Source code for deepctr.models.xdeepfm

# -*- coding:utf-8 -*-
    Weichen Shen,

    [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.(
from tensorflow.python.keras.models import Model
from tensorflow.python.keras.layers import Dense

from ..feature_column import build_input_features, get_linear_logit, input_from_feature_columns
from ..layers.core import PredictionLayer, DNN
from ..layers.interaction import CIN
from ..layers.utils import concat_func, add_func, combined_dnn_input

[docs]def xDeepFM(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'): """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 :return: A Keras model instance. """ features = build_input_features( linear_feature_columns + dnn_feature_columns) inputs_list = list(features.values()) linear_logit = get_linear_logit(features, linear_feature_columns, seed=seed, prefix='linear', l2_reg=l2_reg_linear) sparse_embedding_list, dense_value_list = input_from_feature_columns(features, dnn_feature_columns, l2_reg_embedding, seed) 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) dnn_logit = Dense(1, use_bias=False)(dnn_output) final_logit = add_func([linear_logit, 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) exFM_logit = Dense(1, use_bias=False)(exFM_out) final_logit = add_func([final_logit, exFM_logit]) output = PredictionLayer(task)(final_logit) model = Model(inputs=inputs_list, outputs=output) return model