def SDM(user_feature_columns,
item_feature_columns,
history_feature_list,
num_sampled=5,
units=64,
rnn_layers=2,
dropout_rate=0.2,
rnn_num_res=1,
num_head=4,
l2_reg_embedding=1e-6,
dnn_activation='tanh',
init_std=0.0001,
seed=1024):
"""Instantiates the Sequential Deep Matching Model architecture.
:param user_feature_columns: An iterable containing user's features used by the model.
:param item_feature_columns: An iterable containing item's features used by the model.
:param history_feature_list: list,to indicate short and prefer sequence sparse field
:param num_sampled: int, the number of classes to randomly sample per batch.
:param units: int, dimension for each output layer
:param rnn_layers: int, layer number of rnn
:param dropout_rate: float in [0,1), the probability we will drop out a given DNN coordinate.
:param rnn_num_res: int. The number of residual layers in rnn layers
:param num_head: int int, the number of attention head
:param l2_reg_embedding: float. L2 regularizer strength applied to embedding vector
:param dnn_activation: Activation function to use in deep net
:param init_std: float,to use as the initialize std of embedding vector
:param seed: integer ,to use as random seed.
:return: A Keras model instance.
"""
if len(item_feature_columns) > 1:
raise ValueError("Now MIND only support 1 item feature like item_id")
item_feature_column = item_feature_columns[0]
item_feature_name = item_feature_column.name
item_vocabulary_size = item_feature_columns[0].vocabulary_size
features = build_input_features(user_feature_columns)
user_inputs_list = list(features.values())
sparse_feature_columns = list(
filter(lambda x: isinstance(x, SparseFeat),
user_feature_columns)) if user_feature_columns else []
dense_feature_columns = list(
filter(lambda x: isinstance(x, DenseFeat),
user_feature_columns)) if user_feature_columns else []
if len(dense_feature_columns) != 0:
raise ValueError("Now SDM don't support dense feature")
varlen_sparse_feature_columns = list(
filter(lambda x: isinstance(x, VarLenSparseFeat),
user_feature_columns)) if user_feature_columns else []
sparse_varlen_feature_columns = []
prefer_history_columns = []
short_history_columns = []
prefer_fc_names = list(map(lambda x: "prefer_" + x, history_feature_list))
short_fc_names = list(map(lambda x: "short_" + x, history_feature_list))
for fc in varlen_sparse_feature_columns:
feature_name = fc.name
if feature_name in prefer_fc_names:
prefer_history_columns.append(fc)
elif feature_name in short_fc_names:
short_history_columns.append(fc)
else:
sparse_varlen_feature_columns.append(fc)
embedding_matrix_dict = create_embedding_matrix(user_feature_columns +
item_feature_columns,
l2_reg_embedding,
init_std,
seed,
prefix="")
item_features = build_input_features(item_feature_columns)
item_inputs_list = list(item_features.values())
prefer_emb_list = embedding_lookup(embedding_matrix_dict,
features,
prefer_history_columns,
prefer_fc_names,
prefer_fc_names,
to_list=True) # L^u
short_emb_list = embedding_lookup(embedding_matrix_dict,
features,
short_history_columns,
short_fc_names,
short_fc_names,
to_list=True) # S^u
# dense_value_list = get_dense_input(features, dense_feature_columns)
user_emb_list = embedding_lookup(embedding_matrix_dict,
features,
sparse_feature_columns,
to_list=True)
sequence_embed_dict = varlen_embedding_lookup(
embedding_matrix_dict, features, sparse_varlen_feature_columns)
sequence_embed_list = get_varlen_pooling_list(
sequence_embed_dict,
features,
sparse_varlen_feature_columns,
to_list=True)
user_emb_list += sequence_embed_list # e^u
