5.1.1.1.1.8. FedEval.aggregator.utils

5.1.1.1.1.8.1. Module Contents

5.1.1.1.1.8.1.1. Functions

stack_layers(→ numpy.ndarray)	stack the given layers into a single array
layerwise_aggregate(...)	Aggregate the given client-side params layer-wise.

FedEval.aggregator.utils.stack_layers(layers: Iterable[numpy.ndarray]) → numpy.ndarray

stack the given layers into a single array

Parameters:

layers (Iterable[ndarray]) – the layers to stack, ordered like [layer1, layer2, …]

Returns:

the stacked layers, with shape (len(layers), *layers[0].shape)

Return type:

ndarray

Example

>>> _stack_layers([np.array([[1, 2], [3, 4]]), np.array([[5, 6], [7, 8]])])
array([[[1, 2],
        [3, 4]],
        [[5, 6],
        [7, 8]]])

FedEval.aggregator.utils.layerwise_aggregate(params: Iterable[FedEval.aggregator.ModelWeight.ModelWeights], func: Callable[[numpy.ndarray], numpy.ndarray]) → FedEval.aggregator.ModelWeight.ModelWeights

Aggregate the given client-side params layer-wise.

Parameters:

• params (Iterable[ModelWeights]) – the weights form different clients, ordered like [params1, params2, …]

• func (Callable[[ndarray], ndarray]) – the aggregation function to apply to stacked layers from each client. And they will be called with axis=0.

Returns:

the aggregated parameters which have the same format with any instance from the params

Return type:

ModelWeights

Example

>>> params = [[np.array([[1, 2], [3, 4]]), np.array([[5, 6], [7, 8]])], [np.array([[9, 10], [11, 12]]), np.array([[13, 14], [15, 16]])]]
>>> _layerwise_aggregate(params, np.mean)
[array([[5., 6.],
       [7., 8.]]),
array([[9., 10.],
       [11., 12.]])]

>>> _layerwise_aggregate(params, np.median)
[array([[1., 2.],
       [3., 4.]]),
array([[5., 6.],
       [7., 8.]])]