merlin.models.tf.CGCBlock

class merlin.models.tf.CGCBlock(*args, **kwargs)

Bases: merlin.models.tf.core.combinators.ParallelBlock

Implements the Customized Gate Control (CGC) proposed in [1].

References

[1] Tang, Hongyan, et al. “Progressive layered extraction (ple): A novel multi-task learning (mtl) model for personalized recommendations.” Fourteenth ACM Conference on Recommender Systems. 2020.

Parameters

• outputs (Union[List[str], List[PredictionTask], ParallelPredictionBlock, ParallelBlock]) –

  Names of the tasks or PredictionTask/ParallelPredictionBlock objects from

  which we can extract the task names

• expert_block (Union[Block, tf.keras.layers.Layer]) – Block that will be used for the experts

• num_task_experts (int, optional) – Number of task-specific experts, by default 1

• num_shared_experts (int, optional) – Number of shared experts for tasks, by default 1

• add_shared_gate (bool, optional) – Whether to add a shared gate for this CGC block, by default False. Useful when multiple CGC blocks are stacked (e.g. in PLEBlock) As all CGC blocks except the last one should include the shared gate.

• gate_block (Optional[Block], optional) – Optional block than can make the Gate mode powerful in converting the inputs into expert weights for averaging, by default None

• gate_softmax_temperature (float, optional) – Temperature of the softmax used by the Gates for getting weights for the average. Temperature can be used to smooth the weights distribution, and is by default 1.0.

• enable_gate_weights_metrics (bool, optional) – Enables logging the average gate weights on experts

• name (Optional[str], optional) – Name of the CGC block, by default None

__init__(outputs: Union[List[str], List[merlin.models.tf.prediction_tasks.base.PredictionTask], merlin.models.tf.prediction_tasks.base.ParallelPredictionBlock, merlin.models.tf.core.combinators.ParallelBlock], expert_block: Union[merlin.models.tf.core.base.Block, keras.engine.base_layer.Layer], num_task_experts: int = 1, num_shared_experts: int = 1, add_shared_gate: bool = False, gate_block: Optional[merlin.models.tf.core.base.Block] = None, gate_softmax_temperature: float = 1.0, enable_gate_weights_metrics: bool = False, name: Optional[str] = None, **kwargs)