# if len(user_emb_list) > 0 or len(dense_value_list) > 0:
# user_emb_feature = combined_dnn_input(user_emb_list, dense_value_list)
user_emb = concat_func(user_emb_list)
user_emb_output = Dense(units,
activation=dnn_activation,
name="user_emb_output")(user_emb)
prefer_sess_length = features['prefer_sess_length']
prefer_att_outputs = []
for i, prefer_emb in enumerate(prefer_emb_list):
prefer_attention_output = AttentionSequencePoolingLayer(
dropout_rate=0)([user_emb_output, prefer_emb, prefer_sess_length])
prefer_att_outputs.append(prefer_attention_output)
prefer_att_concat = concat_func(prefer_att_outputs)
prefer_output = Dense(units,
activation=dnn_activation,
name="prefer_output")(prefer_att_concat)
short_sess_length = features['short_sess_length']
short_emb_concat = concat_func(short_emb_list)
short_emb_input = Dense(units,
activation=dnn_activation,
name="short_emb_input")(short_emb_concat)
short_rnn_output = DynamicMultiRNN(
num_units=units,
return_sequence=True,
num_layers=rnn_layers,
num_residual_layers=rnn_num_res,
dropout_rate=dropout_rate)([short_emb_input, short_sess_length])
short_att_output = SelfMultiHeadAttention(
num_units=units,
head_num=num_head,
dropout_rate=dropout_rate,
future_binding=True,
use_layer_norm=True)([short_rnn_output, short_sess_length
]) # [batch_size, time, num_units]
short_output = UserAttention(num_units=units, activation=dnn_activation, use_res=True, dropout_rate=dropout_rate) \
([user_emb_output, short_att_output, short_sess_length])
gate_input = concat_func([prefer_output, short_output, user_emb_output])
gate = Dense(units, activation='sigmoid')(gate_input)
gate_output = Lambda(
lambda x: tf.multiply(x[0], x[1]) + tf.multiply(1 - x[0], x[2]))(
[gate, short_output, prefer_output])
gate_output_reshape = Lambda(lambda x: tf.squeeze(x, 1))(gate_output)
item_index = EmbeddingIndex(list(range(item_vocabulary_size)))(
item_features[item_feature_name])
item_embedding_matrix = embedding_matrix_dict[item_feature_name]
item_embedding_weight = NoMask()(item_embedding_matrix(item_index))
pooling_item_embedding_weight = PoolingLayer()([item_embedding_weight])
output = SampledSoftmaxLayer(num_sampled=num_sampled)([
pooling_item_embedding_weight, gate_output_reshape,
item_features[item_feature_name]
])
model = Model(inputs=user_inputs_list + item_inputs_list, outputs=output)
model.__setattr__("user_input", user_inputs_list)
model.__setattr__("user_embedding", gate_output_reshape)
model.__setattr__("item_input", item_inputs_list)
model.__setattr__(
"item_embedding",
get_item_embedding(pooling_item_embedding_weight,
item_features[item_feature_name]))
return model
def MIND(dnn_feature_columns,
history_feature_list,
target_song_size,
k_max=2,
dnn_use_bn=False,
user_hidden_unit=64,
dnn_activation='relu',
l2_reg_dnn=0,
l2_reg_embedding=1e-6,
dnn_dropout=0,
init_std=0.0001,
seed=1024):
"""
:param dnn_feature_columns: An iterable containing all the features used by deep part of the model.
:param history_feature_list: list,to indicate sequence sparse field
:param target_song_size: int, the total size of the recall songs
:param k_max: int, the max size of user interest embedding
:param dnn_use_bn: bool. Whether use BatchNormalization before activation or not in deep net
:param user_hidden_unit: int. user dnn hidden layer size
:param dnn_activation: Activation function to use in deep net
:param l2_reg_dnn: L2 regularizer strength applied to DNN
:param l2_reg_embedding: float. L2 regularizer strength applied to embedding vector
:param dnn_dropout: float in [0,1), the probability we will drop out a given DNN coordinate.
:param init_std: float,to use as the initialize std of embedding vector
:param seed: integer ,to use as random seed.
