merlin.models.tf.PopularityBasedSampler

class merlin.models.tf.PopularityBasedSampler(*args, **kwargs)[source]

Bases: merlin.models.tf.blocks.sampling.base.ItemSampler

Provides a popularity-based negative sampling for the softmax layer to ensure training efficiency when the catalog of items is very large. The capacity of the queue is fixed and is equal to the catalog size. For each batch, we sample max_num_samples unique negatives.

This implementation does not require the actual item frequencies/probabilities distribution, but instead tries to approximate the item probabilities using the log_uniform (zipfian) distribution. The only requirement is that the item ids are decreasingly sorted by their count frequency. We use the default log-uniform (zipfian) sampler given by Tensorflow:

The Categorify op provided by nvtabular supports the frequency-based encoding as default.

P.s. Ignoring the false negatives (negative items equal to the positive ones) is managed by ItemRetrievalScorer(…, sampling_downscore_false_negatives=True)

Parameters
  • max_num_samples (int) – The number of unique negatives to sample at each batch.

  • max_id (int) – The maximum id value to be sampled. It should be equal to the categorical feature cardinality

  • min_id (int) – The minimum id value to be sampled. Useful to ignore the first categorical encoded ids, which are usually reserved for <nulls>, out-of-vocabulary or padding. Defaults to 0.

  • seed (int) – Fix the random values returned by the sampler to ensure reproducibility Defaults to None

  • item_id_feature_name (str) – Name of the column containing the item ids Defaults to item_id

__init__(max_id: int, min_id: int = 0, max_num_samples: int = 100, seed: Optional[int] = None, item_id_feature_name: str = 'item_id', **kwargs)[source]

Methods

__init__(max_id[, min_id, max_num_samples, …])

add(embeddings, items_metadata[, training])

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.

build(input_shape)

Creates the variables of the layer (for subclass implementers).

build_from_config(config)

call(inputs, item_weights[, training])

compute_mask(inputs[, mask])

Computes an output mask tensor.

compute_output_shape(input_shape)

Computes the output shape of the layer.

compute_output_signature(input_signature)

Compute the output tensor signature of the layer based on the inputs.

count_params()

Count the total number of scalars composing the weights.

finalize_state()

Finalizes the layers state after updating layer weights.

from_config(config)

Creates a layer from its config.

get_build_config()

get_config()

get_distribution_probs()

Tries to approximate the log uniform (zipfian) distribution used by tf.random.log_uniform_candidate_sampler (https://www.tensorflow.org/api_docs/python/tf/random/log_uniform_candidate_sampler)

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_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_weights()

Returns the current weights of the layer, as NumPy arrays.

sample(item_weights)

set_max_num_samples(value)

set_weights(weights)

Sets the weights of the layer, from NumPy arrays.

with_name_scope(method)

Decorator to automatically enter the module name scope.

Attributes

activity_regularizer

Optional regularizer function for the output of this layer.

compute_dtype

The dtype of the layer’s computations.

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.

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.

losses

List of losses added using the add_loss() API.

max_num_samples

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.

required_features

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.

add(embeddings: tensorflow.python.framework.ops.Tensor, items_metadata: Dict[str, tensorflow.python.framework.ops.Tensor], training=True)[source]
call(inputs: Dict[str, tensorflow.python.framework.ops.Tensor], item_weights: tensorflow.python.framework.ops.Tensor, training=True)merlin.models.tf.core.base.EmbeddingWithMetadata[source]
sample(item_weights)merlin.models.tf.core.base.EmbeddingWithMetadata[source]
get_distribution_probs()[source]

Tries to approximate the log uniform (zipfian) distribution used by tf.random.log_uniform_candidate_sampler (https://www.tensorflow.org/api_docs/python/tf/random/log_uniform_candidate_sampler)

Returns

A tensor with the expected probability distribution of item ids assuming log-uniform (zipfian) distribution

Return type

tf.Tensor

get_config()[source]