GitHub - rjsandeepkumawat/MOON: Model-Contrastive Federated Learning (MOON) is a federated learning framework that uses model representation similarity to correct individual parties' local training. MOON has been shown to perform better than other federated learning algorithms on various image classification tasks.

rjsandeepkumawat / MOON Public

Notifications You must be signed in to change notification settings
Fork 0
Star 0

Model-Contrastive Federated Learning (MOON) is a federated learning framework that uses model representation similarity to correct individual parties' local training. MOON has been shown to perform better than other federated learning algorithms on various image classification tasks.