|View source on GitHub|
Creates aggregator with adaptive zeroing and differential privacy.
tff.learning.dp_aggregator( noise_multiplier: float, clients_per_round: float, zeroing: bool = True ) ->
Zeroes out extremely large values for robustness to data corruption on clients, and performs adaptive clipping and addition of Gaussian noise for differentially private learning. For details of the DP algorithm see McMahan et. al (2017) https://arxiv.org/abs/1710.06963 The adaptive clipping uses the geometric method described in Andrew, Thakkar et al. (2021) https://arxiv.org/abs/1905.03871