Federated Learning: Issues in Medical Application

Since the federated learning, which makes AI learning possible without moving local data around, was introduced by google in 2017 it has been actively studied particularly field of medicine. In fact, idea machine collecting from clients is very attractive because remain sites. However, techniques still have various open issues due to its own characteristics such as non identical distribution, client participation management, and vulnerable environments. this presentation, current make flawlessly useful real world will be briefly overviewed. They are related data/system heterogeneity, traceability, security. Also, we introduce modularized framework, currently develop, experiment protocols find solutions for aforementioned issues. The framework public after development completes.