Source code for deepctr.estimator.models.afm

# -*- coding:utf-8 -*-

    Weichen Shen,

    [1] Xiao J, Ye H, He X, et al. Attentional factorization machines: Learning the weight of feature interactions via attention networks[J]. arXiv preprint arXiv:1708.04617, 2017.

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.interaction import AFMLayer, FM
from ...layers.utils import concat_func

[docs]def AFMEstimator(linear_feature_columns, dnn_feature_columns, use_attention=True, attention_factor=8, l2_reg_linear=1e-5, l2_reg_embedding=1e-5, l2_reg_att=1e-5, afm_dropout=0, seed=1024, task='binary', model_dir=None, config=None, linear_optimizer='Ftrl', dnn_optimizer='Adagrad', training_chief_hooks=None): """Instantiates the Attentional Factorization Machine 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 use_attention: bool,whether use attention or not,if set to ``False``.it is the same as **standard Factorization Machine** :param attention_factor: positive integer,units in attention net :param l2_reg_linear: float. L2 regularizer strength applied to linear part :param l2_reg_embedding: float. L2 regularizer strength applied to embedding vector :param l2_reg_att: float. L2 regularizer strength applied to attention net :param afm_dropout: float in [0,1), Fraction of the attention net output units to dropout. :param seed: integer ,to use as random seed. :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) with variable_scope(DNN_SCOPE_NAME): sparse_embedding_list, _ = input_from_feature_columns(features, dnn_feature_columns, l2_reg_embedding=l2_reg_embedding) if use_attention: fm_logit = AFMLayer(attention_factor, l2_reg_att, afm_dropout, seed)(sparse_embedding_list, training=train_flag) else: fm_logit = FM()(concat_func(sparse_embedding_list, axis=1)) logits = linear_logits + fm_logit 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)