def build_federated_averaging_process( model_fn: Callable[[], model_lib.Model], client_optimizer_fn: Callable[[], tf.keras.optimizers.Optimizer], server_optimizer_fn: Callable[ [], tf.keras.optimizers.Optimizer] = DEFAULT_SERVER_OPTIMIZER_FN, client_weight_fn: Callable[[Any], tf.Tensor] = None, stateful_delta_aggregate_fn=None, stateful_model_broadcast_fn=None) -> tff.utils.IterativeProcess: """Builds the TFF computations for optimization using federated averaging. Args: model_fn: A no-arg function that returns a `tff.learning.Model`. client_optimizer_fn: A no-arg callable that returns a `tf.keras.Optimizer`. server_optimizer_fn: A no-arg callable that returns a `tf.keras.Optimizer`. The `apply_gradients` method of this optimizer is used to apply client updates to the server model. The default creates a `tf.keras.optimizers.SGD` with a learning rate of 1.0, which simply adds the average client delta to the server's model. client_weight_fn: Optional function that takes the output of `model.report_local_outputs` and returns a tensor that provides the weight in the federated average of model deltas. If not provided, the default is the total number of examples processed on device. stateful_delta_aggregate_fn: A `tff.utils.StatefulAggregateFn` where the `next_fn` performs a federated aggregation and upates state. That is, it has TFF type `(state@SERVER, value@CLIENTS, weights@CLIENTS) -> (state@SERVER, aggregate@SERVER)`, where the `value` type is `tff.learning.framework.ModelWeights.trainable` corresponding to the object returned by `model_fn`. By default performs arithmetic mean aggregation, weighted by `client_weight_fn`. stateful_model_broadcast_fn: A `tff.utils.StatefulBroadcastFn` where the `next_fn` performs a federated broadcast and upates state. That is, it has TFF type `(state@SERVER, value@SERVER) -> (state@SERVER, value@CLIENTS)`, where the `value` type is `tff.learning.framework.ModelWeights` corresponding to the object returned by `model_fn`. By default performs identity broadcast. Returns: A `tff.utils.IterativeProcess`. """ def client_fed_avg(model_fn): return _ClientFedAvg(model_fn(), client_optimizer_fn(), client_weight_fn) if stateful_delta_aggregate_fn is None: stateful_delta_aggregate_fn = optimizer_utils.build_stateless_mean() else: py_typecheck.check_type(stateful_delta_aggregate_fn, tff.utils.StatefulAggregateFn) if stateful_model_broadcast_fn is None: stateful_model_broadcast_fn = optimizer_utils.build_stateless_broadcaster() else: py_typecheck.check_type(stateful_model_broadcast_fn, tff.utils.StatefulBroadcastFn) return optimizer_utils.build_model_delta_optimizer_process( model_fn, client_fed_avg, server_optimizer_fn, stateful_delta_aggregate_fn, stateful_model_broadcast_fn)
def test_fails_stateful_broadcast_and_process(self): model_weights_type = model_utils.weights_type_from_model( model_examples.LinearRegression) with self.assertRaises(optimizer_utils.DisjointArgumentError): federated_averaging.build_federated_averaging_process( model_fn=model_examples.LinearRegression, client_optimizer_fn=tf.keras.optimizers.SGD, stateful_model_broadcast_fn=tff.utils.StatefulBroadcastFn( initialize_fn=lambda: (), next_fn=lambda state, weights: # pylint: disable=g-long-lambda (state, tff.federated_broadcast(weights))), broadcast_process=optimizer_utils.build_stateless_broadcaster( model_weights_type=model_weights_type))
def test_fails_stateful_broadcast_and_process(self): model_weights_type = model_utils.weights_type_from_model( model_examples.LinearRegression) with self.assertRaises(optimizer_utils.DisjointArgumentError): optimizer_utils.build_model_delta_optimizer_process( model_fn=model_examples.LinearRegression, model_to_client_delta_fn=DummyClientDeltaFn, server_optimizer_fn=tf.keras.optimizers.SGD, stateful_model_broadcast_fn=computation_utils.StatefulBroadcastFn( initialize_fn=lambda: (), next_fn=lambda state, weights: # pylint: disable=g-long-lambda (state, intrinsics.federated_broadcast(weights))), broadcast_process=optimizer_utils.build_stateless_broadcaster( model_weights_type=model_weights_type))
