Quantum computing shows immense potential for solving traditional, near to impossible, complex problems. It also shows how the performance and speed can be improved for the solution of existing classical problems by using quantum mechanics. However, the computation power of current computers, servers, and supercomputers is well enough to speed up the existing problem solutions. But as data generated from various resources increases rapidly, in current scenarios more than 2.5 quintillion bytes of data is generated daily and is expected to be 200+ zettabytes on the cloud by 2025. Handling and storing such a massive amount of data is a significant issue for current computing and storage devices. Quantum computing has the capability to resolve this issue with quantum rules. In this paper, the task of pattern finding and recognizing in data (i.e., machine learning) is explored with the help of quantum computing and introducing a collaborative learning architecture. It enables collaborative computation from heterogeneous quantum computing devices for machine learning tasks. Also, it can be adapted to any quantum machine learning approach and speed up the learning phase with better data privacy. The proposed scheme is implemented with the MNIST dataset to compare with current existing research work. Results show that the proposed architecture matches existing research work’s performance with the additional features of privacy and heterogeneity of quantum devices.
Quantum computing shows immense potential for solving traditional, near to impossible, complex problems. It also shows how the performance and speed can be improved for the solution of existing classical problems by using quantum mechanics. However, the computation power of current computers, servers, and supercomputers is well enough to speed up the existing problem solutions. But as data generated from various resources increases rapidly, in current scenarios more than 2.5 quintillion bytes of data is generated daily and is expected to be 200+ zettabytes on the cloud by 2025. Handling and storing such a massive amount of data is a significant issue for current computing and storage devices. Quantum computing has the capability to resolve this issue with quantum rules. In this paper, the task of pattern finding and recognizing in data (i.e., machine learning) is explored with the help of quantum computing and introducing a collaborative learning architecture. It enables collaborative computation from heterogeneous quantum computing devices for machine learning tasks. Also, it can be adapted to any quantum machine learning approach and speed up the learning phase with better data privacy. The proposed scheme is implemented with the MNIST dataset to compare with current existing research work. Results show that the proposed architecture matches existing research work’s performance with the additional features of privacy and heterogeneity of quantum devices.
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 machine learning has become a promising field due to the capability to solve the computational issues of classical machine learning models. This research investigates the integration of machine learning and quantum computing with the aim of establishing and utilizing the QML models including QSVM and QNN. Given the large number of experiments on both conventional and quantum enriched datasets, the authors show that quantum machine learning models can be faster and more accurate when compared to Classical models. Furthermore, they provide a practical way for extending current quantum models’ capabilities to fight against available quantum device limitations, achieve higher computation rates and better data handling. Savings in training times and better performance are well-demonstrated in the outcome – especially with large data sets like MNIST. As much as such issues as quantum hardware constraints persist, marrying quantum computing with machine learning expands the ability to solve problems that are big and complicated across several fields including finance, healthcare and AI. This paper therefore encourages more investment on the you need more research and development towards the realization of quantum computing in the realm of machine learning.
Healthcare organizations have a high volume of sensitive data and traditional technologies have limited storage capacity and computational resources. The prospect of sharing healthcare data for machine learning is more arduous due to firm regulations related to patient privacy. In recent years, federated learning has offered a solution to accelerate distributed machine learning addressing concerns related to data privacy and governance. Currently, the blend of quantum computing and machine learning has experienced significant attention from academic institutions and research communities. The ultimate objective of this work is to develop a federated quantum machine learning framework (FQML) to tackle the optimization, security, and privacy challenges in the healthcare industry for medical imaging tasks. In this work, we proposed federated quantum convolutional neural networks (QCNNs) with distributed training across edge devices. To demonstrate the feasibility of the proposed FQML framework, we performed extensive experiments on two benchmark medical datasets (Pneumonia MNIST, and CT kidney disease analysis), which are non-independently and non-identically partitioned among the healthcare institutions/clients. The proposed framework is validated and assessed via large-scale simulations. Based on our results, the quantum simulation experiments achieve performance levels on par with well-known classical CNN models, 86.3% accuracy on the pneumonia dataset and 92.8% on the CT-kidney dataset, while requiring fewer model parameters and consuming less data. Moreover, the client selection mechanism is proposed to reduce the computation overhead at each communication round, which effectively improves the convergence rate.
Advances in federated and quantum machine learning have improved data privacy and computational efficiency in distributed systems. Quantum Federated Learning is a novel framework which combines the superior computational power of quantum computer and scalability and data privacy concern in classical federated learning framework. However, similarly to classical counterpart, quantum distributed training version still faces with challenges in heterogeneous data settings, leading to downgrade performance. To address this issue, a personalized quantum federated learning is introduced, where the local models are divided into two parts. While the major part will be aggregated normally with vanilla federated learning, the minor layers are keep locally, without transmitting. The proposed model has shown its supremacy capabilities in difficult scenarios in multiple datasets, which is shown comprehensively through simulations and numerical results.
Machine Learning (ML) has been extensively utilized in various scientific and engineering domains. But the inherent constraints and computational complexity that arise in classical machine learning are particularly evident when dealing with large-scale, high-dimensional datasets or when attempting to solve intricate optimisation problems. Quantum systems exhibit unconventional patterns that are typically not effectively generated by traditional systems and can also tackle high dimensional and large size datasets efficiently. Therefore, it is believed that quantum computing systems may outperform traditional computing devices in machine learning tasks. Quantum Machine Learning (QML) has emerged as a rapidly developing field that combines the concepts of quantum mechanics and machine learning to solve complex problems across various disciplines. The domain of quantum machine learning investigates the development and execution of quantum software with the potential to facilitate machine learning at a much superior pace compared to traditional computers. However, the major challenges encountered are hardware limitations, noise, and development of quantum algorithms. The objective of this paper is to provide an insight on the foundational principles, essential algorithms, various associated platforms, potential applications and challenges being faced by QML. As data continues to grow in size and complexity, together with the emergence of nonlinear and high-dimensional real-world situations, the computing benefits offered by QML have the potential to facilitate significant advancements in the fields of healthcare, finance, robotics, logistics, communication, and cyber security. This paper presents the basis for future research work related to development of quantum algorithms in the domain of machine learning.
Quantum computing has been proven to excel in factorization issues and unordered search problems due to its capability of quantum parallelism. This unique feature allows exponential speed-up in solving certain problems. However, this advantage does not apply universally, and challenges arise when combining classical and quantum computing to achieve acceleration in computation speed. This paper aims to address these challenges by exploring the current state of quantum machine learning and benchmarking the performance of quantum and classical algorithms in terms of accuracy. Specifically, we conducted experiments with three datasets for binary classification, implementing Support Vector Machine (SVM) and Quantum SVM (QSVM) algorithms. Our findings suggest that the QSVM algorithm outperforms classical SVM on complex datasets, and the performance gap between quantum and classical models increases with dataset complexity, as simple models tend to overfit with complex datasets. While there is still a long way to go in terms of developing quantum hardware with sufficient resources, quantum machine learning holds great potential in areas such as unsupervised learning and generative models. Moving forward, more efforts are needed to explore new quantum learning models that can leverage the power of quantum mechanics to overcome the limitations of classical machine learning.