Quantum Federated Learning for Distributed Quantum Networks
- URL: http://arxiv.org/abs/2212.12913v2
- Date: Fri, 26 Apr 2024 13:37:44 GMT
- Title: Quantum Federated Learning for Distributed Quantum Networks
- Authors: Kai Yu, Fei Gao, Song Lin,
- Abstract summary: 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.
- Score: 9.766446130011706
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Federated learning is a framework that can learn from distributed networks. It attempts to build a global model based on virtual fusion data without sharing the actual data. Nevertheless, the traditional federated learning process encounters two main challenges: high computational cost and message transmission security. To address these challenges, we propose a quantum federated learning for distributed quantum networks by utilizing interesting characteristics of quantum mechanics. First, we give two methods to extract the data information to the quantum state. It can cope with different acquisition frequencies of data information. Next, a quantum gradient descent algorithm is provided to help clients in the distributed quantum networks to train local models. In other words, the algorithm gives the clients a mechanism to estimate the gradient of the local model in parallel. Compared with the classical counterpart, the proposed algorithm achieves exponential acceleration in dataset scale and quadratic speedup in data dimensionality. And, a quantum secure multi-party computation protocol is designed, which utilizes the Chinese residual theorem. It could avoid errors and overflow problems that may occur in the process of large number operation. Security analysis shows that this quantum protocol can resist common external and internal attacks. Finally, to demonstrate the effectiveness of the proposed framework, we use it to the train federated linear regression model and execute essential computation steps on the Qiskit quantum computing framework.
Related papers
- Dissipation-driven quantum generative adversarial networks [11.833077116494929]
We introduce a novel dissipation-driven quantum generative adversarial network (DQGAN) architecture specifically tailored for generating classical data.
The classical data is encoded into the input qubits of the input layer via strong tailored dissipation processes.
We extract both the generated data and the classification results by measuring the observables of the steady state of the output qubits.
arXiv Detail & Related papers (2024-08-28T07:41:58Z) - Efficient Learning for Linear Properties of Bounded-Gate Quantum Circuits [63.733312560668274]
Given a quantum circuit containing d tunable RZ gates and G-d Clifford gates, can a learner perform purely classical inference to efficiently predict its linear properties?
We prove that the sample complexity scaling linearly in d is necessary and sufficient to achieve a small prediction error, while the corresponding computational complexity may scale exponentially in d.
We devise a kernel-based learning model capable of trading off prediction error and computational complexity, transitioning from exponential to scaling in many practical settings.
arXiv Detail & Related papers (2024-08-22T08:21:28Z) - The curse of random quantum data [62.24825255497622]
We quantify the performances of quantum machine learning in the landscape of quantum data.
We find that the training efficiency and generalization capabilities in quantum machine learning will be exponentially suppressed with the increase in qubits.
Our findings apply to both the quantum kernel method and the large-width limit of quantum neural networks.
arXiv Detail & Related papers (2024-08-19T12:18:07Z) - 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) - Multimodal deep representation learning for quantum cross-platform
verification [60.01590250213637]
Cross-platform verification, a critical undertaking in the realm of early-stage quantum computing, endeavors to characterize the similarity of two imperfect quantum devices executing identical algorithms.
We introduce an innovative multimodal learning approach, recognizing that the formalism of data in this task embodies two distinct modalities.
We devise a multimodal neural network to independently extract knowledge from these modalities, followed by a fusion operation to create a comprehensive data representation.
arXiv Detail & Related papers (2023-11-07T04:35:03Z) - ShadowNet for Data-Centric Quantum System Learning [188.683909185536]
We propose a data-centric learning paradigm combining the strength of neural-network protocols and classical shadows.
Capitalizing on the generalization power of neural networks, this paradigm can be trained offline and excel at predicting previously unseen systems.
We present the instantiation of our paradigm in quantum state tomography and direct fidelity estimation tasks and conduct numerical analysis up to 60 qubits.
arXiv Detail & Related papers (2023-08-22T09:11:53Z) - Quantum neural networks [0.0]
This thesis combines two of the most exciting research areas of the last decades: quantum computing and machine learning.
We introduce dissipative quantum neural networks (DQNNs), which are capable of universal quantum computation and have low memory requirements while training.
arXiv Detail & Related papers (2022-05-17T07:47:00Z) - Comparing concepts of quantum and classical neural network models for
image classification task [0.456877715768796]
This material includes the results of experiments on training and performance of a hybrid quantum-classical neural network.
Although its simulation is time-consuming, the quantum network, although its simulation is time-consuming, overcomes the classical network.
arXiv Detail & Related papers (2021-08-19T18:49:30Z) - 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) - Variational learning for quantum artificial neural networks [0.0]
We first review a series of recent works describing the implementation of artificial neurons and feed-forward neural networks on quantum processors.
We then present an original realization of efficient individual quantum nodes based on variational unsampling protocols.
While keeping full compatibility with the overall memory-efficient feed-forward architecture, our constructions effectively reduce the quantum circuit depth required to determine the activation probability of single neurons.
arXiv Detail & Related papers (2021-03-03T16:10:15Z)
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.