:return:
"""
features = build_input_features(dnn_feature_columns)
sparse_feature_columns = list(
filter(lambda x: isinstance(x, SparseFeat),
dnn_feature_columns)) if dnn_feature_columns else []
dense_feature_columns = list(
filter(lambda x: isinstance(x, DenseFeat),
dnn_feature_columns)) if dnn_feature_columns else []
varlen_sparse_feature_columns = list(
filter(lambda x: isinstance(x, VarLenSparseFeat),
dnn_feature_columns)) if dnn_feature_columns else []
history_feature_columns = []
sparse_varlen_feature_columns = []
history_fc_names = list(map(lambda x: "hist_" + x, history_feature_list))
for fc in varlen_sparse_feature_columns:
feature_name = fc.name
if feature_name in history_fc_names:
history_feature_columns.append(fc)
else:
sparse_varlen_feature_columns.append(fc)
hist_len = features['hist_len']
inputs_list = list(features.values())
embedding_dict = create_embedding_matrix(dnn_feature_columns,
l2_reg_embedding,
init_std,
seed,
prefix="")
history_emb_list = embedding_lookup(embedding_dict,
features,
history_feature_columns,
history_fc_names,
history_fc_names,
to_list=True)
history_emb = concat_func(history_emb_list, mask=False)
target_emb_list = embedding_lookup(embedding_dict,
features,
sparse_feature_columns, ['item'],
history_feature_list,
to_list=True)
target_emb_tmp = concat_func(target_emb_list, mask=False)
target_emb_size = target_emb_tmp.get_shape()[-1].value
target_emb = tf.keras.layers.Lambda(
shape_target, arguments={'target_emb_size':
target_emb_size})(target_emb_tmp)
dnn_input_emb_list = embedding_lookup(embedding_dict,
features,
sparse_feature_columns,
mask_feat_list=history_feature_list,
to_list=True)
sequence_embed_dict = varlen_embedding_lookup(
embedding_dict, features, sparse_varlen_feature_columns)
sequence_embed_list = get_varlen_pooling_list(
sequence_embed_dict,
features,
sparse_varlen_feature_columns,
to_list=True)
dnn_input_emb_list += sequence_embed_list
deep_input_emb = concat_func(dnn_input_emb_list)
user_other_feature = Flatten()(deep_input_emb)
max_len = history_emb.get_shape()[1].value
high_capsule = CapsuleLayer(input_units=target_emb_size,
out_units=target_emb_size,
max_len=max_len,
k_max=k_max)((history_emb, hist_len))
other_feature_tile = tf.keras.layers.Lambda(
tile_user_otherfeat, arguments={'k_max': k_max})(user_other_feature)
user_deep_input = Concatenate()(
[NoMask()(other_feature_tile), high_capsule])
user_embeddings = DNN((user_hidden_unit, target_emb_size),
dnn_activation,
l2_reg_dnn,
dnn_dropout,
dnn_use_bn,
seed,
name="user_embedding")(user_deep_input)
k_user = tf.cast(tf.maximum(
1.,
tf.minimum(tf.cast(k_max, dtype="float32"),
tf.log1p(tf.cast(hist_len, dtype="float32")) / tf.log(2.))),
dtype="int64") # [B,1] forword/Cast_2
user_embedding_final = DotProductAttentionLayer(
shape=[target_emb_size, target_emb_size])(
(user_embeddings, target_emb), seq_length=k_user, max_len=k_max)
output = SampledSoftmaxLayer(
target_song_size=target_song_size,
target_emb_size=target_emb_size)(inputs=(user_embedding_final,
features['item']))
model = Model(inputs=inputs_list, outputs=output)
return model
def DSIN(
feature_dim_dict,
sess_feature_list,
embedding_size=8,
sess_max_count=5,
sess_len_max=10,
att_embedding_size=1,
att_head_num=8,
dnn_hidden_units=(200, 80),
dnn_activation='sigmoid',
l2_reg_dnn=0,
l2_reg_embedding=1e-6,
task='binary',
dnn_dropout=0,
init_std=0.0001,
seed=1024,
encoding='bias',
):
check_feature_config_dict(feature_dim_dict)
print(
'sess_count',
sess_max_count,
'encoding',
encoding,
)
sparse_input, dense_input, user_behavior_input_dict, _, user_sess_length = get_input(
