论文标题
量子联合学习，纠缠控制的电路和叠加编码
Quantum Federated Learning with Entanglement Controlled Circuits and Superposition Coding
论文作者
论文摘要
在目睹嘈杂的中间量子量子（NISQ）时代及以后，量子联盟学习（QFL）最近已成为一个新兴的研究领域。在QFL中，每台量子计算机或设备在本地使用可训练的门训练其量子神经网络（QNN），并仅通过经典通道传达这些门参数，而无需昂贵的量子通信。为了在各种渠道条件下启用QFL，在本文中，我们开发了一个可控制的深度控制构建，可纠缠的微小量子神经网络（ESQNNS），并提出了一个纠缠的微小QFL（ESQFL），该QFL（ESQFL）传达了ES-QNNS的叠置编码参数。与现有的深度固定QNN相比，由于高纠缠熵和深度间干扰，训练深度控制的ESQNN结构更具挑战性，通过引入纠缠通用盖茨（CU）盖茨（CU）盖茨（CU）盖茨（CU）盖茨（CU）盖茨（CU）盖茨（CU）盖茨（CU）盖茨（CU）盖茨（CU）盖茨（CU）盖茨（CU）弥补（ipfd）的定期置换量（IPFD）正常互动量相差。此外，我们通过得出和最小化ESQFL的收敛结合来优化叠加编码功率分配。在图像分类任务中，与香草QFL以及不同的通道条件和各种数据分布相比，广泛的模拟在预测准确性，忠诚度和熵方面证实了ESQFL的有效性。
While witnessing the noisy intermediate-scale quantum (NISQ) era and beyond, quantum federated learning (QFL) has recently become an emerging field of study. In QFL, each quantum computer or device locally trains its quantum neural network (QNN) with trainable gates, and communicates only these gate parameters over classical channels, without costly quantum communications. Towards enabling QFL under various channel conditions, in this article we develop a depth-controllable architecture of entangled slimmable quantum neural networks (eSQNNs), and propose an entangled slimmable QFL (eSQFL) that communicates the superposition-coded parameters of eS-QNNs. Compared to the existing depth-fixed QNNs, training the depth-controllable eSQNN architecture is more challenging due to high entanglement entropy and inter-depth interference, which are mitigated by introducing entanglement controlled universal (CU) gates and an inplace fidelity distillation (IPFD) regularizer penalizing inter-depth quantum state differences, respectively. Furthermore, we optimize the superposition coding power allocation by deriving and minimizing the convergence bound of eSQFL. In an image classification task, extensive simulations corroborate the effectiveness of eSQFL in terms of prediction accuracy, fidelity, and entropy compared to Vanilla QFL as well as under different channel conditions and various data distributions.
