deepctr.layers.interaction module

Author:
Weichen Shen,wcshen1994@163.com
class deepctr.layers.interaction.AFMLayer(attention_factor=4, l2_reg_w=0, dropout_rate=0, seed=1024, **kwargs)[source]

Attentonal Factorization Machine models pairwise (order-2) feature interactions without linear term and bias.

Input shape
  • A list of 3D tensor with shape: (batch_size,1,embedding_size).
Output shape
  • 2D tensor with shape: (batch_size, 1).
Arguments
  • attention_factor : Positive integer, dimensionality of the
attention network output space.
  • l2_reg_w : float between 0 and 1. L2 regularizer strength
applied to attention network.
  • dropout_rate : float between in [0,1). Fraction of the attention net output units to dropout.
  • seed : A Python integer to use as random seed.
References
  • [Attentional Factorization Machines : Learning the Weight of Feature

Interactions via Attention Networks](https://arxiv.org/pdf/1708.04617.pdf)

build(input_shape)[source]

Creates the variables of the layer.

call(inputs, training=None, **kwargs)[source]

This is where the layer’s logic lives.

Arguments:
inputs: Input tensor, or list/tuple of input tensors. **kwargs: Additional keyword arguments.
Returns:
A tensor or list/tuple of tensors.
compute_output_shape(input_shape)[source]

Computes the output shape of the layer.

Assumes that the layer will be built to match that input shape provided.

Arguments:
input_shape: Shape tuple (tuple of integers)
or list of shape tuples (one per output tensor of the layer). Shape tuples can include None for free dimensions, instead of an integer.
Returns:
An input shape tuple.
get_config()[source]

Returns the config of the layer.

A layer config is a Python dictionary (serializable) containing the configuration of a layer. The same layer can be reinstantiated later (without its trained weights) from this configuration.

The config of a layer does not include connectivity information, nor the layer class name. These are handled by Network (one layer of abstraction above).

Returns:
Python dictionary.
class deepctr.layers.interaction.BiInteractionPooling(**kwargs)[source]

Bi-Interaction Layer used in Neural FM,compress the pairwise element-wise product of features into one single vector.

Input shape
  • A 3D tensor with shape:(batch_size,field_size,embedding_size).
Output shape
  • 3D tensor with shape: (batch_size,1,embedding_size).
References
  • [He X, Chua T S. Neural factorization machines for sparse predictive analytics[C]//Proceedings of the 40th International ACM SIGIR conference on Research and Development in Information Retrieval. ACM, 2017: 355-364.](http://arxiv.org/abs/1708.05027)
build(input_shape)[source]

Creates the variables of the layer.

call(inputs, **kwargs)[source]

This is where the layer’s logic lives.

Arguments:
inputs: Input tensor, or list/tuple of input tensors. **kwargs: Additional keyword arguments.
Returns:
A tensor or list/tuple of tensors.
compute_output_shape(input_shape)[source]

Computes the output shape of the layer.

Assumes that the layer will be built to match that input shape provided.

Arguments:
input_shape: Shape tuple (tuple of integers)
or list of shape tuples (one per output tensor of the layer). Shape tuples can include None for free dimensions, instead of an integer.
Returns:
An input shape tuple.
class deepctr.layers.interaction.BilinearInteraction(bilinear_type='interaction', seed=1024, **kwargs)[source]

BilinearInteraction Layer used in FiBiNET.

Input shape
  • A list of 3D tensor with shape: (batch_size,1,embedding_size).
Output shape
  • 3D tensor with shape: (batch_size,1,embedding_size).
Arguments
  • str : String, types of bilinear functions used in this layer.
  • seed : A Python integer to use as random seed.
References
  • [FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction

Tongwen](https://arxiv.org/pdf/1905.09433.pdf)

build(input_shape)[source]

Creates the variables of the layer.

call(inputs, **kwargs)[source]

This is where the layer’s logic lives.

Arguments:
inputs: Input tensor, or list/tuple of input tensors. **kwargs: Additional keyword arguments.
Returns:
A tensor or list/tuple of tensors.
compute_output_shape(input_shape)[source]

Computes the output shape of the layer.

Assumes that the layer will be built to match that input shape provided.

Arguments:
input_shape: Shape tuple (tuple of integers)
or list of shape tuples (one per output tensor of the layer). Shape tuples can include None for free dimensions, instead of an integer.
Returns:
An input shape tuple.
get_config()[source]

Returns the config of the layer.

A layer config is a Python dictionary (serializable) containing the configuration of a layer. The same layer can be reinstantiated later (without its trained weights) from this configuration.

