensive evaluations conducted on large-scale benchmark datasets demonstrate that QGFT achieves a 3.8–6.4% improvement in analytics accuracy, a 28–35% reduction in communication overhead, and a 22–31% faster convergence rate compared to conventional federated transformer and Fed Avg-based approaches. Furthermore, the integration of quantum-guided optimization improves model generalization by 18.6% under high data heterogeneity. Differential privacy analysis confirms that the proposed framework maintains a privacy leakage probability below 10⁻⁶, satisfying stringent regulatory requirements. These results indicate that QGFT provides a scalable, secure, and efficient solution for next-generation privacy-preserving analytics in federated edge–cloud intelligence. The framework enhances the confidentiality of data during the collaborating process of different nodes while preserving the accuracy of the models across multiple resources. In addition, QGFT is adaptable to all types of edge devices, thus enabling intelligent distributed systems to use Privacy-Aware systems.

CompSci & AI Advances•Jul 29, 2025•0 citations

QFed: Parameter-Compact Quantum-Classical Federated Learning

Samar Ramadan Mohamed AbdelGhani, Soumaya Cherkaoui

Organizations and enterprises across domains such as healthcare, finance, and scientific research are increasingly required to extract collective intelligence from distributed, siloed datasets while adhering to strict privacy, regulatory, and sovereignty requirements. Federated Learning (FL) enables collaborative model building without sharing sensitive raw data, but faces growing challenges posed by statistical heterogeneity, system diversity, and the computational burden from complex models. This study examines the potential of quantum-assisted federated learning, which could cut the number of parameters in classical models by polylogarithmic factors and thus lessen training overhead. Accordingly, we introduce QFed, a quantum-enabled federated learning framework aimed at boosting computational efficiency across edge device networks. We evaluate the proposed framework using the widely adopted FashionMNIST dataset. Experimental results show that QFed achieves a 77.6 % reduction in the parameter count of a VGG-like model while maintaining an accuracy comparable to classical approaches in a scalable environment. These results point to the potential of leveraging quantum computing within a federated learning context to strengthen FL capabilities of edge devices.

arXiv:2601.09809•IEEE Middle East Conference on Communications and Networking (MECOM)•Nov 4, 2025•2 citations

Quantum-Enhanced Federated Learning for Realtime Consumer Sentiment Analysis: a Privacypreserving Hybrid Framework

Hongzhen Yu, Hazirah Bee Binti Yusof Ali, M. Kazem Chamran

As real-time data processing becomes central to industries like retail, e-commerce, and entertainment, ensuring both computational efficiency and data privacy is increasingly vital. This study proposes a novel hybrid framework that integrates quantum-enhanced transformers within a Federated Learning (FL) system to perform real-time consumer sentiment analysis. While FL ensures data privacy by decentralizing model training across edge devices, it struggles with issues like high communication overhead and slow convergence in non-IID environments. On the other hand, quantum-enhanced models offer computational acceleration but often lack sufficient privacy safeguards, especially during quantum circuit operations. This research addresses these challenges by developing a quantumenhanced transformer optimized for sentiment analysis and embedding it into a privacy-preserving FL architecture. Advanced encryption techniques such as differential privacy and quantum homomorphic encryption are incorporated to mitigate data leakage risks. The study adopts a four-phase methodology: model development using quantum simulation platforms (e.g., IBM Qiskit), FL integration using FedAvg protocols, system validation through benchmarking against classical models, and real-time deployment simulations across industry-specific datasets. Results show that the proposed system achieves superior performance in latency, model accuracy, and privacy metrics compared to traditional FL models. Despite challenges related to quantum noise and heterogeneity in client data, the system demonstrates robustness and scalability under real-time conditions. This research contributes to the field by providing a viable, secure, and scalable solution for deploying quantum-AI in decentralized environments. It opens pathways for future research in hybrid quantum-classical architectures and domain-specific AI applications that require enhanced privacy and speed.

