def xDeepFM_MTL(
feature_dim_dict,
embedding_size=8,
hidden_size=(256, 256),
cin_layer_size=(
256,
256,
),
cin_split_half=True,
task_net_size=(128, ),
l2_reg_linear=0.00001,
l2_reg_embedding=0.00001,
seed=1024,
):
check_feature_config_dict(feature_dim_dict)
if len(task_net_size) < 1:
raise ValueError('task_net_size must be at least one layer')
print("[xdeepfm] feature_dim_dict: {}".format(feature_dim_dict))
deep_emb_list, linear_logit, inputs_list = preprocess_input_embedding(
feature_dim_dict, embedding_size, l2_reg_embedding, l2_reg_linear,
0.0001, seed)
print("[xdeepfm] deep_emb_list:", deep_emb_list)
print("[xdeepfm] linear_logit:", linear_logit)
print("[xdeepfm] inputs_list:", inputs_list)
# video_input = tf.keras.layers.Input((128,))
# inputs_list.append(video_input)
fm_input = concat_fun(deep_emb_list, axis=1)
if len(cin_layer_size) > 0:
exFM_out = CIN(cin_layer_size, 'relu', cin_split_half, seed)(fm_input)
exFM_logit = tf.keras.layers.Dense(
1,
activation=None,
)(exFM_out)
deep_input = tf.keras.layers.Flatten()(fm_input)
deep_out = MLP(hidden_size)(deep_input)
finish_out = MLP(task_net_size)(deep_out)
finish_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(finish_out)
like_out = MLP(task_net_size)(deep_out)
like_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(like_out)
finish_logit = tf.keras.layers.add(
[linear_logit, finish_logit, exFM_logit])
like_logit = tf.keras.layers.add([linear_logit, like_logit, exFM_logit])
output_finish = PredictionLayer('sigmoid', name='finish')(finish_logit)
output_like = PredictionLayer('sigmoid', name='like')(like_logit)
model = tf.keras.models.Model(inputs=inputs_list,
outputs=[output_finish, output_like])
return model
def myAutoInt(
feature_dim_dict,
embedding_size=8,
att_layer_num=3,
att_embedding_size=8,
att_head_num=4,
att_res=True,
hidden_size=(256, 256),
activation='relu',
l2_reg_deep=0,
l2_reg_embedding=1e-5,
use_bn=False,
keep_prob=1.0,
init_std=0.0001,
seed=1024,
final_activation='sigmoid',
):
if len(hidden_size) <= 0 and att_layer_num <= 0:
raise ValueError("Either hidden_layer or att_layer_num must > 0")
check_feature_config_dict(feature_dim_dict)
deep_emb_list, _, inputs_list = preprocess_input_embedding(
feature_dim_dict, embedding_size, l2_reg_embedding, 0, init_std, seed,
False)
att_input = concat_fun(deep_emb_list, axis=1)
for _ in range(att_layer_num):
att_input = InteractingLayer(att_embedding_size, att_head_num,
att_res)(att_input)
att_output = tf.keras.layers.Flatten()(att_input)
deep_input = tf.keras.layers.Flatten()(concat_fun(deep_emb_list))
deep_out = MLP(hidden_size, activation, l2_reg_deep, keep_prob, use_bn,
seed)(deep_input)
finish_out = tf.keras.layers.Concatenate()([att_output, deep_out])
finish_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(finish_out)
like_out = tf.keras.layers.Concatenate()([att_output, deep_out])
like_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(like_out)
output_finish = PredictionLayer(final_activation,
name='finish')(finish_logit)
output_like = PredictionLayer(final_activation, name='like')(like_logit)
model = tf.keras.models.Model(inputs=inputs_list,
outputs=[output_finish, output_like])
return model
def MTL_with_Title(
feature_dim_dict,
embedding_size=8,
hidden_size=(256, 256),
cin_layer_size=(
256,
256,
),
cin_split_half=True,
task_net_size=(128, ),
l2_reg_linear=0.00001,
l2_reg_embedding=0.00001,
seed=1024,
):
check_feature_config_dict(feature_dim_dict)
if len(task_net_size) < 1:
raise ValueError('task_net_size must be at least one layer')
# xDeepFM Model
deep_emb_list, linear_logit, inputs_list = preprocess_input_embedding(
feature_dim_dict, embedding_size, l2_reg_embedding, l2_reg_linear,
