Quantum Federated Learning With Quantum Networks

• URL: http://arxiv.org/abs/2310.15084v1
• Date: Mon, 23 Oct 2023 16:45:29 GMT
• Title: Quantum Federated Learning With Quantum Networks
• Authors: Tyler Wang, Huan-Hsin Tseng, Shinjae Yoo
• Abstract summary: We present a quantum-classical transfer learning scheme for classical data and communication with a hub-spoke topology. While quantum communication is secure from eavesdrop attacks and no measurements from quantum to classical translation, due to no cloning theorem, hub-spoke topology is not ideal for quantum communication without quantum memory. We also demonstrate the first successful use of quantum weights for quantum federated learning, which allows us to perform our training entirely in quantum.
• Score: 7.842152902652214
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A major concern of deep learning models is the large amount of data that is required to build and train them, much of which is reliant on sensitive and personally identifiable information that is vulnerable to access by third parties. Ideas of using the quantum internet to address this issue have been previously proposed, which would enable fast and completely secure online communications. Previous work has yielded a hybrid quantum-classical transfer learning scheme for classical data and communication with a hub-spoke topology. While quantum communication is secure from eavesdrop attacks and no measurements from quantum to classical translation, due to no cloning theorem, hub-spoke topology is not ideal for quantum communication without quantum memory. Here we seek to improve this model by implementing a decentralized ring topology for the federated learning scheme, where each client is given a portion of the entire dataset and only performs training on that set. We also demonstrate the first successful use of quantum weights for quantum federated learning, which allows us to perform our training entirely in quantum.

Related papers

• Distributed quantum machine learning via classical communication [0.7378853859331619]
  We present an experimentally accessible distributed quantum machine learning scheme that integrates quantum processor units via classical communication. Our results indicate that incorporating classical communication notably improves classification accuracy compared to schemes without communication.
  arXiv  Detail & Related papers  (2024-08-29T08:05:57Z)
• 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)
• Quantum Internet: The Future of Internetworking [16.313110394211154]
  The purpose of a quantum Internet is to enable applications that are fundamentally out of reach for the classical Internet. This chapter aims to present the main concepts, challenges, and opportunities for research in quantum information, quantum computing and quantum networking.
  arXiv  Detail & Related papers  (2023-04-30T23:17:47Z)
• Quantum Federated Learning for Distributed Quantum Networks [9.766446130011706]
  We propose a quantum federated learning for distributed quantum networks by utilizing interesting characteristics of quantum mechanics. A quantum gradient descent algorithm is provided to help clients in the distributed quantum networks to train local models. A quantum secure multi-party computation protocol is designed, which utilizes the Chinese residual theorem.
  arXiv  Detail & Related papers  (2022-12-25T14:37:23Z)
• Quantum Semantic Communications for Resource-Efficient Quantum Networking [52.3355619190963]
  This letter proposes a novel quantum semantic communications (QSC) framework exploiting advancements in quantum machine learning and quantum semantic representations. The proposed framework achieves approximately 50-75% reduction in quantum communication resources needed, while achieving a higher quantum semantic fidelity.
  arXiv  Detail & Related papers  (2022-05-05T03:49:19Z)
• An Evolutionary Pathway for the Quantum Internet Relying on Secure Classical Repeaters [64.48099252278821]
  We conceive quantum networks using secure classical repeaters combined with the quantum secure direct communication principle. In these networks, the ciphertext gleaned from a quantum-resistant algorithm is transmitted using QSDC along the nodes. We have presented the first experimental demonstration of a secure classical repeater based hybrid quantum network.
  arXiv  Detail & Related papers  (2022-02-08T03:24:06Z)
• QuantumFed: A Federated Learning Framework for Collaborative Quantum Training [10.635097939284751]
  We propose QuantumFed, a quantum federated learning framework to have multiple quantum nodes with local quantum data train a mode together. Our experiments show the feasibility and robustness of our framework.
  arXiv  Detail & Related papers  (2021-06-16T20:28:11Z)
• 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)
• Quantum Deformed Neural Networks [83.71196337378022]
  We develop a new quantum neural network layer designed to run efficiently on a quantum computer. It can be simulated on a classical computer when restricted in the way it entangles input states.
  arXiv  Detail & Related papers  (2020-10-21T09:46:12Z)

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.