Federated Learning with Sparsification-Amplified Privacy and Adaptive Optimization

Understand

Federated learning (FL) enables distributed agents to collaboratively learn a centralized model without sharing their raw data with each other.

• However, data locality does not provide sufficient privacy protection, and it is desirable to facilitate FL with rigorous differential privacy (DP) guarantee.
• Existing DP mechanisms would introduce random noise with magnitude proportional to the model size, which can be quite large in deep neural networks.
• In this paper, we propose a new FL framework with sparsification-amplified privacy.