The privacy in classical federated learning can be breached through the use
of local gradient results by using engineered queries from the clients.
However, quantum communication channels are considered more secure because the
use of measurements in the data causes some loss of information, which can be
detected. Therefore, the quantum version of federated learning can be used to
provide more privacy. Additionally, sending an $N$ dimensional data vector
through a quantum channel requires sending $\log N$ entangled qubits, which can
provide exponential efficiency if the data vector is obtained as quantum
states.
In this paper, we propose a quantum federated learning model where fixed
design quantum chips are operated based on the quantum states sent by a
centralized server. Based on the coming 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 as a quantum state is fed
into client-side chips directly; therefore, it does not require measurements on
the upcoming quantum state to obtain model parameters in order to compute
gradients. This can provide efficiency over the models where parameter vector
is sent via classical or quantum channels and local gradients are obtained
through the obtained values of these parameters.

提出了一种量子联邦学习模型，其中固定设计的量子芯片基于由集中服务器发送的量子状态进行操作。