0.0001, seed)
fm_input = concat_fun(deep_emb_list, axis=1)
if len(cin_layer_size) > 0:
exFM_out = CIN(cin_layer_size, 'relu', cin_split_half, seed)(fm_input)
exFM_logit = tf.keras.layers.Dense(
1,
activation=None,
)(exFM_out)
deep_input = tf.keras.layers.Flatten()(fm_input)
deep_out = MLP(hidden_size)(deep_input)
finish_out = MLP(task_net_size)(deep_out)
finish_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(finish_out)
like_out = MLP(task_net_size)(deep_out)
like_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(like_out)
# Add Title Features
title_input = Input(shape=(35, ), dtype='int32', name='title_input')
title_embedding = Embedding(output_dim=32,
input_dim=134545,
input_length=35)(title_input)
lstm_out = LSTM(units=32, return_sequences=True)(title_embedding)
avg_out = GlobalAveragePooling1D()(lstm_out)
dense1 = Dense(32, activation='relu')(avg_out)
dense2 = Dense(1, activation='relu')(dense1)
#
finish_logit = tf.keras.layers.add(
[linear_logit, finish_logit, exFM_logit, dense2])
like_logit = tf.keras.layers.add(
[linear_logit, like_logit, exFM_logit, dense2])
output_finish = PredictionLayer('sigmoid', name='finish')(finish_logit)
output_like = PredictionLayer('sigmoid', name='like')(like_logit)
print(str(inputs_list))
inputs_list.append(title_input)
model = tf.keras.models.Model(inputs=inputs_list,
outputs=[output_finish, output_like])
return model
def xDeepFM_MTL(
feature_dim_dict,
embedding_size=8,
hidden_size=(256, 256),
cin_layer_size=(
256,
256,
),
cin_split_half=True,
task_net_size=(128, ),
l2_reg_linear=0.000001,
l2_reg_embedding=0.000001,
seed=1024,
):
check_feature_config_dict(feature_dim_dict) # 未知
if len(task_net_size) < 1:
raise ValueError('task_net_size must be at least one layer')
deep_emb_list, linear_logit, inputs_list = preprocess_input_embedding(
feature_dim_dict, embedding_size, l2_reg_embedding, l2_reg_linear,
0.0001, seed)
# video_input = tf.keras.layers.Input((128,))
# inputs_list.append(video_input)
fm_input = concat_fun(deep_emb_list, axis=1) # 模型输入
'''
构建CIN，默认CIN的size为[256,256]，激活函数为relu，输入为
(batch_size,field_size,embedding_size)，输出为(batch_size,feature_num)。
如果split_half为True，那么隐藏层的feature map只有一半的会连接到输出单元。
'''
if len(cin_layer_size) > 0:
exFM_out = CIN(cin_layer_size, 'relu', cin_split_half, seed)(fm_input)
exFM_logit = tf.keras.layers.Dense(
1,
activation=None,
)(exFM_out) # 全连接输出到Output_unit
'''
Flatten将输入除了batch的维度，其他维度拉直，得到的输出为(batch_size, sum_size)
将embedding特征直接输入MLP
'''
deep_input = tf.keras.layers.Flatten()(fm_input)
deep_out = MLP(hidden_size)(deep_input)
'''
将deep_out过一个MLP，并全连接到finish的logits输出，同样的操作应用于like的logits输出
'''
finish_out = MLP(task_net_size)(deep_out)
finish_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(finish_out)
like_out = MLP(task_net_size)(deep_out)
like_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(like_out)
'''
最终的finish的logit由linear_logit,finish_logit\like_logit和exFM_logit三者叠加。
'''
finish_logit = tf.keras.layers.add(
[linear_logit, finish_logit, exFM_logit])
like_logit = tf.keras.layers.add([linear_logit, like_logit, exFM_logit])
'''
将logit通过sigmoid转化为概率，通过输入和输出构建model
'''
output_finish = PredictionLayer('sigmoid', name='finish')(finish_logit)
output_like = PredictionLayer('sigmoid', name='like')(like_logit)
model = tf.keras.models.Model(inputs=inputs_list,
outputs=[output_finish, output_like])
return model
def xDeepFM_MTL(feature_dim_dict, embedding_size=8, hidden_size=(256, 256), cin_layer_size=(256, 256,),
cin_split_half=True,
task_net_size=(128,), l2_reg_linear=0.00001, l2_reg_embedding=0.00001,
seed=1024, ):
"""
:param feature_dim_dict: 特征词典，包括特征名和特征列表
:param embedding_size:
:param hidden_size:
:param cin_layer_size:
