Handling Privacy-sensitive Clinical Data with Federated Quantum Machine Learning
Abstract
Healthcare organizations have a high volume of sensitive data and traditional technologies have limited storage capacity and computational resources. The balanced protection of confidentiality, integrity, and availability of healthcare data has become a major concern beyond classical data security considerations. Quantum computers have the potential to bring huge benefits to the healthcare sector through efficient distributed training across several quantum computers and could also advance data privacy with effective data security techniques. In this work, we proposed a novel framework to train quantum convolutional neural networks in federated learning settings that allows the implementation of decentralized quantum learning. The quantum federated learning approach trains a quantum machine learning algorithm across several decentralized servers holding non-identically and independently distributed healthcare data without exchanging them. The objective is not only to deeply analyze but also to preserve the privacy intact of individual healthcare clients during the quantum federated learning process. Our results show that the combination of quantum convolutional neural network and federated averaging algorithm can be practicable, as the federated averaging algorithm trains the quantum algorithm in fewer communication training rounds. It would be extremely beneficial to deploy distributed quantum machine learning algorithms for enabling scalable and privacy-preserving intelligent applications.
- Publication:
-
APS March Meeting Abstracts
- Pub Date:
- 2023
- Bibcode:
- 2023APS..MART70007B