Federated Learning with Heterogeneous Differential Privacy

Understand

Federated learning (FL) takes a first step towards privacy-preserving machine learning by training models while keeping client data local.

• Models trained using FL may still leak private client information through model updates during training.
• Differential privacy (DP) may be employed on model updates to provide privacy guarantees within FL, typically at the cost of degraded performance of the final trained model.
• Both non-private FL and DP-FL can be solved using variants of the federated averaging (FedAvg) algorithm.