def test_fails_stateful_broadcast_and_process(self): with tf.Graph().as_default(): model_weights_type = tff.framework.type_from_tensors( model_utils.ModelWeights.from_model( model_examples.LinearRegression())) with self.assertRaises(optimizer_utils.DisjointArgumentError): optimizer_utils.build_model_delta_optimizer_process( model_fn=model_examples.LinearRegression, model_to_client_delta_fn=DummyClientDeltaFn, server_optimizer_fn=tf.keras.optimizers.SGD, stateful_model_broadcast_fn=tff.utils.StatefulBroadcastFn( initialize_fn=lambda: (), next_fn=lambda state, weights: # pylint: disable=g-long-lambda (state, tff.federated_broadcast(weights))), broadcast_process=optimizer_utils.build_stateless_broadcaster( model_weights_type=model_weights_type))
def build_federated_process_for_test(model_fn, num_passes=5, tolerance=1e-6): """Build a test FedAvg process with a dummy client computation. Analogue of `build_federated_averaging_process`, but with client_fed_avg replaced by the dummy mean computation defined above. Args: model_fn: callable that returns a `tff.learning.Model`. num_passes: integer number of communication rounds in the smoothed Weiszfeld algorithm (min. 1). tolerance: float smoothing parameter of smoothed Weiszfeld algorithm. Default 1e-6. Returns: A `tff.utils.IterativeProcess`. """ server_optimizer_fn = lambda: tf.keras.optimizers.SGD(learning_rate=1.0) def client_fed_avg(model_fn): return DummyClientComputation(model_fn(), client_weight_fn=None) # Build robust aggregation function with tf.Graph().as_default(): # workaround since keras automatically appends "_n" to the nth call of # `model_fn` model_type = tff.framework.type_from_tensors( model_fn().weights.trainable) stateful_delta_aggregate_fn = rfa.build_stateless_robust_aggregation( model_type, num_communication_passes=num_passes, tolerance=tolerance) stateful_model_broadcast_fn = optimizer_utils.build_stateless_broadcaster( ) return optimizer_utils.build_model_delta_optimizer_process( model_fn, client_fed_avg, server_optimizer_fn, stateful_delta_aggregate_fn, stateful_model_broadcast_fn)
def build_federated_averaging_process( model_fn: Callable[[], model_lib.Model], client_optimizer_fn: Callable[[], tf.keras.optimizers.Optimizer], server_optimizer_fn: Callable[ [], tf.keras.optimizers.Optimizer] = DEFAULT_SERVER_OPTIMIZER_FN, client_weight_fn: Callable[[Any], tf.Tensor] = None, stateful_delta_aggregate_fn=None, stateful_model_broadcast_fn=None) -> tff.utils.IterativeProcess: """Builds an iterative process that performs federated averaging. This function creates a `tff.utils.IterativeProcess` that performs federated averaging on client models. The iterative process has the following methods: * `initialize`: A `tff.Computation` with the functional type signature `( -> S@SERVER)`, where `S` is a`tff.learning.framework.ServerState` representing the initial state of the server. * `next`: A `tff.Computation` with the functional type signature `(<S@SERVER, {B*}@CLIENTS> -> <S@SERVER, T@SERVER>)` where `S` is a `tff.learning.framework.ServerState` whose type matches that of the output of `initialize`, and `{B*}@CLIENTS` represents the client datasets, where `B` is the type of a single batch. This computation returns a `tff.learning.framework.ServerState` representing the updated server state and training metrics that are the result of `tff.learning.Model.federated_output_computation` during client training. Each time the `next` method is called, the server model is broadcast to each client using a broadcast function. For each client, one epoch of local training is performed via the `tf.keras.optimizers.Optimizer.apply_gradients` method of the client optimizer. Each client computes the difference between the client model after training and the initial broadcast model. These model deltas are then aggregated at the server using some aggregation function. The aggregate model delta is applied at the server by using the `tf.keras.optimizers.Optimizer.apply_gradients` method of the server optimizer. Note: the default server optimizer function is `tf.keras.optimizers.SGD` with a learning rate of 1.0, which corresponds to adding the model delta to the current server model. This recovers the original FedAvg algorithm in [McMahan et al., 2017](https://arxiv.org/abs/1602.05629). More sophisticated federated averaging procedures may use different learning rates