DifferentialPrivacyClientSideAdaptiveClipping#

class DifferentialPrivacyClientSideAdaptiveClipping(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)[源代码]#

基类:Strategy

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

Use adaptiveclipping_mod modifier at the client side.

In comparison to DifferentialPrivacyServerSideAdaptiveClipping, which performs clipping on the server-side, DifferentialPrivacyClientSideAdaptiveClipping expects clipping to happen on the client-side, usually by using the built-in adaptiveclipping_mod.

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 stddev of the noise added to the count of updates currently below the estimate. Andrew et al. recommends to set to expected_num_records/20

示例

Create a strategy:

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

Wrap the strategy with the DifferentialPrivacyClientSideAdaptiveClipping wrapper:

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

On the client, add the adaptiveclipping_mod to the client-side mods:

>>> app = fl.client.ClientApp(
>>>     client_fn=client_fn, mods=[adaptiveclipping_mod]
>>> )

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]][源代码]#

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]][源代码]#

Aggregate training results and update clip norms.

configure_evaluate(server_round: int, parameters: Parameters, client_manager: ClientManager) List[Tuple[ClientProxy, EvaluateIns]][源代码]#

配置下一轮评估。

configure_fit(server_round: int, parameters: Parameters, client_manager: ClientManager) List[Tuple[ClientProxy, FitIns]][源代码]#

配置下一轮训练。

evaluate(server_round: int, parameters: Parameters) Tuple[float, Dict[str, bool | bytes | float | int | str]] | None[源代码]#

使用策略中的评估函数评估模型参数。

initialize_parameters(client_manager: ClientManager) Parameters | None[源代码]#

使用给定的策略初始化全局模型参数。