Update Compression for Deep Neural Networks on the Edge

no code implementations • 9 Mar 2022 • Bo Chen, Ali Bakhshi, Gustavo Batista, Brian Ng, Tat-Jun Chin

In this paper, we consider the scenario where retraining can be done on the server side based on a copy of the DNN model, with only the necessary data transmitted to the edge to update the deployed model.

Federated Learning