or server optimizers. Args: model_fn: A no-arg function that returns a `tff.learning.Model`. client_optimizer_fn: A no-arg callable that returns a `tf.keras.Optimizer`. server_optimizer_fn: A no-arg callable that returns a `tf.keras.Optimizer`. By default, this uses `tf.keras.optimizers.SGD` with a learning rate of 1.0. client_weight_fn: Optional function that takes the output of `model.report_local_outputs` and returns a tensor providing the weight in the federated average of model deltas. If not provided, the default is the total number of examples processed on device. stateful_delta_aggregate_fn: A `tff.utils.StatefulAggregateFn` where the `next_fn` performs a federated aggregation and upates state. It must have TFF type `(<state@SERVER, value@CLIENTS, weights@CLIENTS> -> <state@SERVER, aggregate@SERVER>)`, where the `value` type is `tff.learning.framework.ModelWeights.trainable` corresponding to the object returned by `model_fn`. By default performs arithmetic mean aggregation, weighted by `client_weight_fn`. stateful_model_broadcast_fn: A `tff.utils.StatefulBroadcastFn` where the `next_fn` performs a federated broadcast and upates state. It must have TFF type `(<state@SERVER, value@SERVER> -> <state@SERVER, value@CLIENTS>)`, where the `value` type is `tff.learning.framework.ModelWeights` corresponding to the object returned by `model_fn`. The default is the identity broadcast. Returns: A `tff.utils.IterativeProcess`. """ def client_fed_avg(model_fn): return ClientFedAvg(model_fn(), client_optimizer_fn(), client_weight_fn) if stateful_delta_aggregate_fn is None: stateful_delta_aggregate_fn = optimizer_utils.build_stateless_mean() else: py_typecheck.check_type(stateful_delta_aggregate_fn, tff.utils.StatefulAggregateFn) if stateful_model_broadcast_fn is None: stateful_model_broadcast_fn = optimizer_utils.build_stateless_broadcaster( ) else: py_typecheck.check_type(stateful_model_broadcast_fn, tff.utils.StatefulBroadcastFn) return optimizer_utils.build_model_delta_optimizer_process( model_fn, client_fed_avg, server_optimizer_fn, stateful_delta_aggregate_fn, stateful_model_broadcast_fn)
def build_federated_sgd_process( model_fn, server_optimizer_fn=lambda: tf.keras.optimizers.SGD(learning_rate=0.1), client_weight_fn=None, stateful_delta_aggregate_fn=None, stateful_model_broadcast_fn=None): """Builds the TFF computations for optimization using federated SGD. This function creates a `tff.templates.IterativeProcess` that performs federated averaging on client models. The iterative process has the following methods: * `initialize`: A `tff.Computation` with the functional type signature `( -> S@SERVER)`, where `S` is a`tff.learning.framework.ServerState` representing the initial state of the server. * `next`: A `tff.Computation` with the functional type signature `(<S@SERVER, {B*}@CLIENTS> -> <S@SERVER, T@SERVER>)` where `S` is a `tff.learning.framework.ServerState` whose type matches that of the output of `initialize`, and `{B*}@CLIENTS` represents the client datasets, where `B` is the type of a single batch. This computation returns a `tff.learning.framework.ServerState` representing the updated server state and training metrics that are the result of `tff.learning.Model.federated_output_computation` during client training. Each time the `next` method is called, the server model is broadcast to each client using a broadcast function. Each client sums the gradients at each batch in the client's local dataset. These gradient sums are then aggregated at the server using an aggregation function. The aggregate gradients are applied at the server by using the `tf.keras.optimizers.Optimizer.apply_gradients` method of the server optimizer. Note: the default server optimizer function is `tf.keras.optimizers.SGD` with a learning rate of 1.0, which corresponds to adding the aggregate of the gradients to the current server model. This recovers the original FedSGD algorithm in [McMahan et al., 2017](https://arxiv.org/abs/1602.05629). More sophisticated federated SGD procedures may use different learning rates or server optimizers. Args: model_fn: A no-arg function that returns a `tff.learning.Model`. This method must *not* capture TensorFlow tensors or variables and use