New Metrics to Evaluate the Performance and Fairness of Personalized Federated Learning

no code implementations • 28 Jul 2021 • Siddharth Divi, Yi-Shan Lin, Habiba Farrukh, Z. Berkay Celik

In this setting, the non-IID distribution of the data across clients restricts the global FL model from delivering good performance on the local data of each client.

Fairness Personalized Federated Learning

Unifying Distillation with Personalization in Federated Learning

no code implementations • 31 May 2021 • Siddharth Divi, Habiba Farrukh, Berkay Celik

In the first stage, PersFL finds the optimal teacher model of each client during the FL training phase.

Fairness Federated Learning +1