:param cin_split_half:
:param task_net_size: 网络层数
:param l2_reg_linear:
:param l2_reg_embedding:
:param seed:
:return:
"""
# 判断sparse 和dense feature结构是否正确
check_feature_config_dict(feature_dim_dict)
if len(task_net_size) < 1:
raise ValueError('task_net_size must be at least one layer')
# Todo, add text sequence embedding
deep_emb_list, linear_logit, inputs_list = preprocess_input_embedding(
feature_dim_dict, embedding_size, l2_reg_embedding, l2_reg_linear, 0.0001, seed)
# video_input = tf.keras.layers.Input((128,))
# inputs_list.append(video_input)
# TODO, add other feature
if 'txt' in feature_dim_dict:
# txt_input = OrderedDict()
for i, feat in enumerate(feature_dim_dict["txt"]):
txt_input = tf.keras.layers.Input(
shape=(feat.dimension,), name='txt_' + str(i) + '-' + feat.name)
inputs_list.append(txt_input)
fm_input = concat_fun(deep_emb_list, axis=1)
if len(cin_layer_size) > 0:
exFM_out = CIN(cin_layer_size, 'relu',
cin_split_half, seed)(fm_input)
exFM_logit = tf.keras.layers.Dense(1, activation=None, )(exFM_out)
deep_input = tf.keras.layers.Flatten()(fm_input)
deep_out = MLP(hidden_size)(deep_input)
finish_out = MLP(task_net_size)(deep_out)
finish_logit = tf.keras.layers.Dense(
1, use_bias=False, activation=None)(finish_out)
like_out = MLP(task_net_size)(deep_out)
like_logit = tf.keras.layers.Dense(
1, use_bias=False, activation=None)(like_out)
finish_logit = tf.keras.layers.add(
[linear_logit, finish_logit, exFM_logit])
like_logit = tf.keras.layers.add(
[linear_logit, like_logit, exFM_logit])
output_finish = PredictionLayer('sigmoid', name='finish')(finish_logit)
output_like = PredictionLayer('sigmoid', name='like')(like_logit)
model = tf.keras.models.Model(inputs=inputs_list, outputs=[
output_finish, output_like])
return model
def xDeepFM(feature_dim_dict,
embedding_size=8,
seed=1024,
init_std=0.0001,
l2_reg_linear=0.00001,
l2_reg_embedding=0.00001,
cin_layer_size=(256, 256),
cin_split_half=True,
cin_activation='relu',
hidden_size=(256, 256),
activation='relu',
keep_prob=1,
use_bn=False,
l2_reg_deep=0,
final_activation='sigmoid',
use_video=False,
use_audio=False):
check_feature_config_dict(feature_dim_dict)
deep_emb_list, linear_logit, inputs_list = preprocess_input_embedding(
feature_dim_dict, embedding_size, l2_reg_embedding, l2_reg_linear,
init_std, seed, True)
if use_video:
video_input = tf.keras.layers.Input(shape=(128, ), name='video')
video_emb = tf.keras.layers.Dense(
embedding_size,
use_bias=False,
kernel_regularizer=l2(l2_reg_embedding))(video_input)
video_emb = tf.keras.layers.Reshape(
(1, embedding_size), input_shape=(embedding_size, ))(video_emb)
deep_emb_list.append(video_emb)
inputs_list.append(video_input)
if use_audio:
audio_input = tf.keras.layers.Input(shape=(128, ), name='audio')
audio_emb = tf.keras.layers.Dense(
embedding_size,
use_bias=False,
kernel_regularizer=l2(l2_reg_embedding))(audio_input)
audio_emb = tf.keras.layers.Reshape(
(1, embedding_size), input_shape=(embedding_size, ))(audio_emb)
deep_emb_list.append(audio_emb)
inputs_list.append(audio_input)
fm_input = concat_fun(deep_emb_list, axis=1)
if len(cin_layer_size) > 0:
exFM_out = CIN(cin_layer_size, cin_activation, cin_split_half,
seed)(fm_input)
exFM_logit = tf.keras.layers.Dense(
1,
activation=None,
)(exFM_out)
deep_input = tf.keras.layers.Flatten()(fm_input)
deep_out = MLP(hidden_size, activation, l2_reg_deep, keep_prob, use_bn,
seed)(deep_input)
deep_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(deep_out)
final_logit = tf.keras.layers.add([linear_logit, deep_logit, exFM_logit])
output = PredictionLayer(final_activation, name='output')(final_logit)
model = tf.keras.models.Model(inputs=inputs_list, outputs=output)
return model