them. The model must be constructed entirely from scratch on each invocation, returning the same pre-constructed model each call will result in an error. server_optimizer_fn: A no-arg function that returns a `tf.Optimizer`. The `apply_gradients` method of this optimizer is used to apply client updates to the server model. client_weight_fn: Optional function that takes the output of `model.report_local_outputs` and returns a tensor that provides the weight in the federated average of the aggregated gradients. If not provided, the default is the total number of examples processed on device. stateful_delta_aggregate_fn: A `tff.utils.StatefulAggregateFn` where the `next_fn` performs a federated aggregation and upates state. It must have TFF type `(<state@SERVER, value@CLIENTS, weights@CLIENTS> -> <state@SERVER, aggregate@SERVER>)`, where the `value` type is `tff.learning.framework.ModelWeights.trainable` corresponding to the object returned by `model_fn`. By default performs arithmetic mean aggregation, weighted by `client_weight_fn`. stateful_model_broadcast_fn: A `tff.utils.StatefulBroadcastFn` where the `next_fn` performs a federated broadcast and upates state. It must have TFF type `(<state@SERVER, value@SERVER> -> <state@SERVER, value@CLIENTS>)`, where the `value` type is `tff.learning.framework.ModelWeights` corresponding to the object returned by `model_fn`. The default is the identity broadcast. Returns: A `tff.templates.IterativeProcess`. """ def client_sgd_avg(model_fn): return ClientSgd(model_fn(), client_weight_fn) if stateful_delta_aggregate_fn is None: stateful_delta_aggregate_fn = optimizer_utils.build_stateless_mean() else: py_typecheck.check_type(stateful_delta_aggregate_fn, tff.utils.StatefulAggregateFn) if stateful_model_broadcast_fn is None: stateful_model_broadcast_fn = optimizer_utils.build_stateless_broadcaster( ) else: py_typecheck.check_type(stateful_model_broadcast_fn, tff.utils.StatefulBroadcastFn) return optimizer_utils.build_model_delta_optimizer_process( model_fn, client_sgd_avg, server_optimizer_fn, stateful_delta_aggregate_fn, stateful_model_broadcast_fn)
def build_federated_evaluation( model_fn: training_process.ModelFn, *, # Callers pass below args by name. loss_fn: training_process.LossFn, metrics_fn: Optional[training_process.MetricsFn] = None, reconstruction_optimizer_fn: training_process.OptimizerFn = functools. partial(tf.keras.optimizers.SGD, 0.1), dataset_split_fn: Optional[reconstruction_utils.DatasetSplitFn] = None, broadcast_process: Optional[measured_process_lib.MeasuredProcess] = None, ) -> computation_base.Computation: """Builds a `tff.Computation` for evaluating a reconstruction `Model`. The returned computation proceeds in two stages: (1) reconstruction and (2) evaluation. During the reconstruction stage, local variables are reconstructed by freezing global variables and training using `reconstruction_optimizer_fn`. During the evaluation stage, the reconstructed local variables and global variables are evaluated using the provided `loss_fn` and `metrics_fn`. Usage of returned computation: eval_comp = build_federated_evaluation(...) metrics = eval_comp(tff.learning.reconstruction.get_global_variables(model), federated_data) Args: model_fn: A no-arg function that returns a `tff.learning.reconstruction.Model`. This method must *not* capture Tensorflow tensors or variables and use them. Must be constructed entirely from scratch on each invocation, returning the same pre-constructed model each call will result in an error. loss_fn: A no-arg function returning a `tf.keras.losses.Loss` to use to reconstruct and evaluate the model. The loss will be applied to the model's outputs during the evaluation stage. The final loss metric is the example-weighted mean loss across batches (and across clients). metrics_fn: A no-arg function returning a list of `tf.keras.metrics.Metric`s to evaluate the model. The metrics will be applied to the model's outputs during the evaluation stage. Final metric values are the example-weighted mean of metric values across batches (and across clients). If None, no metrics are applied. reconstruction_optimizer_fn: A no-arg function that returns a `tf.keras.optimizers.Optimizer` used to reconstruct the