DifferentialPrivacyServerSideAdaptiveClipping

class DifferentialPrivacyServerSideAdaptiveClipping(strategy: Strategy, noise_multiplier: float, num_sampled_clients: int, initial_clipping_norm: float = 0.1, target_clipped_quantile: float = 0.5, clip_norm_lr: float = 0.2, clipped_count_stddev: float | None = None)

Bases: Strategy

Strategy wrapper for central DP with server-side adaptive clipping.

参数:

• strategy (Strategy) -- The strategy to which DP functionalities will be added by this wrapper.

• noise_multiplier (float) -- The noise multiplier for the Gaussian mechanism for model updates.

• num_sampled_clients (int) -- The number of clients that are sampled on each round.

• initial_clipping_norm (float) -- The initial value of clipping norm. Defaults to 0.1. Andrew et al. recommends to set to 0.1.

• target_clipped_quantile (float) -- The desired quantile of updates which should be clipped. Defaults to 0.5.

• clip_norm_lr (float) -- The learning rate for the clipping norm adaptation. Defaults to 0.2. Andrew et al. recommends to set to 0.2.

• clipped_count_stddev (float) -- The standard deviation of the noise added to the count of updates below the estimate. Andrew et al. recommends to set to expected_num_records/20

实例

Create a strategy:

>>> strategy = fl.server.strategy.FedAvg( ... )

Wrap the strategy with the DifferentialPrivacyServerSideAdaptiveClipping wrapper

>>> dp_strategy = DifferentialPrivacyServerSideAdaptiveClipping(
>>>     strategy, cfg.noise_multiplier, cfg.num_sampled_clients, ...
>>> )

Methods

aggregate_evaluate(server_round, results, ...)	使用给定的策略汇总评估损失。
aggregate_fit(server_round, results, failures)	Aggregate training results and update clip norms.
configure_evaluate(server_round, parameters, ...)	配置下一轮评估。
configure_fit(server_round, parameters, ...)	配置下一轮训练。
evaluate(server_round, parameters)	使用策略中的评估函数评估模型参数。
initialize_parameters(client_manager)	使用给定的策略初始化全局模型参数。

aggregate_evaluate(server_round: int, results: list[tuple[ClientProxy, EvaluateRes]], failures: list[tuple[ClientProxy, EvaluateRes] | BaseException]) → tuple[float | None, dict[str, bool | bytes | float | int | str]]

使用给定的策略汇总评估损失。

aggregate_fit(server_round: int, results: list[tuple[ClientProxy, FitRes]], failures: list[tuple[ClientProxy, FitRes] | BaseException]) → tuple[Parameters | None, dict[str, bool | bytes | float | int | str]]

Aggregate training results and update clip norms.

configure_evaluate(server_round: int, parameters: Parameters, client_manager: ClientManager) → list[tuple[ClientProxy, EvaluateIns]]

配置下一轮评估。

configure_fit(server_round: int, parameters: Parameters, client_manager: ClientManager) → list[tuple[ClientProxy, FitIns]]

配置下一轮训练。

evaluate(server_round: int, parameters: Parameters) → tuple[float, dict[str, bool | bytes | float | int | str]] | None

使用策略中的评估函数评估模型参数。

initialize_parameters(client_manager: ClientManager) → Parameters | None

使用给定的策略初始化全局模型参数。