深度推荐模型——PNN [TOIS 16][交大]

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


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)
    cate_num = val_x[0].shape[0]
    sub_emb_arr = []
    product_list = []

    inputs = keras.Input((cate_num,))
    emb = keras.layers.Embedding(FEAT_CATE_NUM, VEC_DIM, input_length=cate_num)(inputs)
    liner = keras.layers.Flatten()(emb)

    # 将emb切分成各个field的小emb
    split_arr = tf.split(emb, cate_num, 1)
    for split in split_arr:
        sub_emb_arr.append(keras.layers.Flatten()(split))

    # 内积
    for i in range(0, len(sub_emb_arr)):
        for j in range(i + 1, len(sub_emb_arr)):
            product_list.append(keras.layers.Dot(axes=1)([sub_emb_arr[i], sub_emb_arr[j]]))

    dense = keras.layers.concatenate(product_list + [liner])
    dense = keras.layers.Dropout(DROPOUT_RATE)(dense)

    for units in DNN_LAYERS:
        dense = keras.layers.Dense(units, activation='relu')(dense)
        dense = keras.layers.Dropout(DROPOUT_RATE)(dense)
    outputs = keras.layers.Dense(1, activation='sigmoid')(dense)

    model = keras.Model(inputs=inputs, outputs=outputs)
    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()