FLOP: Federated Learning on Medical Datasets using Partial Networks
This addresses privacy concerns in federated learning for medical data sharing among hospitals, though it appears incremental as it builds on existing FL methods with a partial network modification.
The paper tackles the problem of data scarcity and privacy risks in federated learning for medical datasets, particularly for COVID-19 diagnosis, by proposing FLOP, which shares only partial models between servers and clients. It achieves comparable or better performance while reducing privacy and security risks, as demonstrated on benchmark data and real-world healthcare tasks.
The outbreak of COVID-19 Disease due to the novel coronavirus has caused a shortage of medical resources. To aid and accelerate the diagnosis process, automatic diagnosis of COVID-19 via deep learning models has recently been explored by researchers across the world. While different data-driven deep learning models have been developed to mitigate the diagnosis of COVID-19, the data itself is still scarce due to patient privacy concerns. Federated Learning (FL) is a natural solution because it allows different organizations to cooperatively learn an effective deep learning model without sharing raw data. However, recent studies show that FL still lacks privacy protection and may cause data leakage. We investigate this challenging problem by proposing a simple yet effective algorithm, named \textbf{F}ederated \textbf{L}earning \textbf{o}n Medical Datasets using \textbf{P}artial Networks (FLOP), that shares only a partial model between the server and clients. Extensive experiments on benchmark data and real-world healthcare tasks show that our approach achieves comparable or better performance while reducing the privacy and security risks. Of particular interest, we conduct experiments on the COVID-19 dataset and find that our FLOP algorithm can allow different hospitals to collaboratively and effectively train a partially shared model without sharing local patients' data.