Abstract
Distributed training across several quantum computers could significantly improve the training time and if we could share the learned model, not the data, it could potentially improve the data privacy as the training would happen where the data is located. One of the potential schemes to achieve this property is the federated learning (FL), which consists of several clients or local nodes learning on their own data and a central node to aggregate the models collected from those local nodes. However, to the best of our knowledge, no work has been done in quantum machine learning (QML) in federation setting yet. In this work, we present the federated training on hybrid quantum-classical machine learning models although our framework could be generalized to pure quantum machine learning model. Specifically, we consider the quantum neural network (QNN) coupled with classical pre-trained convolutional model. Our distributed federated learning scheme demonstrated almost the same level of trained model accuracies and yet significantly faster distributed training. It demonstrates a promising future research direction for scaling and privacy aspects.
Highlights
Federated Quantum MachineRecently, advances in machine learning (ML), in particular deep learning (DL), have found significant success in a wide variety of challenging tasks such as computer vision [1,2,3], natural language processing [4], and even playing the game of Go with a superhuman performance [5].In the meantime, quantum computers are introduced to the general public by several technology companies such as IBM [6], Google [7], IonQ [8] and D-Wave [9]
Quantum computation tasks or quantum circuits with a large number of qubits and/or a long circuit depth cannot be faithfully implemented on these so-called noisy intermediate-scale quantum (NISQ)
To harness the power of quantum computers in the NISQ era, the key challenge is how to distribute the computational tasks to different quantum machines with limited quantum capabilities. Another challenge is the rising privacy concern in the use of large scale machine learning infrastructure. We address these two challenges by providing the framework of training quantum machine learning models in a federated manner
Summary
Quantum computers are introduced to the general public by several technology companies such as IBM [6], Google [7], IonQ [8] and D-Wave [9]. Quantum computing can provide exponential speedup to certain classes of hard problems that are intractable on classical computers [10,11]. The most famous example is the factorization of large numbers via Shor algorithm [12] which can provide exponential speedup. While the search in unstructured database via Grover algorithm [13] can provide quadratic speedup. Quantum computation tasks or quantum circuits with a large number of qubits and/or a long circuit depth cannot be faithfully implemented on these so-called noisy intermediate-scale quantum (NISQ)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