International Conference on Artificial Intelligence, Robotics, and Communication (ICAIRC)•Nov 7, 2025•0 citations
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.
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.
Quantum-AI is Ushering in a new scientific revolution, where Quantum Spiking Neural Networks (QSNN) with Quantum Leaky Integrate-and-Fire (QLIF) neurons propel advancements in the modeling of complex biological systems and neural networks. Inspired by the remarkable synergy between quantum mechanics and biological spiking neurons, we present a novel QSNN architecture that leverages QLIF to tackle complex AI tasks. Leveraging entanglement, the quantum variant of SNNs acts as a game-changer, offering faster computation, enhanced accuracy. QLIF Spiking Neurons provide a powerful solution to scalability issues, advancing the potential of AI and quantum technologies in neural networks and complex problem-solving across industries and science. Our approach presents the QLIF model, where neurons integrate incoming signals and fire upon a threshold crossing, creating spikes that interact with quantum circuits to form a quantum-spiking neural network. Our work aims to: (i) enhance computational time and (ii) enrich the learning capabilities of the training model. Our results highlight that QSNN not only accelerates training but also improves accuracy, particularly in deeper quantum circuits. This demonstrates the effectiveness of integrating spiking neural dynamics into quantum models, paving the way for more efficient and biologically inspired quantum learning systems. The proposed approach holds promise for future applications in neuromorphic quantum computing and real-time edge intelligence.
Abstract Quantum machine learning is in a period of rapid development and discovery, however it still lacks the resources and diversity of computational models of its classical complement. With the growing difficulties of classical models requiring extreme hardware and power solutions, and quantum models being limited by noisy intermediate-scale quantum (NISQ) hardware, there is an emerging opportunity to solve both problems together. Here we introduce a new software model for quantum neuromorphic computing — a quantum leaky integrate-and-fire (QLIF) neuron, implemented as a compact high-fidelity quantum circuit, requiring only 2 rotation gates and no CNOT gates. We use these neurons as building blocks in the construction of a quantum spiking neural network (QSNN), and a quantum spiking convolutional neural network (QSCNN), as the first of their kind. We apply these models to the MNIST, Fashion-MNIST, and KMNIST datasets for a full comparison with other classical and quantum models. We find that the proposed models perform competitively, with comparative accuracy, with efficient scaling and fast computation in classical simulation as well as on quantum devices.
The proliferation of large-scale analytics across distributed edge–cloud environments has raised critical challenges related to data privacy, communication overhead, and computational efficiency. To address these issues, this paper proposes a Quantum-Guided Federated Transformer (QGFT) framework for privacy-preserving large-scale analytics, integrating quantum-inspired optimization with federated transformer learning. In the proposed model, a quantum-guided variational optimizer leverages superposition-driven exploration and entanglement-inspired correlation modeling to adaptively optimize transformer attention weights during decentralized training, without sharing raw data. Federated aggregation is enhanced using privacy-aware adaptive parameter fusion, enabling robust convergence under heterogeneous and non-IID client data distributions. Extensive evaluations conducted on large-scale benchmark datasets demonstrate that QGFT achieves a 3.8–6.4% improvement in analytics accuracy, a 28–35% reduction in communication overhead, and a 22–31% faster convergence rate compared to conventional federated transformer and Fed Avg-based approaches. Furthermore, the integration of quantum-guided optimization improves model generalization by 18.6% under high data heterogeneity. Differential privacy analysis confirms that the proposed framework maintains a privacy leakage probability below 10⁻⁶, satisfying stringent regulatory requirements. These results indicate that QGFT provides a scalable, secure, and efficient solution for next-generation privacy-preserving analytics in federated edge–cloud intelligence. The framework enhances the confidentiality of data during the collaborating process of different nodes while preserving the accuracy of the models across multiple resources. In addition, QGFT is adaptable to all types of edge devices, thus enabling intelligent distributed systems to use Privacy-Aware systems.
Organizations and enterprises across domains such as healthcare, finance, and scientific research are increasingly required to extract collective intelligence from distributed, siloed datasets while adhering to strict privacy, regulatory, and sovereignty requirements. Federated Learning (FL) enables collaborative model building without sharing sensitive raw data, but faces growing challenges posed by statistical heterogeneity, system diversity, and the computational burden from complex models. This study examines the potential of quantum-assisted federated learning, which could cut the number of parameters in classical models by polylogarithmic factors and thus lessen training overhead. Accordingly, we introduce QFed, a quantum-enabled federated learning framework aimed at boosting computational efficiency across edge device networks. We evaluate the proposed framework using the widely adopted FashionMNIST dataset. Experimental results show that QFed achieves a 77.6 % reduction in the parameter count of a VGG-like model while maintaining an accuracy comparable to classical approaches in a scalable environment. These results point to the potential of leveraging quantum computing within a federated learning context to strengthen FL capabilities of edge devices.
As real-time data processing becomes central to industries like retail, e-commerce, and entertainment, ensuring both computational efficiency and data privacy is increasingly vital. This study proposes a novel hybrid framework that integrates quantum-enhanced transformers within a Federated Learning (FL) system to perform real-time consumer sentiment analysis. While FL ensures data privacy by decentralizing model training across edge devices, it struggles with issues like high communication overhead and slow convergence in non-IID environments. On the other hand, quantum-enhanced models offer computational acceleration but often lack sufficient privacy safeguards, especially during quantum circuit operations. This research addresses these challenges by developing a quantumenhanced transformer optimized for sentiment analysis and embedding it into a privacy-preserving FL architecture. Advanced encryption techniques such as differential privacy and quantum homomorphic encryption are incorporated to mitigate data leakage risks. The study adopts a four-phase methodology: model development using quantum simulation platforms (e.g., IBM Qiskit), FL integration using FedAvg protocols, system validation through benchmarking against classical models, and real-time deployment simulations across industry-specific datasets. Results show that the proposed system achieves superior performance in latency, model accuracy, and privacy metrics compared to traditional FL models. Despite challenges related to quantum noise and heterogeneity in client data, the system demonstrates robustness and scalability under real-time conditions. This research contributes to the field by providing a viable, secure, and scalable solution for deploying quantum-AI in decentralized environments. It opens pathways for future research in hybrid quantum-classical architectures and domain-specific AI applications that require enhanced privacy and speed.