Abstract The unstoppable growth of the Industrial Internet of Things (IIoT) already has left the field of outright decentralization of data, provoking an urgent need in the creation of sensitive machine learning models that consider user privacy. The de facto standard towards this goal has been Federated Learning (FL), which allows edge devices to be trained without providing access to raw information. However, the dynamism of IIoT systems with Non-Independent and Identically Distributed (Non-IID) data is expected to worsen the performance of FL, resulting in such problems as model divergence and catastrophic forgetting. Quantum Federated Learning (QFL) solves these difficulties by transferring project data to high dimensional Hilbert spaces with Variational Quantum Circuits (VQCs), which is able to discover correlations that cannot be observed with classical networks. Among the latest inventions in this respect is the usage of TimeReversal Symmetry, another concept of physics which has been used to stabilize the learning process, based on matching the present model states with their preceding ones. The existing methods, such as Dual-Timeline QFL (DT-QFL) are flawed in the sense that they use hyperparameters to weight historical snapshots that are known beforehand. This rigidity may lead to slow convergence and too much communication overhead especially among networks. The present paper suggests a new model called Q-Attentive DT-QFL that implements a Quantum Self-Attention Mechanism (QSAM) in the time-reversal workflow. The model defines the relative values of past data at a certain point in time on its own based on dynamically computing attention scores between the current parameter trajectory and time reversed states. To support our proposal we present in depth theoretical analysis which illustrates convergence limits and reveals that our adaptive weighting methodology forms an important minimization of the variance of global updates. Scaling experiments on the Quantum MNIST dataset have shown that Q -Attentive DT -QFL has the highest accuracy in classification with 94.2 per cent accuracy and consumes forty percent less communication rounds compared with both fixed DT -QFL and classical baselines. b We also perform a detailed security review and certify the resistance of the framework to quantum noise (i.e. Depolarizing and Amplitude Damping ) and also compatibility with NearIntermediate-Scale Quantum (NISQ) hardware. In order to ensure transparency, we project the space of quantum features with SHAP values to explain the mechanisms of decision-making and use Principal Component Analysis(PCA).
Abstract The unstoppable growth of the Industrial Internet of Things (IIoT) already has left the field of outright decentralization of data, provoking an urgent need in the creation of sensitive machine learning models that consider user privacy. The de facto standard towards this goal has been Federated Learning (FL), which allows edge devices to be trained without providing access to raw information. However, the dynamism of IIoT systems with Non-Independent and Identically Distributed (Non-IID) data is expected to worsen the performance of FL, resulting in such problems as model divergence and catastrophic forgetting. Quantum Federated Learning (QFL) solves these difficulties by transferring project data to high dimensional Hilbert spaces with Variational Quantum Circuits (VQCs), which is able to discover correlations that cannot be observed with classical networks. Among the latest inventions in this respect is the usage of TimeReversal Symmetry, another concept of physics which has been used to stabilize the learning process, based on matching the present model states with their preceding ones. The existing methods, such as Dual-Timeline QFL (DT-QFL) are flawed in the sense that they use hyperparameters to weight historical snapshots that are known beforehand. This rigidity may lead to slow convergence and too much communication overhead especially among networks. The present paper suggests a new model called Q-Attentive DT-QFL that implements a Quantum Self-Attention Mechanism (QSAM) in the time-reversal workflow. The model defines the relative values of past data at a certain point in time on its own based on dynamically computing attention scores between the current parameter trajectory and time reversed states. To support our proposal we present in depth theoretical analysis which illustrates convergence limits and reveals that our adaptive weighting methodology forms an important minimization of the variance of global updates. Scaling experiments on the Quantum MNIST dataset have shown that Q -Attentive DT -QFL has the highest accuracy in classification with 94.2 per cent accuracy and consumes forty percent less communication rounds compared with both fixed DT -QFL and classical baselines. b We also perform a detailed security review and certify the resistance of the framework to quantum noise (i.e. Depolarizing and Amplitude Damping ) and also compatibility with NearIntermediate-Scale Quantum (NISQ) hardware. In order to ensure transparency, we project the space of quantum features with SHAP values to explain the mechanisms of decision-making and use Principal Component Analysis(PCA).