The config of a layer does not include connectivity information, nor the layer class name. These are handled by Network (one layer of abstraction above).

Returns:
Python dictionary.
class deepctr.layers.interaction.CIN(layer_size=(128, 128), activation='relu', split_half=True, l2_reg=1e-05, seed=1024, **kwargs)[source]

Compressed Interaction Network used in xDeepFM.This implemention is adapted from code that the author of the paper published on https://github.com/Leavingseason/xDeepFM.

Input shape
  • 3D tensor with shape: (batch_size,field_size,embedding_size).
Output shape
  • 2D tensor with shape: (batch_size, featuremap_num) featuremap_num =  sum(self.layer_size[:-1]) // 2 + self.layer_size[-1] if split_half=True,else sum(layer_size) .
Arguments
  • layer_size : list of int.Feature maps in each layer.
  • activation : activation function used on feature maps.
  • split_half : bool.if set to False, half of the feature maps in each hidden will connect to output unit.
  • seed : A Python integer to use as random seed.
References
  • [Lian J, Zhou X, Zhang F, et al. xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems[J]. arXiv preprint arXiv:1803.05170, 2018.] (https://arxiv.org/pdf/1803.05170.pdf)
build(input_shape)[source]

Creates the variables of the layer.

call(inputs, **kwargs)[source]

This is where the layer’s logic lives.

Arguments:
inputs: Input tensor, or list/tuple of input tensors. **kwargs: Additional keyword arguments.
Returns:
A tensor or list/tuple of tensors.
compute_output_shape(input_shape)[source]

Computes the output shape of the layer.

Assumes that the layer will be built to match that input shape provided.

Arguments:
input_shape: Shape tuple (tuple of integers)
or list of shape tuples (one per output tensor of the layer). Shape tuples can include None for free dimensions, instead of an integer.
Returns:
An input shape tuple.
get_config()[source]

Returns the config of the layer.

A layer config is a Python dictionary (serializable) containing the configuration of a layer. The same layer can be reinstantiated later (without its trained weights) from this configuration.

The config of a layer does not include connectivity information, nor the layer class name. These are handled by Network (one layer of abstraction above).

Returns:
Python dictionary.
class deepctr.layers.interaction.CrossNet(layer_num=2, l2_reg=0, seed=1024, **kwargs)[source]

The Cross Network part of Deep&Cross Network model, which leans both low and high degree cross feature.

Input shape
  • 2D tensor with shape: (batch_size, units).
Output shape
  • 2D tensor with shape: (batch_size, units).
Arguments
  • layer_num: Positive integer, the cross layer number
  • l2_reg: float between 0 and 1. L2 regularizer strength applied to the kernel weights matrix
  • seed: A Python integer to use as random seed.
References
  • [Wang R, Fu B, Fu G, et al. Deep & cross network for ad click predictions[C]//Proceedings of the ADKDD‘17. ACM, 2017: 12.](https://arxiv.org/abs/1708.05123)
build(input_shape)[source]

Creates the variables of the layer.

call(inputs, **kwargs)[source]

This is where the layer’s logic lives.

Arguments:
inputs: Input tensor, or list/tuple of input tensors. **kwargs: Additional keyword arguments.
Returns:
A tensor or list/tuple of tensors.
compute_output_shape(input_shape)[source]

Computes the output shape of the layer.

Assumes that the layer will be built to match that input shape provided.

Arguments:
input_shape: Shape tuple (tuple of integers)
or list of shape tuples (one per output tensor of the layer). Shape tuples can include None for free dimensions, instead of an integer.
Returns:
An input shape tuple.
get_config()[source]

Returns the config of the layer.

A layer config is a Python dictionary (serializable) containing the configuration of a layer. The same layer can be reinstantiated later (without its trained weights) from this configuration.

The config of a layer does not include connectivity information, nor the layer class name. These are handled by Network (one layer of abstraction above).

Returns:
Python dictionary.
class deepctr.layers.interaction.FGCNNLayer(filters=(14, 16), kernel_width=(7, 7), new_maps=(3, 3), pooling_width=(2, 2), **kwargs)[source]

Feature Generation Layer used in FGCNN,including Convolution,MaxPooling and Recombination.

Input shape
  • A 3D tensor with shape:(batch_size,field_size,embedding_size).
Output shape
  • 3D tensor with shape: (batch_size,new_feture_num,embedding_size).
References
  • [Liu B, Tang R, Chen Y, et al. Feature Generation by Convolutional Neural Network for Click-Through Rate Prediction[J]. arXiv preprint arXiv:1904.04447, 2019.](https://arxiv.org/pdf/1904.04447)
build(input_shape)[source]

Creates the variables of the layer.

call(inputs, **kwargs)[source]

This is where the layer’s logic lives.

