Re-Weighted Softmax Cross-Entropy to Control Forgetting in Federated Learning

no code implementations • 11 Apr 2023 • Gwen Legate, Lucas Caccia, Eugene Belilovsky

In Federated Learning, a global model is learned by aggregating model updates computed at a set of independent client nodes, to reduce communication costs multiple gradient steps are performed at each node prior to aggregation.

Federated Learning