Recently, several studies have proposed frameworks for Quantum Federated Learning (QFL). For instance, the Google TensorFlow Quantum (TFQ) and TensorFlow Federated (TFF) libraries have been deployed for realizing QFL. However, developers, in the main, are not as yet familiar with Quantum Computing (QC) libraries and frameworks. A Domain-Specific Modeling Language (DSML) that provides an abstraction layer over the underlying QC and Federated Learning (FL) libraries would be beneficial. This could enable practitioners to carry out software development and data science tasks efficiently while deploying the state of the art in Quantum Machine Learning (QML). In this position paper, we propose extending existing domain-specific Model-Driven Engineering (MDE) tools for Machine Learning (ML) enabled systems, such as MontiAnna, ML-Quadrat, and GreyCat, to support QFL.
Recently, several studies have proposed frameworks for Quantum Federated Learning (QFL). For instance, the Google TensorFlow Quantum (TFQ) and TensorFlow Federated (TFF) libraries have been deployed for realizing QFL. However, developers, in the main, are not as yet familiar with Quantum Computing (QC) libraries and frameworks. A Domain-Specific Modeling Language (DSML) that provides an abstraction layer over the underlying QC and Federated Learning (FL) libraries would be beneficial. This could enable practitioners to carry out software development and data science tasks efficiently while deploying the state of the art in Quantum Machine Learning (QML). In this position paper, we propose extending existing domain-specific Model-Driven Engineering (MDE) tools for Machine Learning (ML) enabled systems, such as MontiAnna, ML-Quadrat, and GreyCat, to support QFL.
Quantum machine learning (QML) has emerged as a promising field that leans on the developments in quantum computing to explore complex machine learning problems. Recently, some QML models were proposed for performing classification tasks, however, they rely on centralized solutions that cannot scale well for distributed quantum networks. Hence, it is apropos to consider more practical quantum federated learning (QFL) solutions tailored towards emerging quantum networks to allow for distributing quantum learning. This paper proposes the first fully quantum federated learning frame-work that can operate over purely quantum data. First, the proposed framework generates the first quantum federated dataset in literature. Then, quantum clients share the learning of quantum circuit parameters in a decentralized manner. Extensive experiments are conducted to evaluate and validate the effectiveness of the proposed QFL solution, which is the first implementation combining Google’s TensorFlow Federated and TensorFlow Quantum.
Abstract Federated learning (FL) is a recent technique that emerged to handle the vast amount of training data needed in machine learning algorithms while fulfilling data owners’ privacy challenges in such scenarios. Simultaneously, the field of quantum computing (QC), using quantum properties such as entanglement and superposition to perform computation, has experienced exponential growth, theoretically proving to be more efficient in specific machine learning tasks and creating the discipline known as quantum machine learning (QML). Thus, an emerging body of knowledge has started studying the combination of these two research agendas, giving rise to the field of quantum federated learning (QFL). In this review, we systematically classify the existing literature through a novel taxonomy, identify current trends and challenges, and highlight research gaps and future directions to support the continued development of this emerging field.
Quantum federated learning (QFL) is a novel framework that integrates the advantages of classical federated learning (FL) with the computational power of quantum technologies. This includes quantum computing and quantum machine learning (QML), enabling QFL to handle high-dimensional complex data. QFL can be deployed over both classical and quantum communication networks in order to benefit from information-theoretic security levels surpassing traditional FL frameworks. In this paper, we provide the first comprehensive investigation of the challenges and opportunities of QFL. We particularly examine the key components of QFL and identify the unique challenges that arise when deploying it over both classical and quantum networks. We then develop novel solutions and articulate promising research directions that can help address the identified challenges. We also provide actionable recommendations to advance the practical realization of QFL.
Quantum machine learning (QML) has emerged as a promising field that leans on the developments in quantum computing to explore large complex machine learning problems. Recently, some purely quantum machine learning models were proposed such as the quantum convolutional neural networks (QCNN) to perform classification on quantum data. However, all of the existing QML models rely on centralized solutions that cannot scale well for large-scale and distributed quantum networks. Hence, it is apropos to consider more practical quantum federated learning (QFL) solutions tailored towards emerging quantum network architectures. Indeed, developing QFL frameworks for quantum networks is critical given the fragile nature of computing qubits and the difficulty of transferring them. On top of its practical momentousness, QFL allows for distributed quantum learning by leveraging existing wireless communication infrastructure. This paper proposes the first fully quantum federated learning framework that can operate over quantum data and, thus, share the learning of quantum circuit parameters in a decentralized manner. First, given the lack of existing quantum federated datasets in the literature, the proposed framework begins by generating the first quantum federated dataset, with a hierarchical data format, for distributed quantum networks. Then, clients sharing QCNN models are fed with the quantum data to perform a classification task. Subsequently, the server aggregates the learnable quantum circuit parameters from clients and performs federated averaging. Extensive experiments are conducted to evaluate and validate the effectiveness of the proposed QFL solution. This work is the first to combine Google's TensorFlow Federated and TensorFlow Quantum in a practical implementation.
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.
In this study, we explore the innovative domain of Quantum Federated Learning (QFL) as a framework for training Quantum Machine Learning (QML) models via distributed networks. Conventional machine learning models frequently grapple with issues about data privacy and the exposure of sensitive information. Our proposed Federated Quantum Neural Network (FedQNN) framework emerges as a cutting-edge solution, integrating the singular characteristics of QML with the principles of classical federated learning. This work thoroughly investigates QFL, underscoring its capability to secure data handling in a distributed environment and facilitate cooperative learning without direct data sharing. Our research corroborates the concept through experiments across varied datasets, including genomics and healthcare, thereby validating the versatility and efficacy of our FedQNN framework. The results consistently exceed 86% accuracy across three distinct datasets, proving its suitability for conducting various QML tasks. Our research not only identifies the limitations of classical paradigms but also presents a novel framework to propel the field of QML into a new era of secure and collaborative innovation.