Optimizing Quantum Federated Learning Based on Federated Quantum Natural Gradient Descent
This work addresses communication efficiency in quantum federated learning, an incremental improvement for quantum machine learning applications.
The authors tackled the problem of high communication overhead in quantum federated learning by proposing the federated quantum natural gradient descent algorithm, which reduced training iterations and improved test accuracy on a handwritten digit classification dataset.
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 composed 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.