Arguments:
inputs: Input tensor, or list/tuple of input tensors. **kwargs: Additional keyword arguments.
Returns:
A tensor or list/tuple of tensors.
compute_output_shape(input_shape)[source]

Computes the output shape of the layer.

Assumes that the layer will be built to match that input shape provided.

Arguments:
input_shape: Shape tuple (tuple of integers)
or list of shape tuples (one per output tensor of the layer). Shape tuples can include None for free dimensions, instead of an integer.
Returns:
An input shape tuple.
get_config()[source]

Returns the config of the layer.

A layer config is a Python dictionary (serializable) containing the configuration of a layer. The same layer can be reinstantiated later (without its trained weights) from this configuration.

The config of a layer does not include connectivity information, nor the layer class name. These are handled by Network (one layer of abstraction above).

Returns:
Python dictionary.
class deepctr.layers.interaction.FM(**kwargs)[source]

Factorization Machine models pairwise (order-2) feature interactions without linear term and bias.

Input shape
  • 3D tensor with shape: (batch_size,field_size,embedding_size).
Output shape
  • 2D tensor with shape: (batch_size, 1).
References
build(input_shape)[source]

Creates the variables of the layer.

call(inputs, **kwargs)[source]

This is where the layer’s logic lives.

Arguments:
inputs: Input tensor, or list/tuple of input tensors. **kwargs: Additional keyword arguments.
Returns:
A tensor or list/tuple of tensors.
compute_output_shape(input_shape)[source]

Computes the output shape of the layer.

Assumes that the layer will be built to match that input shape provided.

Arguments:
input_shape: Shape tuple (tuple of integers)
or list of shape tuples (one per output tensor of the layer). Shape tuples can include None for free dimensions, instead of an integer.
Returns:
An input shape tuple.
class deepctr.layers.interaction.InnerProductLayer(reduce_sum=True, **kwargs)[source]

InnerProduct Layer used in PNN that compute the element-wise product or inner product between feature vectors.

Input shape
  • a list of 3D tensor with shape: (batch_size,1,embedding_size).
Output shape
  • 3D tensor with shape: (batch_size, N*(N-1)/2 ,1) if use reduce_sum. or 3D tensor with shape: (batch_size, N*(N-1)/2, embedding_size ) if not use reduce_sum.
Arguments
  • reduce_sum: bool. Whether return inner product or element-wise product
References
  • [Qu Y, Cai H, Ren K, et al. Product-based neural networks for user response prediction[C]//Data Mining (ICDM), 2016 IEEE 16th International Conference on. IEEE, 2016: 1149-1154.](https://arxiv.org/pdf/1611.00144.pdf)
build(input_shape)[source]

Creates the variables of the layer.

call(inputs, **kwargs)[source]

This is where the layer’s logic lives.

Arguments:
inputs: Input tensor, or list/tuple of input tensors. **kwargs: Additional keyword arguments.
Returns:
A tensor or list/tuple of tensors.
compute_output_shape(input_shape)[source]

Computes the output shape of the layer.

Assumes that the layer will be built to match that input shape provided.

Arguments:
input_shape: Shape tuple (tuple of integers)
or list of shape tuples (one per output tensor of the layer). Shape tuples can include None for free dimensions, instead of an integer.
Returns:
An input shape tuple.
get_config()[source]

Returns the config of the layer.

A layer config is a Python dictionary (serializable) containing the configuration of a layer. The same layer can be reinstantiated later (without its trained weights) from this configuration.

The config of a layer does not include connectivity information, nor the layer class name. These are handled by Network (one layer of abstraction above).

Returns:
Python dictionary.
class deepctr.layers.interaction.InteractingLayer(att_embedding_size=8, head_num=2, use_res=True, seed=1024, **kwargs)[source]

A Layer used in AutoInt that model the correlations between different feature fields by multi-head self-attention mechanism.

Input shape
  • A 3D tensor with shape: (batch_size,field_size,embedding_size).
Output shape
  • 3D tensor with shape:(batch_size,field_size,att_embedding_size * head_num).
Arguments
  • att_embedding_size: int.The embedding size in multi-head self-attention network.
  • head_num: int.The head number in multi-head self-attention network.
  • use_res: bool.Whether or not use standard residual connections before output.
  • seed: A Python integer to use as random seed.
References
  • [Song W, Shi C, Xiao Z, et al. AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks[J]. arXiv preprint arXiv:1810.11921, 2018.](https://arxiv.org/abs/1810.11921)
build(input_shape)[source]

Creates the variables of the layer.

call(inputs, **kwargs)[source]

This is where the layer’s logic lives.