feature_dim_dict, sess_feature_list, sess_max_count, sess_len_max)
sparse_embedding_dict = {
feat.name:
Embedding(feat.dimension,
embedding_size,
embeddings_initializer=RandomNormal(mean=0.0,
stddev=init_std,
seed=seed),
embeddings_regularizer=l2(l2_reg_embedding),
name='sparse_emb_' + str(i) + '-' + feat.name,
mask_zero=(feat.name in sess_feature_list))
for i, feat in enumerate(feature_dim_dict["sparse"])
}
query_emb_list = get_embedding_vec_list(sparse_embedding_dict,
sparse_input,
feature_dim_dict["sparse"],
sess_feature_list,
sess_feature_list)
query_emb = concat_fun(query_emb_list)
deep_input_emb_list = get_embedding_vec_list(
sparse_embedding_dict,
sparse_input,
feature_dim_dict["sparse"],
mask_feat_list=sess_feature_list)
deep_input_emb = concat_fun(deep_input_emb_list)
deep_input_emb = Flatten()(NoMask()(deep_input_emb))
be_flag = True if encoding == 'bias' else False
tr_input = sess_interest_division(sparse_embedding_dict,
user_behavior_input_dict,
feature_dim_dict['sparse'],
sess_feature_list,
sess_max_count,
bias_encoding=be_flag)
Self_Attention = Transformer(att_embedding_size,
att_head_num,
dropout_rate=0,
use_layer_norm=False,
use_positional_encoding=(not be_flag),
seed=seed,
supports_masking=True,
blinding=True)
sess_fea = sess_interest_extractor(tr_input, sess_max_count,
Self_Attention)
interest_attention_layer = AttentionSequencePoolingLayer(
att_hidden_units=(64, 16),
weight_normalization=True,
supports_masking=False)([query_emb, sess_fea, user_sess_length])
lstm_outputs = BiLSTM(
len(sess_feature_list) * embedding_size,
layers=2,
res_layers=0,
dropout_rate=0.2,
)(sess_fea)
lstm_attention_layer = AttentionSequencePoolingLayer(
att_hidden_units=(64, 16),
weight_normalization=True)([query_emb, lstm_outputs, user_sess_length])
deep_input_emb = Concatenate()([
deep_input_emb,
Flatten()(interest_attention_layer),
Flatten()(lstm_attention_layer)
])
if len(dense_input) > 0:
deep_input_emb = Concatenate()([deep_input_emb] +
list(dense_input.values()))
output = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn, dnn_dropout,
False, seed)(deep_input_emb)
output = Dense(1, use_bias=False, activation=None)(output)
output = PredictionLayer(task)(output)
sess_input_list = []
#sess_input_length_list = []
for i in range(sess_max_count):
sess_name = "sess_" + str(i)
sess_input_list.extend(
get_inputs_list([user_behavior_input_dict[sess_name]]))
#sess_input_length_list.append(user_behavior_length_dict[sess_name])
model_input_list = get_inputs_list(
[sparse_input, dense_input]) + sess_input_list + [user_sess_length]
model = Model(inputs=model_input_list, outputs=output)
return model
def CapsuleNet(feature_dim_dict,
seq_feature_list,
embedding_size=8,
hist_len_max=50,
use_bn=False,
dnn_hidden_units=(200, 80),
dnn_activation='sigmoid',
num_capsule=8,
dim_capsule=2,
routing_iterations=3,
att_hidden_size=(64, 16),
att_activation="dice",
att_weight_normalization=True,
att_embedding_size=1,
att_head_num=8,
l2_reg_dnn=0,
l2_reg_embedding=1e-6,
dnn_dropout=0,
init_std=0.0001,
alpha=1e-6,
seed=1024,
task='binary'):
check_feature_config_dict(feature_dim_dict)
sparse_input, dense_input, user_behavior_input, user_behavior_length = get_input(
feature_dim_dict, seq_feature_list, hist_len_max)
sparse_embedding_dict = {
feat.name:
Embedding(feat.dimension,
embedding_size,
embeddings_initializer=RandomNormal(mean=0.0,
stddev=init_std,
seed=seed),
embeddings_regularizer=l2(l2_reg_embedding),
name='sparse_emb_' + str(i) + '-' + feat.name,
mask_zero=(feat.name in seq_feature_list))