Federated learning has emerged as a powerful paradigm for decentralized model training, ensuring privacy preservation by allowing clients to collaboratively learn a shared model without exchanging raw data. Quantum federated learning (QFL) extends this approach by leveraging quantum computing to enhance computational efficiency and security. However, existing QFL frameworks face challenges in handling temporal inconsistencies and ensuring model robustness across time-evolving datasets. Recent findings in quantum physics suggest the emergence of two opposing arrows of time in quantum systems, indicating that time-reversal symmetry can be harnessed for computational processes. This work introduces dual-timeline quantum federated learning (DT-QFL), a novel framework that integrates time-reversal symmetry into QFL. DT-QFL employs quantum memory kernels to encode temporal correlations in client updates, ensuring that both past and future data distributions contribute to the learning process. In addition, we introduce a quantum temporal-invariant neural network, which enables federated models to learn patterns invariant to time flow, improving generalization and reducing catastrophic forgetting in decentralized environments.
Federated learning (FL) is a privacy-preserving alternative to centralized machine learning, where model training is performed on local devices and only global model updates are shared, effectively addressing challenges, such as data silos and privacy protection. Recently, quantum FL (QFL), an emerging FL branch, has garnered significant attention in many industry applications. However, existing QFL algorithms predominantly employ average weighting for global model training, which shows poor performance on heterogeneous healthcare data. To address this challenge, this study proposes a dynamic aggregation QFL algorithm (DAQFL) for intelligent diagnosis. Specifically, it utilizes quantum neural networks (QNNs) as local training models and designs corresponding variational quantum circuits (VQC). To mitigate performance degradation caused by the heterogeneity of medical industrial data, a dynamic aggregation method based on accuracy is proposed to enhance global model performance effectively. Extensive experiments with three distribution settings, including independent and identically distributed (IID), non-independent and identically distributed (Non-IID), and long-tail datasets, show that DAQFL outperforms baseline algorithms in accuracy and training speed. It also performs well in privacy protection and robustness of anti-noise, improving its suitability for real-world medical applications.
Quantum Federated Learning (QFL) recently becomes a promising approach with the potential to revolutionize Machine Learning (ML). It merges the established strengths of classical Federated Learning (FL) with the exceptional parallel mechanism and exponential speed enhancements characteristic of quantum computing. While this innovative fusion has garnered considerable attention, a notable gap in current research is the tendency to consider traditional FL and its quantum-enhanced counterpart, QFL, in isolation. This approach often overlooks the critical role of Quantum Machine Learning (QML) in effectively bridging these two domains. Recognizing this, there emerges a pressing need for a comprehensive survey that encompasses the entire spectrum of FL paradigms, from foundational FL concepts to the cutting-edge developments in QFL. Our survey aims to address this need by providing an in-depth exploration of the various facets of FL paradigms, ultimately leading to a thorough understanding of Quantum Federated Learning. We start by emphasizing the driving factors and prevalent research topics related to FL. To develop a more efficient, robust, and precise computing paradigm, we investigate the current solutions that address the concerns of heterogeneity, privacy, security, and evaluation in FL. After that, we explore the possibility of improving the computational efficiency of ML methods by leveraging the computational capabilities of quantum computers. In particular, we discuss the frameworks, evaluation, and applications for QML. Following that, we detail the integration of quantum computing technologies with standard FL, aiming to bolster computational performance and mitigate security and privacy risks. The potential solutions to improve the efficiency (i.e., slimming mechanism) and respect the privacy and security (i.e., quantum key distribution) for QFL are explored. Finally, we outline some critical future directions towards unlocking the full potential of QFL in distributed machine learning.
Quantum federated learning (QFL) emerges as a powerful technique that combines quantum computing with federated learning to efficiently process complex data across distributed quantum devices while ensuring data privacy in quantum networks. Despite recent research efforts, existing QFL frameworks struggle to achieve optimal model training performance primarily due to inherent heterogeneity in terms of (i) quantum noise where current quantum devices are subject to varying levels of noise due to varying device quality and susceptibility to quantum decoherence, and (ii) heterogeneous data distributions where data across participating quantum devices are naturally non-independent and identically distributed (non-IID). To address these challenges, we propose a novel integrated sporadic-personalized approach called SPQFL that simultaneously handles quantum noise and data heterogeneity in a single QFL framework. It is featured in two key aspects: (i) for quantum noise heterogeneity, we introduce a notion of sporadic learning to tackle quantum noise heterogeneity across quantum devices, and (ii) for quantum data heterogeneity, we implement personalized learning through model regularization to mitigate overfitting during local training on non-IID quantum data distributions, thereby enhancing the convergence of the global model. Moreover, we conduct a rigorous convergence analysis for the proposed SPQFL framework, with both sporadic and personalized learning considerations. Theoretical findings reveal that the upper bound of the SPQFL algorithm is strongly influenced by both the number of quantum devices and the number of quantum noise measurements. Extensive simulation results in real-world datasets also illustrate that the proposed SPQFL approach yields significant improvements in terms of training performance and convergence stability compared to the state-of-the-art methods.
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.
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.