QUANTUM FEDERATED LEARNING WITH QUANTUM DATA

Quantum machine learning (QML) has emerged as a promising field that leans on the developments in quantum computing to explore complex machine learning problems. Recently, some QML models were proposed for performing classification tasks, however, they rely on centralized solutions that cannot scale well for distributed quantum networks. Hence, it is apropos to consider more practical quantum federated learning (QFL) solutions tailored towards emerging quantum networks to allow for distributing quantum learning. This paper proposes the first fully quantum federated learning framework that can operate over purely quantum data. First, the proposed framework generates the first quantum federated dataset in literature. Then, quantum clients share the learning of quantum circuit parameters in a decentralized manner. Extensive experiments are conducted to evaluate and validate the effectiveness of the proposed QFL solution, which is the first implementation combining Google's TensorFlow Federated and TensorFlow Quantum.

Automated summary

This paper proposes the first fully quantum federated learning framework that operates over purely quantum data. It introduces a decentralized learning method for distributing quantum learning over quantum networks and provides the first quantum federated dataset. Extensive experiments are conducted to evaluate and validate the effectiveness of the proposed QFL solution, which combines Google's TensorFlow Federated and TensorFlow Quantum.