for i, feat in enumerate(feature_dim_dict["sparse"])
}
query_emb_list = get_embedding_vec_list(sparse_embedding_dict,
sparse_input,
feature_dim_dict["sparse"],
return_feat_list=seq_feature_list)
keys_emb_list = get_embedding_vec_list(sparse_embedding_dict,
user_behavior_input,
feature_dim_dict['sparse'],
return_feat_list=seq_feature_list)
deep_input_emb_list = get_embedding_vec_list(sparse_embedding_dict,
sparse_input,
feature_dim_dict['sparse'])
query_emb = concat_fun(query_emb_list)
keys_emb = concat_fun(keys_emb_list)
scores = AttentionSequencePoolingLayer(
att_hidden_units=att_hidden_size,
att_activation=att_activation,
weight_normalization=att_weight_normalization,
return_score=True)([query_emb, keys_emb, user_behavior_length])
Self_Attention = Transformer(att_embedding_size,
att_head_num,
dropout_rate=0,
use_layer_norm=True,
use_positional_encoding=True,
seed=seed,
supports_masking=False,
blinding=True)
keys_emb = Self_Attention(
[keys_emb, keys_emb, user_behavior_length, user_behavior_length])
cap = Capsule(num_capsule=num_capsule,
dim_capsule=dim_capsule,
routings=routing_iterations,
share_weights=True,
supports_masking=True)
hist_cap = cap(keys_emb, scores=scores)
disp_loss = get_disp_loss(hist_cap)
hist_cap = Reshape([1, num_capsule * dim_capsule])(NoMask()(hist_cap))
deep_input_emb = concat_fun(deep_input_emb_list)
deep_input_emb = Concatenate()([deep_input_emb, hist_cap])
deep_input_emb = tf.keras.layers.Flatten()(NoMask()(deep_input_emb))
if len(dense_input) > 0:
deep_input_emb = Concatenate()([deep_input_emb] +
list(dense_input.values()))
output = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn, dnn_dropout,
use_bn, seed)(deep_input_emb)
final_logit = Dense(1, use_bias=False)(output)
output = PredictionLayer(task)(final_logit)
model_input_list = get_inputs_list(
[sparse_input, dense_input, user_behavior_input])
model_input_list += [user_behavior_length]
model = tf.keras.models.Model(inputs=model_input_list, outputs=output)
model.add_loss(alpha * disp_loss)
tf.keras.backend.get_session().run(tf.global_variables_initializer())
return model
def MIND(user_feature_columns,
item_feature_columns,
num_sampled=5,
k_max=2,
p=1.0,
dynamic_k=False,
user_dnn_hidden_units=(64, 32),
dnn_activation='relu',
dnn_use_bn=False,
l2_reg_dnn=0,
l2_reg_embedding=1e-6,
dnn_dropout=0,
output_activation='linear',
seed=1024):
"""Instantiates the MIND Model architecture.
:param user_feature_columns: An iterable containing user's features used by the model.
:param item_feature_columns: An iterable containing item's features used by the model.
:param num_sampled: int, the number of classes to randomly sample per batch.
:param k_max: int, the max size of user interest embedding
:param p: float,the parameter for adjusting the attention distribution in LabelAwareAttention.
:param dynamic_k: bool, whether or not use dynamic interest number
:param dnn_use_bn: bool. Whether use BatchNormalization before activation or not in deep net
:param user_dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of user tower
:param dnn_activation: Activation function to use in deep net
:param dnn_use_bn: bool. Whether use BatchNormalization before activation or not in deep net
:param l2_reg_dnn: L2 regularizer strength applied to DNN
:param l2_reg_embedding: float. L2 regularizer strength applied to embedding vector
:param dnn_dropout: float in [0,1), the probability we will drop out a given DNN coordinate.
:param seed: integer ,to use as random seed.
:param output_activation: Activation function to use in output layer
:return: A Keras model instance.
