# -*- coding:utf-8 -*-
"""
Author:
Weichen Shen, weichenswc@163.com
Reference:
[1] 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)
"""
import tensorflow as tf
from ..feature_column import get_linear_logit, input_from_feature_columns
from ..utils import deepctr_model_fn, DNN_SCOPE_NAME, variable_scope
from ...layers.core import DNN
from ...layers.interaction import CIN
from ...layers.utils import concat_func, add_func, combined_dnn_input
[docs]def xDeepFMEstimator(linear_feature_columns, dnn_feature_columns, dnn_hidden_units=(256, 128, 64),
cin_layer_size=(128, 128,), cin_split_half=True, cin_activation='relu', l2_reg_linear=0.00001,
l2_reg_embedding=0.00001, l2_reg_dnn=0, l2_reg_cin=0, seed=1024, dnn_dropout=0,
dnn_activation='relu', dnn_use_bn=False, task='binary', model_dir=None, config=None,
linear_optimizer='Ftrl',
dnn_optimizer='Adagrad', training_chief_hooks=None):
"""Instantiates the xDeepFM architecture.
:param linear_feature_columns: An iterable containing all the features used by linear part of the model.
:param dnn_feature_columns: An iterable containing all the features used by deep part of the model.
:param dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of deep net
:param cin_layer_size: list,list of positive integer or empty list, the feature maps in each hidden layer of Compressed Interaction Network
:param cin_split_half: bool.if set to True, half of the feature maps in each hidden will connect to output unit
:param cin_activation: activation function used on feature maps
:param l2_reg_linear: float. L2 regularizer strength applied to linear part
:param l2_reg_embedding: L2 regularizer strength applied to embedding vector
:param l2_reg_dnn: L2 regularizer strength applied to deep net
:param l2_reg_cin: L2 regularizer strength applied to CIN.
:param seed: integer ,to use as random seed.
:param dnn_dropout: float in [0,1), the probability we will drop out a given DNN coordinate.
:param dnn_activation: Activation function to use in DNN
:param dnn_use_bn: bool. Whether use BatchNormalization before activation or not in DNN
:param task: str, ``"binary"`` for binary logloss or ``"regression"`` for regression loss
:param model_dir: Directory to save model parameters, graph and etc. This can
also be used to load checkpoints from the directory into a estimator
to continue training a previously saved model.
:param config: tf.RunConfig object to configure the runtime settings.
:param linear_optimizer: An instance of `tf.Optimizer` used to apply gradients to
the linear part of the model. Defaults to FTRL optimizer.
:param dnn_optimizer: An instance of `tf.Optimizer` used to apply gradients to
the deep part of the model. Defaults to Adagrad optimizer.
:param training_chief_hooks: Iterable of `tf.train.SessionRunHook` objects to
run on the chief worker during training.
:return: A Tensorflow Estimator instance.
"""
def _model_fn(features, labels, mode, config):
train_flag = (mode == tf.estimator.ModeKeys.TRAIN)
linear_logits = get_linear_logit(features, linear_feature_columns, l2_reg_linear=l2_reg_linear)
logits_list = [linear_logits]
with variable_scope(DNN_SCOPE_NAME):
sparse_embedding_list, dense_value_list = input_from_feature_columns(features, dnn_feature_columns,
l2_reg_embedding=l2_reg_embedding)
fm_input = concat_func(sparse_embedding_list, axis=1)
dnn_input = combined_dnn_input(sparse_embedding_list, dense_value_list)
dnn_output = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn, dnn_dropout, dnn_use_bn, seed=seed)(dnn_input, training=train_flag)
dnn_logit = tf.keras.layers.Dense(
1, use_bias=False, kernel_initializer=tf.keras.initializers.glorot_normal(seed))(dnn_output)
logits_list.append(dnn_logit)
if len(cin_layer_size) > 0:
exFM_out = CIN(cin_layer_size, cin_activation,
cin_split_half, l2_reg_cin, seed)(fm_input, training=train_flag)
exFM_logit = tf.keras.layers.Dense(1, kernel_initializer=tf.keras.initializers.glorot_normal(seed) )(exFM_out)
logits_list.append(exFM_logit)
logits = add_func(logits_list)
return deepctr_model_fn(features, mode, logits, labels, task, linear_optimizer, dnn_optimizer,
training_chief_hooks=training_chief_hooks)
return tf.estimator.Estimator(_model_fn, model_dir=model_dir, config=config)