fl4health.servers.client_level_dp_fed_avg_server module

class ClientLevelDPFedAvgServer(client_manager, fl_config, strategy, server_noise_multiplier, num_server_rounds, reporters=None, checkpoint_and_state_module=None, delta=None, on_init_parameters_config_fn=None, server_name=None, accept_failures=True)

Bases: FlServer

__init__(client_manager, fl_config, strategy, server_noise_multiplier, num_server_rounds, reporters=None, checkpoint_and_state_module=None, delta=None, on_init_parameters_config_fn=None, server_name=None, accept_failures=True)

Server to be used in case of Client Level Differential Privacy with Federated Averaging.

Parameters:

• client_manager (ClientManager) – Determines the mechanism by which clients are sampled by the server, if they are to be sampled at all.

• fl_config (Config) – This should be the configuration that was used to setup the federated training. In most cases it should be the “source of truth” for how FL training/evaluation should proceed. For example, the config used to produce the on_fit_config_fn and on_evaluate_config_fn for the strategy. NOTE: This config is DISTINCT from the Flwr server config, which is extremely minimal.

• strategy (ClientLevelDPFedAvgM) – The aggregation strategy to be used by the server to handle. client updates and other information potentially sent by the participating clients.

• server_noise_multiplier (float) – Magnitude of noise added to the weights aggregation process by the server.

• num_server_rounds (int) – Number of rounds of FL training carried out by the server.

• reporters (Sequence[BaseReporter], optional) – A sequence of FL4Health reporters which the server should send data to before and after each round.

• checkpoint_and_state_module (BaseServerCheckpointAndStateModule | None, optional) – This module is used to handle both model checkpointing and state checkpointing. The former is aimed at saving model artifacts to be used or evaluated after training. The latter is used to preserve training state (including models) such that if FL training is interrupted, the process may be restarted. If no module is provided, no checkpointing or state preservation will happen. Defaults to None.

• delta (float | None, optional) – The delta value for epsilon-delta DP accounting. If None it defaults to being 1/total_samples in the FL run. Defaults to None.

• on_init_parameters_config_fn (Callable[[int], dict[str, Scalar]] | None, optional) – Function used to configure how one asks a client to provide parameters from which to initialize all other clients by providing a Config dictionary. If this is none, then a blank config is sent with the parameter request (which is default behavior for flower servers). Defaults to None.

• server_name (str | None, optional) – An optional string name to uniquely identify server. This name is also used as part of any state checkpointing done by the server. Defaults to None.

• accept_failures (bool, optional) – Determines whether the server should accept failures during training or evaluation from clients or not. If set to False, this will cause the server to shutdown all clients and throw an exception. Defaults to True.

fit(num_rounds, timeout)

Run federated averaging for a number of rounds.

Parameters:

• num_rounds (int) – Number of server rounds to run.

• timeout (float | None) – The amount of time in seconds that the server will wait for results from the clients selected to participate in federated training.

Returns:

The first element of the tuple is a history object containing the full set of

FL training results, including things like aggregated loss and metrics. Tuple also contains the elapsed time in seconds for the round.

Return type:

tuple[History, float]

setup_privacy_accountant(sample_counts)

Sets up FL Accountant and computes privacy loss based on class attributes and retrieved sample counts.

Parameters:

sample_counts (list[int]) – These should be the total number of training examples fetched from all clients during the sample polling process.

Return type:

None