local variables with the global ones frozen. dataset_split_fn: A `tff.learning.reconstruction.DatasetSplitFn` taking in a single TF dataset and producing two TF datasets. The first is iterated over during reconstruction, and the second is iterated over during evaluation. This can be used to preprocess datasets to e.g. iterate over them for multiple epochs or use disjoint data for reconstruction and evaluation. If None, split client data in half for each user, using one half for reconstruction and the other for evaluation. See `tff.learning.reconstruction.build_dataset_split_fn` for options. broadcast_process: A `tff.templates.MeasuredProcess` that broadcasts the model weights on the server to the clients. It must support the signature `(input_values@SERVER -> output_values@CLIENT)` and have empty state. If set to default None, the server model is broadcast to the clients using the default `tff.federated_broadcast`. Raises: TypeError: if `broadcast_process` does not have the expected signature or has non-empty state. Returns: A `tff.Computation` that accepts global model parameters and federated data and returns example-weighted evaluation loss and metrics. """ # Construct the model first just to obtain the metadata and define all the # types needed to define the computations that follow. with tf.Graph().as_default(): model = model_fn() global_weights = reconstruction_utils.get_global_variables(model) model_weights_type = type_conversions.type_from_tensors(global_weights) batch_type = computation_types.to_type(model.input_spec) metrics = [keras_utils.MeanLossMetric(loss_fn())] if metrics_fn is not None: metrics.extend(metrics_fn()) federated_output_computation = ( keras_utils.federated_output_computation_from_metrics(metrics)) # Remove unneeded variables to avoid polluting namespace. del model del global_weights del metrics if dataset_split_fn is None: dataset_split_fn = reconstruction_utils.build_dataset_split_fn( split_dataset=True) if broadcast_process is None: broadcast_process = optimizer_utils.build_stateless_broadcaster( model_weights_type=model_weights_type) if not optimizer_utils.is_valid_broadcast_process(broadcast_process): raise TypeError( 'broadcast_process type signature does not conform to expected ' 'signature (<state@S, input@S> -> <state@S, result@C, measurements@S>).' ' Got: {t}'.format(t=broadcast_process.next.type_signature)) if iterative_process.is_stateful(broadcast_process): raise TypeError( f'Eval broadcast_process must be stateless (have an empty ' 'state), has state ' f'{broadcast_process.initialize.type_signature.result!r}') @tensorflow_computation.tf_computation( model_weights_type, computation_types.SequenceType(batch_type)) def client_computation(incoming_model_weights: computation_types.Type, client_dataset: computation_types.SequenceType): """Reconstructs and evaluates with `incoming_model_weights`.""" client_model = model_fn() client_global_weights = reconstruction_utils.get_global_variables( client_model) client_local_weights = reconstruction_utils.get_local_variables( client_model) metrics = [keras_utils.MeanLossMetric(loss_fn())] if metrics_fn is not None: metrics.extend(metrics_fn()) client_loss = loss_fn() reconstruction_optimizer = reconstruction_optimizer_fn() @tf.function def reconstruction_reduce_fn(num_examples_sum, batch): """Runs reconstruction training on local client batch.""" with tf.GradientTape() as tape: output = client_model.forward_pass(batch, training=True) batch_loss = client_loss(y_true=output.labels, y_pred=output.predictions) gradients = tape.gradient(batch_loss, client_local_weights.trainable) reconstruction_optimizer.apply_gradients( zip(gradients, client_local_weights.trainable)) return num_examples_sum + output.num_examples @tf.function def evaluation_reduce_fn(num_examples_sum, batch): """Runs evaluation on client batch without training.""" output = client_model.forward_pass(batch, training=False) # Update each metric. for metric in metrics: metric.update_state(y_true=output.labels, y_pred=output.predictions) return num_examples_sum + output.num_examples @tf.function def tf_client_computation(incoming_model_weights, client_dataset): """Reconstructs and evaluates with `incoming_model_weights`.""" recon_dataset, eval_dataset = dataset_split_fn(client_dataset) # Assign incoming global weights to `client_model` before reconstruction. tf.nest.map_structure(lambda v, t: v.assign(t), client_global_weights, incoming_model_weights) recon_dataset.reduce(tf.constant(0), reconstruction_reduce_fn) eval_dataset.reduce(tf.constant(0), evaluation_reduce_fn) eval_local_outputs = keras_utils.read_metric_variables(metrics) return eval_local_outputs return tf_client_computation(incoming_model_weights, client_dataset) @federated_computation.federated_computation( computation_types.at_server(model_weights_type), computation_types.at_clients( computation_types.SequenceType(batch_type))) def server_eval(server_model_weights: computation_types.FederatedType, federated_dataset: computation_types.FederatedType): broadcast_output = broadcast_process.next( broadcast_process.initialize(), server_model_weights) client_outputs = intrinsics.federated_map( client_computation, [broadcast_output.result, federated_dataset]) aggregated_client_outputs = federated_output_computation( client_outputs) measurements = intrinsics.federated_zip( collections.OrderedDict(broadcast=broadcast_output.measurements, eval=aggregated_client_outputs)) return measurements return server_eval
def build_training_process( model_fn: ModelFn, *, # Callers pass below args by name. loss_fn: LossFn, metrics_fn: Optional[MetricsFn] = None, server_optimizer_fn: OptimizerFn = functools.partial( tf.keras.optimizers.SGD, 1.0), client_optimizer_fn: OptimizerFn = functools.partial( tf.keras.optimizers.SGD, 0.1), reconstruction_optimizer_fn: OptimizerFn = functools.partial( tf.keras.optimizers.SGD, 0.1), dataset_split_fn: Optional[reconstruction_utils.DatasetSplitFn] = None, client_weighting: Optional[client_weight_lib.ClientWeightType] = None, broadcast_process: Optional[measured_process_lib.MeasuredProcess] = None, aggregation_factory: Optional[AggregationFactory] = None, ) -> iterative_process_lib.IterativeProcess: """Builds the IterativeProcess for optimization using FedRecon. Returns a `tff.templates.IterativeProcess` for Federated Reconstruction. On the client, computation can be divided into two stages: (1) reconstruction of local variables and (2) training of global variables. Args: model_fn: A no-arg function that returns a `tff.learning.reconstruction.Model`. This method must *not* capture Tensorflow tensors or variables and use them. must be constructed entirely from scratch on each invocation, returning the same pre-constructed model each call will result in an error. loss_fn: A no-arg function returning a `tf.keras.losses.Loss` to use to compute local model updates during reconstruction and post-reconstruction and evaluate the model during training. The final loss metric is the example-weighted mean loss across batches and across clients. The loss metric does not include reconstruction batches in the loss. metrics_fn: A no-arg function returning a list of `tf.keras.metrics.Metric`s to evaluate the model. Metrics results are computed locally as described by the metric, and are aggregated across clients as in `federated_aggregate_keras_metric`. If None, no metrics are applied. Metrics are not computed on reconstruction batches. server_optimizer_fn: A `tff.learning.optimizers.Optimizer`, or a no-arg function that returns a `tf.keras.optimizers.Optimizer` for applying updates to the global model on the server. client_optimizer_fn: A `tff.learning.optimizers.Optimizer`, or a no-arg function that returns a `tf.keras.optimizers.Optimizer` for local client training after reconstruction. reconstruction_optimizer_fn: A `tff.learning.optimizers.Optimizer`, or a no-arg function that returns a `tf.keras.optimizers.Optimizer` used to reconstruct the local variables, with the global ones frozen, or the first stage described above. dataset_split_fn: A `reconstruction_utils.DatasetSplitFn` taking in a single TF dataset and producing two TF datasets. The first is iterated over during reconstruction, and the second is iterated over post-reconstruction. This can be used to preprocess datasets to e.g. iterate over them for multiple epochs or use disjoint data for reconstruction and post-reconstruction. If None, split client data