Optimizing Quantum Federated Learning Based on Federated Quantum Natural Gradient Descent

• Published in: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 1 - 5
• Main Authors: Qi, Jun, Zhang, Xiao-Lei, Tejedor, Javier
• Format: Conference Proceeding
• Language: English
• Published: IEEE 04.06.2023
• Subjects: Federated learning; federated quantum natural gradient descent; Neural networks; quantum federated learning; Quantum neural network; Signal processing; Signal processing algorithms; Speech processing; Stochastic processes; Training; variational quantum circuit
• ISSN: 2379-190X
• DOI: 10.1109/ICASSP49357.2023.10094634

Quantum federated learning (QFL) is a quantum extension of the classical federated learning model across multiple local quantum devices. An efficient optimization algorithm is always expected to minimize the communication overhead among different quantum participants. In this work, we propose an efficient optimization algorithm, namely federated quantum natural gradient descent (FQNGD), and further, apply it to a QFL framework that is com-posed of a variational quantum circuit (VQC)-based quantum neural networks (QNN). Compared with stochastic gradient descent methods like Adam and Adagrad, the FQNGD algorithm admits much fewer training iterations for the QFL to get converged. Moreover, it can significantly reduce the total communication overhead among local quantum devices. Our experiments on a handwritten digit classification dataset justify the effectiveness of the FQNGD for the QFL framework in terms of a faster convergence rate on the training set and higher accuracy on the test set.