Methods

__init__(outputs, expert_block[, ...])
add_branch(name, block)
add_loss(losses, **kwargs)	Add loss tensor(s), potentially dependent on layer inputs.
add_metric(value[, name])	Adds metric tensor to the layer.
add_update(updates)	Add update op(s), potentially dependent on layer inputs.
add_variable(*args, **kwargs)	Deprecated, do NOT use! Alias for add_weight.
add_weight([name, shape, dtype, ...])	Adds a new variable to the layer.
apply_to_all(inputs[, columns_to_filter])
apply_to_branch(branch_name, *block)
as_tabular([name])
build(input_shape)
build_from_config(config)
calculate_batch_size_from_input_shapes(...)
call(inputs, **kwargs)
call_outputs(outputs[, training])
check_schema([schema])
compute_call_output_shape(input_shape)
compute_mask(inputs[, mask])	Computes an output mask tensor.
compute_output_shape(input_shapes)
compute_output_signature(input_signature)	Compute the output tensor signature of the layer based on the inputs.
connect(*block[, block_name, context])	Connect the block to other blocks sequentially.
connect_branch(*branches[, add_rest, post, ...])	Connect the block to one or multiple branches.
connect_debug_block([append])	Connect the block to a debug block.
connect_with_residual(block[, activation])	Connect the block to other blocks sequentially with a residual connection.
connect_with_shortcut(block[, ...])	Connect the block to other blocks sequentially with a shortcut connection.
copy()
count_params()	Count the total number of scalars composing the weights.
finalize_state()	Finalizes the layers state after updating layer weights.
from_config(config[, custom_objects])
from_features(features[, pre, post, ...])	Initializes a TabularLayer instance where the contents of features will be filtered out
from_layer(layer)
from_schema(schema[, tags, allow_none])	Instantiate a TabularLayer instance from a DatasetSchema.
get_build_config()
get_config()
get_input_at(node_index)	Retrieves the input tensor(s) of a layer at a given node.
get_input_mask_at(node_index)	Retrieves the input mask tensor(s) of a layer at a given node.
get_input_shape_at(node_index)	Retrieves the input shape(s) of a layer at a given node.
get_item_ids_from_inputs(inputs)
get_output_at(node_index)	Retrieves the output tensor(s) of a layer at a given node.
get_output_mask_at(node_index)	Retrieves the output mask tensor(s) of a layer at a given node.
get_output_shape_at(node_index)	Retrieves the output shape(s) of a layer at a given node.
get_padding_mask_from_item_id(inputs[, ...])
get_weights()	Returns the current weights of the layer, as NumPy arrays.
parse(*block)
parse_block(input)
parse_config(config[, custom_objects])
post_call(inputs[, transformations, ...])	Method that's typically called after the forward method for post-processing.
pre_call(inputs[, transformations])	Method that's typically called before the forward method for pre-processing.
prepare([block, post, aggregation])	Transform the inputs of this block.
register_features(feature_shapes)
repeat([num])	Repeat the block num times.
repeat_in_parallel([num, prefix, names, ...])	Repeat the block num times in parallel.
repr_add()
repr_extra()
repr_ignore()
select_by_name(name)	Select a parallel block by name
select_by_names(names)	Select a list of parallel blocks by names
select_by_tag(tags)	Select layers of parallel blocks by tags.
set_aggregation(value)	param value
set_post(value)
set_pre(value)
set_schema([schema])
set_weights(weights)	Sets the weights of the layer, from NumPy arrays.
super()
with_name_scope(method)	Decorator to automatically enter the module name scope.

Attributes

REQUIRES_SCHEMA
activity_regularizer	Optional regularizer function for the output of this layer.
aggregation	rtype: TabularAggregation, optional
compute_dtype	The dtype of the layer's computations.
context
dtype	The dtype of the layer weights.
dtype_policy	The dtype policy associated with this layer.
dynamic	Whether the layer is dynamic (eager-only); set in the constructor.
first
has_schema
inbound_nodes	Return Functional API nodes upstream of this layer.
input	Retrieves the input tensor(s) of a layer.
input_mask	Retrieves the input mask tensor(s) of a layer.
input_shape	Retrieves the input shape(s) of a layer.
input_spec	InputSpec instance(s) describing the input format for this layer.
is_input
is_tabular
layers
losses	List of losses added using the add_loss() API.
metrics	List of metrics added using the add_metric() API.
name	Name of the layer (string), set in the constructor.
name_scope	Returns a tf.name_scope instance for this class.
non_trainable_variables
non_trainable_weights	List of all non-trainable weights tracked by this layer.
outbound_nodes	Return Functional API nodes downstream of this layer.
output	Retrieves the output tensor(s) of a layer.
output_mask	Retrieves the output mask tensor(s) of a layer.
output_shape	Retrieves the output shape(s) of a layer.
parallel_dict
parallel_values
post	rtype: SequentialTabularTransformations, optional
pre	rtype: SequentialTabularTransformations, optional
registry
schema
stateful
submodules	Sequence of all sub-modules.
supports_masking	Whether this layer supports computing a mask using compute_mask.
trainable
trainable_variables
trainable_weights	List of all trainable weights tracked by this layer.
updates
variable_dtype	Alias of Layer.dtype, the dtype of the weights.
variables	Returns the list of all layer variables/weights.
weights	Returns the list of all layer variables/weights.

call(inputs, **kwargs)

compute_call_output_shape(input_shape)

classmethod from_config(config, custom_objects=None, **kwargs)

get_config()