in half for each user, using one half for reconstruction and the other for evaluation. See `reconstruction_utils.build_dataset_split_fn` for options. client_weighting: A value of `tff.learning.ClientWeighting` that specifies a built-in weighting method, or a callable that takes the local metrics of the model and returns a tensor that provides the weight in the federated average of model deltas. If None, defaults to weighting by number of examples. broadcast_process: A `tff.templates.MeasuredProcess` that broadcasts the model weights on the server to the clients. It must support the signature `(input_values@SERVER -> output_values@CLIENT)`. If set to default None, the server model is broadcast to the clients using the default `tff.federated_broadcast`. aggregation_factory: An optional instance of `tff.aggregators.WeightedAggregationFactory` or `tff.aggregators.UnweightedAggregationFactory` determining the method of aggregation to perform. If unspecified, uses a default `tff.aggregators.MeanFactory` which computes a stateless mean across clients (weighted depending on `client_weighting`). Raises: TypeError: If `broadcast_process` does not have the expected signature. TypeError: If `aggregation_factory` does not have the expected signature. ValueError: If `aggregation_factory` is not a `tff.aggregators.WeightedAggregationFactory` or a `tff.aggregators.UnweightedAggregationFactory`. ValueError: If `aggregation_factory` is a `tff.aggregators.UnweightedAggregationFactory` but `client_weighting` is not `tff.learning.ClientWeighting.UNIFORM`. Returns: A `tff.templates.IterativeProcess`. """ with tf.Graph().as_default(): throwaway_model_for_metadata = model_fn() model_weights_type = type_conversions.type_from_tensors( reconstruction_utils.get_global_variables( throwaway_model_for_metadata)) if client_weighting is None: client_weighting = client_weight_lib.ClientWeighting.NUM_EXAMPLES if (isinstance(aggregation_factory, factory.UnweightedAggregationFactory) and client_weighting is not client_weight_lib.ClientWeighting.UNIFORM): raise ValueError( f'Expected `tff.learning.ClientWeighting.UNIFORM` client ' f'weighting with unweighted aggregator, instead got ' f'{client_weighting}') if broadcast_process is None: broadcast_process = optimizer_utils.build_stateless_broadcaster( model_weights_type=model_weights_type) if not _is_valid_broadcast_process(broadcast_process): raise TypeError( 'broadcast_process type signature does not conform to expected ' 'signature (<state@S, input@S> -> <state@S, result@C, measurements@S>).' ' Got: {t}'.format(t=broadcast_process.next.type_signature)) broadcaster_state_type = ( broadcast_process.initialize.type_signature.result.member) aggregation_process = _instantiate_aggregation_process( aggregation_factory, model_weights_type) aggregator_state_type = ( aggregation_process.initialize.type_signature.result.member) server_init_tff = _build_server_init_fn(model_fn, server_optimizer_fn, aggregation_process.initialize, broadcast_process.initialize) server_state_type = server_init_tff.type_signature.result.member server_update_fn = _build_server_update_fn( model_fn, server_optimizer_fn, server_state_type, server_state_type.model, aggregator_state_type=aggregator_state_type, broadcaster_state_type=broadcaster_state_type) dataset_type = computation_types.SequenceType( throwaway_model_for_metadata.input_spec) if dataset_split_fn is None: dataset_split_fn = reconstruction_utils.build_dataset_split_fn( split_dataset=True) client_update_fn = _build_client_update_fn( model_fn, loss_fn=loss_fn, metrics_fn=metrics_fn, dataset_type=dataset_type, model_weights_type=server_state_type.model, client_optimizer_fn=client_optimizer_fn, reconstruction_optimizer_fn=reconstruction_optimizer_fn, dataset_split_fn=dataset_split_fn, client_weighting=client_weighting) federated_server_state_type = computation_types.at_server( server_state_type) federated_dataset_type = computation_types.at_clients(dataset_type) # Create placeholder metrics to produce a corresponding federated output # computation. metrics = [] if metrics_fn is not None: metrics.extend(metrics_fn()) metrics.append(keras_utils.MeanLossMetric(loss_fn())) federated_output_computation = ( keras_utils.federated_output_computation_from_metrics(metrics)) run_one_round_tff = _build_run_one_round_fn( server_update_fn, client_update_fn, federated_output_computation, federated_server_state_type, federated_dataset_type, aggregation_process=aggregation_process, broadcast_process=broadcast_process, ) process = iterative_process_lib.IterativeProcess( initialize_fn=server_init_tff, next_fn=run_one_round_tff) @computations.tf_computation(server_state_type) def get_model_weights(server_state): return server_state.model process.get_model_weights = get_model_weights return process
def build_federated_averaging_process( model_fn: Callable[[], model_lib.Model], client_optimizer_fn: Optional[Callable[ [], tf.keras.optimizers.Optimizer]] = None, server_optimizer_fn: Callable[ [], tf.keras.optimizers.Optimizer] = DEFAULT_SERVER_OPTIMIZER_FN, client_weight_fn: Callable[[Any], tf.Tensor] = None, stateful_delta_aggregate_fn=None, stateful_model_broadcast_fn=None) -> tff.utils.IterativeProcess: """Builds the TFF computations for optimization using federated averaging. Args: model_fn: A no-arg function that returns a `tff.learning.Model`. client_optimizer_fn: An optional no-arg callable that returns a `tf.keras.Optimizer` server_optimizer_fn: A no-arg callable that returns a `tf.keras.Optimizer`. The `apply_gradients` method of this optimizer is used to apply client updates to the server model. The default creates a `tf.keras.optimizers.SGD` with a learning rate of 1.0, which simply adds the average client delta to the server's model. client_weight_fn: Optional function that takes the output of `model.report_local_outputs` and returns a tensor that provides the weight in the federated average of model deltas. If not provided, the default is the total number of examples processed on device. stateful_delta_aggregate_fn: A `tff.utils.StatefulAggregateFn` where the `next_fn` performs a federated aggregation and upates state. That is, it has TFF type `(state@SERVER, value@CLIENTS, weights@CLIENTS) -> (state@SERVER, aggregate@SERVER)`, where the `value` type is `tff.learning.framework.ModelWeights.trainable` corresponding to the object returned by `model_fn`. By default performs arithmetic mean aggregation, weighted by `client_weight_fn`. stateful_model_broadcast_fn: A `tff.utils.StatefulBroadcastFn` where the `next_fn` performs a federated broadcast and upates state. That is, it has TFF type `(state@SERVER, value@SERVER) -> (state@SERVER, value@CLIENTS)`, where the `value` type is `tff.learning.framework.ModelWeights` corresponding to the object returned by `model_fn`. By default performs identity broadcast. Returns: A `tff.utils.IterativeProcess`. """ if client_optimizer_fn is None: warnings.warn('tff.learning.build_federated_averaging_process will start ' 'requiring a new argument \'client_optimizer_fn\'. Specify ' 'the local client optimizer here rather than building a ' 'ttf.learning.TrainableModel') else: # Validate parameters and surfacing errors early requires building a # throwaway model here. with tf.Graph().as_default(): model = model_fn() if isinstance(model, model_lib.TrainableModel): raise TypeError('model_fn parameter should be a callable that produces ' 'tff.learning.Model, not the deprecated ' 'tff.learning.TrainableModel') def client_fed_avg(model_fn): if client_optimizer_fn is None: return _DeprecatedClientFedAvg(model_fn(), client_weight_fn) elif callable(client_optimizer_fn): return _ClientFedAvg(model_fn(), client_optimizer_fn(), client_weight_fn) else: raise TypeError(f'client_optimizer_fn parameter of ' 'tff.learning.build_federated_averaging_process must be ' 'a callable. Received a {type(client_optimizer_fn)}') if stateful_delta_aggregate_fn is None: stateful_delta_aggregate_fn = optimizer_utils.build_stateless_mean() else: py_typecheck.check_type(stateful_delta_aggregate_fn, tff.utils.StatefulAggregateFn) if stateful_model_broadcast_fn is None: stateful_model_broadcast_fn = optimizer_utils.build_stateless_broadcaster() else: py_typecheck.check_type(stateful_model_broadcast_fn, tff.utils.StatefulBroadcastFn) return optimizer_utils.build_model_delta_optimizer_process( model_fn, client_fed_avg, server_optimizer_fn, stateful_delta_aggregate_fn, stateful_model_broadcast_fn)