"""
if len(item_feature_columns) > 1:
raise ValueError("Now MIND only support 1 item feature like item_id")
item_feature_column = item_feature_columns[0]
item_feature_name = item_feature_column.name
item_vocabulary_size = item_feature_columns[0].vocabulary_size
item_embedding_dim = item_feature_columns[0].embedding_dim
# item_index = Input(tensor=tf.constant([list(range(item_vocabulary_size))]))
history_feature_list = [item_feature_name]
features = build_input_features(user_feature_columns)
sparse_feature_columns = list(
filter(lambda x: isinstance(x, SparseFeat),
user_feature_columns)) if user_feature_columns else []
dense_feature_columns = list(
filter(lambda x: isinstance(x, DenseFeat),
user_feature_columns)) if user_feature_columns else []
varlen_sparse_feature_columns = list(
filter(lambda x: isinstance(x, VarLenSparseFeat),
user_feature_columns)) if user_feature_columns else []
history_feature_columns = []
sparse_varlen_feature_columns = []
history_fc_names = list(map(lambda x: "hist_" + x, history_feature_list))
for fc in varlen_sparse_feature_columns:
feature_name = fc.name
if feature_name in history_fc_names:
history_feature_columns.append(fc)
else:
sparse_varlen_feature_columns.append(fc)
seq_max_len = history_feature_columns[0].maxlen
inputs_list = list(features.values())
embedding_matrix_dict = create_embedding_matrix(user_feature_columns +
item_feature_columns,
l2_reg_embedding,
seed=seed,
prefix="")
item_features = build_input_features(item_feature_columns)
query_emb_list = embedding_lookup(embedding_matrix_dict,
item_features,
item_feature_columns,
history_feature_list,
history_feature_list,
to_list=True)
keys_emb_list = embedding_lookup(embedding_matrix_dict,
features,
history_feature_columns,
history_fc_names,
history_fc_names,
to_list=True)
dnn_input_emb_list = embedding_lookup(embedding_matrix_dict,
features,
sparse_feature_columns,
mask_feat_list=history_feature_list,
to_list=True)
dense_value_list = get_dense_input(features, dense_feature_columns)
sequence_embed_dict = varlen_embedding_lookup(
embedding_matrix_dict, features, sparse_varlen_feature_columns)
sequence_embed_list = get_varlen_pooling_list(
sequence_embed_dict,
features,
sparse_varlen_feature_columns,
to_list=True)
dnn_input_emb_list += sequence_embed_list
# keys_emb = concat_func(keys_emb_list, mask=True)
# query_emb = concat_func(query_emb_list, mask=True)
history_emb = PoolingLayer()(NoMask()(keys_emb_list))
target_emb = PoolingLayer()(NoMask()(query_emb_list))
# target_emb_size = target_emb.get_shape()[-1].value
# max_len = history_emb.get_shape()[1].value
hist_len = features['hist_len']
high_capsule = CapsuleLayer(input_units=item_embedding_dim,
out_units=item_embedding_dim,
max_len=seq_max_len,
k_max=k_max)((history_emb, hist_len))
if len(dnn_input_emb_list) > 0 or len(dense_value_list) > 0:
user_other_feature = combined_dnn_input(dnn_input_emb_list,
dense_value_list)
other_feature_tile = tf.keras.layers.Lambda(
tile_user_otherfeat, arguments={'k_max':
k_max})(user_other_feature)
user_deep_input = Concatenate()(
[NoMask()(other_feature_tile), high_capsule])
else:
user_deep_input = high_capsule
user_embeddings = DNN(user_dnn_hidden_units,
dnn_activation,
l2_reg_dnn,
dnn_dropout,
dnn_use_bn,
output_activation=output_activation,
seed=seed,
name="user_embedding")(user_deep_input)
item_inputs_list = list(item_features.values())
item_embedding_matrix = embedding_matrix_dict[item_feature_name]
item_index = EmbeddingIndex(list(range(item_vocabulary_size)))(
item_features[item_feature_name])
item_embedding_weight = NoMask()(item_embedding_matrix(item_index))
pooling_item_embedding_weight = PoolingLayer()([item_embedding_weight])
if dynamic_k:
user_embedding_final = LabelAwareAttention(
k_max=k_max,
pow_p=p,
)((user_embeddings, target_emb, hist_len))
else:
user_embedding_final = LabelAwareAttention(
k_max=k_max,
pow_p=p,
)((user_embeddings, target_emb))
output = SampledSoftmaxLayer(num_sampled=num_sampled)([
pooling_item_embedding_weight, user_embedding_final,
item_features[item_feature_name]
])
model = Model(inputs=inputs_list + item_inputs_list, outputs=output)
model.__setattr__("user_input", inputs_list)
model.__setattr__("user_embedding", user_embeddings)
model.__setattr__("item_input", item_inputs_list)
model.__setattr__(
"item_embedding",
get_item_embedding(pooling_item_embedding_weight,
item_features[item_feature_name]))
return model
def KDD_DIN(dnn_feature_columns,
history_feature_list,
dnn_use_bn=False,
dnn_hidden_units=(200, 80),
dnn_activation='relu',
att_hidden_size=(80, 40),
att_activation="dice",
att_weight_normalization=False,
l2_reg_dnn=0,
l2_reg_embedding=1e-6,
dnn_dropout=0,
init_std=0.0001,
seed=1024,
task='binary'):
"""Instantiates the Deep Interest Network architecture.
