Foundations of Quantum Federated Learning Over Classical and Quantum Networks

• URL: http://arxiv.org/abs/2310.14516v1
• Date: Mon, 23 Oct 2023 02:56:00 GMT
• Title: Foundations of Quantum Federated Learning Over Classical and Quantum Networks
• Authors: Mahdi Chehimi, Samuel Yen-Chi Chen, Walid Saad, Don Towsley, M\'erouane Debbah
• Abstract summary: Quantum federated learning (QFL) is a novel framework that integrates the advantages of classical federated learning (FL) with the computational power of quantum technologies. QFL can be deployed over both classical and quantum communication networks.
• Score: 59.121263013213756
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• A Quantum-Classical Collaborative Training Architecture Based on Quantum State Fidelity [50.387179833629254]
  We introduce a collaborative classical-quantum architecture called co-TenQu. Co-TenQu enhances a classical deep neural network by up to 41.72% in a fair setting. It outperforms other quantum-based methods by up to 1.9 times and achieves similar accuracy while utilizing 70.59% fewer qubits.
  arXiv  Detail & Related papers  (2024-02-23T14:09:41Z)
• Entanglement-Assisted Quantum Networks: Mechanics, Enabling Technologies, Challenges, and Research Directions [66.27337498864556]
  This paper presents a comprehensive survey of entanglement-assisted quantum networks. It provides a detailed overview of the network structure, working principles, and development stages. It also emphasizes open research directions, including architecture design, entanglement-based network issues, and standardization.
  arXiv  Detail & Related papers  (2023-07-24T02:48:22Z)
• Towards Quantum Federated Learning [80.1976558772771]
  Quantum Federated Learning aims to enhance privacy, security, and efficiency in the learning process. We aim to provide a comprehensive understanding of the principles, techniques, and emerging applications of QFL. As the field of QFL continues to progress, we can anticipate further breakthroughs and applications across various industries.
  arXiv  Detail & Related papers  (2023-06-16T15:40:21Z)
• Quantum Split Neural Network Learning using Cross-Channel Pooling [12.261689483681145]
  In this study, a novel approach entitled quantum split learning (QSL) is presented. Cross-channel pooling is introduced, a technique that capitalizes on the distinctive properties of quantum state tomography facilitated by QNNs.
  arXiv  Detail & Related papers  (2022-11-12T00:21:45Z)
• Federated Quantum Natural Gradient Descent for Quantum Federated Learning [7.028664795605032]
  In this work, we put forth an efficient learning algorithm, namely federated quantum natural gradient descent (FQNGD) The FQNGD algorithm admits much fewer training iterations for the QFL model to get converged. Compared with other federated learning algorithms, our experiments on a handwritten digit classification dataset corroborate the effectiveness of the FQNGD algorithm for the QFL.
  arXiv  Detail & Related papers  (2022-08-15T07:17:11Z)
• Slimmable Quantum Federated Learning [44.89303833148191]
  Quantum federated learning (QFL) has recently received increasing attention, where quantum neural networks (QNNs) are integrated into federated learning (FL) We propose slimmable QFL (SlimQFL) in this article, which is a dynamic QFL framework that can cope with time-varying communication channels and computing energy limitations. Simulation results corroborate that SlimQFL achieves higher classification accuracy than Vanilla QFL, particularly under poor channel conditions on average.
  arXiv  Detail & Related papers  (2022-07-20T22:39:23Z)
• Recent Advances for Quantum Neural Networks in Generative Learning [98.88205308106778]
  Quantum generative learning models (QGLMs) may surpass their classical counterparts. We review the current progress of QGLMs from the perspective of machine learning. We discuss the potential applications of QGLMs in both conventional machine learning tasks and quantum physics.
  arXiv  Detail & Related papers  (2022-06-07T07:32:57Z)
• Quantum Federated Learning with Quantum Data [87.49715898878858]
  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. 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.
  arXiv  Detail & Related papers  (2021-05-30T12:19:27Z)
• TensorFlow Quantum: A Software Framework for Quantum Machine Learning [36.75544801185366]
  We introduce Quantum (TFQ), an open source library for the rapid prototyping of hybrid quantum-classical models for classical or quantum data. We demonstrate how one can apply TFQ to tackle advanced quantum learning tasks including meta-learning, layerwise learning, Hamiltonian learning, sampling thermal states, variational quantum eigensolvers, classification of quantum phase transitions, generative adversarial networks, and reinforcement learning.
  arXiv  Detail & Related papers  (2020-03-06T01:31:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.