FedControl: When Control Theory Meets Federated Learning

05/27/2022
by   Adnan Ben Mansour, et al.
0

To date, the most popular federated learning algorithms use coordinate-wise averaging of the model parameters. We depart from this approach by differentiating client contributions according to the performance of local learning and its evolution. The technique is inspired from control theory and its classification performance is evaluated extensively in IID framework and compared with FedAvg.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset