Source code for deepctr.estimator.models.xdeepfm

# -*- 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)