Federated Semi-Supervised Learning with Prototypical Networks

1 code implementation • 27 May 2022 • Woojung Kim, Keondo Park, Kihyuk Sohn, Raphael Shu, Hyung-Sin Kim

Compared to a FSSL approach based on weight sharing, the prototype-based inter-client knowledge sharing significantly reduces both communication and computation costs, enabling more frequent knowledge sharing between more clients for better accuracy.

Federated Learning