Federated learning with distributed fixed design quantum chips and quantum channels

TL;DR

This paper introduces a quantum federated learning framework utilizing fixed design quantum chips and quantum channels, enhancing privacy and efficiency by transmitting quantum states directly and avoiding classical model sharing.

Contribution

The paper proposes a novel quantum federated learning model with fixed design quantum chips and quantum channels, enabling asynchronous updates and improved privacy without sharing model parameters.

Findings

Quantum channels enhance privacy over classical methods.

Quantum states enable efficient data transmission and gradient computation.

Asynchronous learning is feasible with quantum state exchanges.

Abstract

The privacy in classical federated learning can be breached through the use of local gradient results combined with engineered queries to the clients. However, quantum communication channels are considered more secure because a measurement on the channel causes a loss of information, which can be detected by the sender. Therefore, the quantum version of federated learning can be used to provide better privacy. Additionally, sending an $N$-dimensional data vector through a quantum channel requires sending $\log N$ entangled qubits, which can potentially provide efficiency if the data vector is utilized as quantum states. In this paper, we propose a quantum federated learning model in which fixed design quantum chips are operated based on the quantum states sent by a centralized server. Based on the incoming superposition states, the clients compute and then send their local gradients as quantum states to the server, where they are aggregated to update parameters. Since the server does not send model parameters, but instead sends the operator as a quantum state, the clients are not required to share the model. This allows for the creation of asynchronous learning models. In addition, the model is fed into client-side chips directly as a quantum state; therefore, it does not require measurements on the incoming quantum state to obtain model parameters in order to compute gradients. This can provide efficiency over models where the parameter vector is sent via classical or quantum channels and local gradients are obtained through the obtained values these parameters.