5.1.1.8.1.3. FedEval.strategy.FedProx

5.1.1.8.1.3.1. Module Contents

5.1.1.8.1.3.1.1. Classes

FedProxOptimizer
FedProxParamsParser	an implentation of ParamParserInterface.
FedProx	the basic class of federated strategies.

class FedEval.strategy.FedProx.FedProxOptimizer(learning_rate=0.01, mu=0.01, name='FedProxOptimizer', **kwargs)

Bases: tensorflow.keras.optimizers.Optimizer

create_slots(var_list)

_resource_apply_sparse_duplicate_indices(grad, var, indices, **kwargs)

get_config()

_resource_apply_dense(grad, handle, apply_state)

class FedEval.strategy.FedProx.FedProxParamsParser

Bases: FedEval.utils.ParamParser

an implentation of ParamParserInterface.

static parse_model()

construct a tensorflow model according to the model configuration.

Raises:

NotImplementedError – raised when called but not overriden.

Returns:

the model constructed.

Return type:

tf.keras.Model

class FedEval.strategy.FedProx.FedProx(*args, **kwargs)

Bases: FedEval.strategy.FedAvg.FedAvg

the basic class of federated strategies.

fit_on_local_data()

fit model with local data at client side.

Called by the selected clients.

Raises:

NotImplementedError – raised when called but not overriden.

Returns:

TODO(fgh)