Arguments:
inputs: Input tensor, or list/tuple of input tensors. **kwargs: Additional keyword arguments.
Returns:
A tensor or list/tuple of tensors.
compute_output_shape(input_shape)[source]

Computes the output shape of the layer.

Assumes that the layer will be built to match that input shape provided.

Arguments:
input_shape: Shape tuple (tuple of integers)
or list of shape tuples (one per output tensor of the layer). Shape tuples can include None for free dimensions, instead of an integer.
Returns:
An input shape tuple.
get_config()[source]

Returns the config of the layer.

A layer config is a Python dictionary (serializable) containing the configuration of a layer. The same layer can be reinstantiated later (without its trained weights) from this configuration.

The config of a layer does not include connectivity information, nor the layer class name. These are handled by Network (one layer of abstraction above).

Returns:
Python dictionary.
class deepctr.layers.interaction.OutterProductLayer(kernel_type='mat', seed=1024, **kwargs)[source]

OutterProduct Layer used in PNN.This implemention is adapted from code that the author of the paper published on https://github.com/Atomu2014/product-nets.

Input shape
  • A list of N 3D tensor with shape: (batch_size,1,embedding_size).
Output shape
  • 2D tensor with shape:(batch_size,N*(N-1)/2 ).
Arguments
  • kernel_type: str. The kernel weight matrix type to use,can be mat,vec or num
  • seed: A Python integer to use as random seed.
References
  • [Qu Y, Cai H, Ren K, et al. Product-based neural networks for user response prediction[C]//Data Mining (ICDM), 2016 IEEE 16th International Conference on. IEEE, 2016: 1149-1154.](https://arxiv.org/pdf/1611.00144.pdf)
build(input_shape)[source]

Creates the variables of the layer.

call(inputs, **kwargs)[source]

This is where the layer’s logic lives.

Arguments:
inputs: Input tensor, or list/tuple of input tensors. **kwargs: Additional keyword arguments.
Returns:
A tensor or list/tuple of tensors.
compute_output_shape(input_shape)[source]

Computes the output shape of the layer.

Assumes that the layer will be built to match that input shape provided.

Arguments:
input_shape: Shape tuple (tuple of integers)
or list of shape tuples (one per output tensor of the layer). Shape tuples can include None for free dimensions, instead of an integer.
Returns:
An input shape tuple.
get_config()[source]

Returns the config of the layer.

A layer config is a Python dictionary (serializable) containing the configuration of a layer. The same layer can be reinstantiated later (without its trained weights) from this configuration.

The config of a layer does not include connectivity information, nor the layer class name. These are handled by Network (one layer of abstraction above).

Returns:
Python dictionary.
class deepctr.layers.interaction.SENETLayer(reduction_ratio=3, seed=1024, **kwargs)[source]

SENETLayer used in FiBiNET.

Input shape
  • A list of 3D tensor with shape: (batch_size,1,embedding_size).
Output shape
  • A list of 3D tensor with shape: (batch_size,1,embedding_size).
Arguments
  • reduction_ratio : Positive integer, dimensionality of the
attention network output space.
  • seed : A Python integer to use as random seed.
References
  • [FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction

Tongwen](https://arxiv.org/pdf/1905.09433.pdf)

build(input_shape)[source]

Creates the variables of the layer.

call(inputs, training=None, **kwargs)[source]

This is where the layer’s logic lives.

Arguments:
inputs: Input tensor, or list/tuple of input tensors. **kwargs: Additional keyword arguments.
Returns:
A tensor or list/tuple of tensors.
compute_mask(inputs, mask=None)[source]

Computes an output mask tensor.

Arguments:
inputs: Tensor or list of tensors. mask: Tensor or list of tensors.
Returns:
None or a tensor (or list of tensors,
one per output tensor of the layer).
compute_output_shape(input_shape)[source]

Computes the output shape of the layer.

Assumes that the layer will be built to match that input shape provided.

Arguments:
input_shape: Shape tuple (tuple of integers)
or list of shape tuples (one per output tensor of the layer). Shape tuples can include None for free dimensions, instead of an integer.
Returns:
An input shape tuple.
get_config()[source]

Returns the config of the layer.

A layer config is a Python dictionary (serializable) containing the configuration of a layer. The same layer can be reinstantiated later (without its trained weights) from this configuration.

The config of a layer does not include connectivity information, nor the layer class name. These are handled by Network (one layer of abstraction above).

Returns:
Python dictionary.