深度推荐模型——NFM [SIGIR 17][新加坡国立大学]

import tensorflow as tf
from tensorflow import keras
from utils import *

EPOCH = 10
BATCH_SIZE = 32
VEC_DIM = 10
DNN_LAYERS = [64, 128, 64]
DROPOUT_RATE = 0.5

base, test = loadData()
# 所有的特征各个类别值个数之和
FEAT_CATE_NUM = base.shape[1] - 1
K = tf.keras.backend


class BiInteractionLayer(keras.layers.Layer):
    def __init__(self, **kwargs):
        super(BiInteractionLayer, self).__init__(**kwargs)

    def build(self, input_shape):
        super(BiInteractionLayer, self).build(input_shape)

    def call(self, Input, **kwargs):
        sum_square_part = tf.square(tf.reduce_sum(Input, axis=1))  # (batch, K)
        square_sum_part = tf.reduce_sum(tf.square(Input), axis=1)  # (batch, K)
        return 0.5 * (sum_square_part - square_sum_part)

def run():
    # 将所有的特征的各个类别值统一id化。x中每行为各特征的类别值的id
    val_x, val_y = getAllData(test)
    train_x, train_y = getAllData(base)

    model = keras.models.Sequential()
    model.add(keras.layers.Embedding(FEAT_CATE_NUM, VEC_DIM, input_length=val_x[0].shape[0]))
    model.add(BiInteractionLayer())
    model.add(keras.layers.BatchNormalization())
    model.add(keras.layers.Dropout(rate=DROPOUT_RATE))
    for units in DNN_LAYERS:
        model.add(keras.layers.Dense(units, activation='relu'))
        model.add(keras.layers.Dropout(DROPOUT_RATE))
    model.add(keras.layers.Dense(1, activation='sigmoid'))

    model.compile(loss='binary_crossentropy', optimizer=tf.train.AdamOptimizer(0.001), metrics=[keras.metrics.AUC()])
    tbCallBack = keras.callbacks.TensorBoard(log_dir='./logs',
                                             histogram_freq=0,
                                             write_graph=True,
                                             write_grads=True,
                                             write_images=True,
                                             embeddings_freq=0,
                                             embeddings_layer_names=None,
                                             embeddings_metadata=None)

    model.fit(train_x, train_y, batch_size=BATCH_SIZE, epochs=EPOCH, verbose=2, validation_data=(val_x, val_y),
              callbacks=[tbCallBack])


run()