:param dnn_feature_columns: An iterable containing all the features used by deep part of the model.
:param history_feature_list: list,to indicate sequence sparse field
:param dnn_use_bn: bool. Whether use BatchNormalization before activation or not in deep net
:param dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of deep net
:param dnn_activation: Activation function to use in deep net
:param att_hidden_size: list,list of positive integer , the layer number and units in each layer of attention net
:param att_activation: Activation function to use in attention net
:param att_weight_normalization: bool.Whether normalize the attention score of local activation unit.
:param l2_reg_dnn: float. L2 regularizer strength applied to DNN
:param l2_reg_embedding: float. L2 regularizer strength applied to embedding vector
:param dnn_dropout: float in [0,1), the probability we will drop out a given DNN coordinate.
:param init_std: float,to use as the initialize std of embedding vector
:param seed: integer ,to use as random seed.
:param task: str, ``"binary"`` for binary logloss or ``"regression"`` for regression loss
:return: A Keras model instance.
"""
features = build_input_features(dnn_feature_columns)
sparse_feature_columns = list(
filter(lambda x: isinstance(x, SparseFeat),
dnn_feature_columns)) if dnn_feature_columns else []
dense_feature_columns = list(
filter(lambda x: isinstance(x, DenseFeat),
dnn_feature_columns)) if dnn_feature_columns else []
varlen_sparse_feature_columns = list(
filter(lambda x: isinstance(x, VarLenSparseFeat),
dnn_feature_columns)) if dnn_feature_columns else []
history_feature_columns = []
sparse_varlen_feature_columns = []
history_fc_names = list(map(lambda x: "hist_" + x, history_feature_list))
for fc in varlen_sparse_feature_columns:
feature_name = fc.name
if feature_name in history_fc_names:
history_feature_columns.append(fc)
else:
sparse_varlen_feature_columns.append(fc)
inputs_list = list(features.values())
embedding_dict = kdd_create_embedding_matrix(dnn_feature_columns,
l2_reg_embedding,
init_std,
seed,
prefix="")
query_emb_list = embedding_lookup(embedding_dict,
features,
sparse_feature_columns,
history_feature_list,
history_feature_list,
to_list=True)
keys_emb_list = embedding_lookup(embedding_dict,
features,
history_feature_columns,
history_fc_names,
history_fc_names,
to_list=True)
dnn_input_emb_list = embedding_lookup(embedding_dict,
features,
sparse_feature_columns,
mask_feat_list=history_feature_list,
to_list=True)
dense_value_list = get_dense_input(features, dense_feature_columns)
sequence_embed_dict = varlen_embedding_lookup(
embedding_dict, features, sparse_varlen_feature_columns)
sequence_embed_list = get_varlen_pooling_list(
sequence_embed_dict,
features,
sparse_varlen_feature_columns,
to_list=True)
dnn_input_emb_list += sequence_embed_list
keys_emb = concat_func(keys_emb_list, mask=True)
deep_input_emb = concat_func(dnn_input_emb_list)
query_emb = concat_func(query_emb_list, mask=True)
hist = AttentionSequencePoolingLayer(
att_hidden_size,
att_activation,
weight_normalization=att_weight_normalization,
supports_masking=True)([query_emb, keys_emb])
deep_input_emb = Concatenate()([NoMask()(deep_input_emb), hist])
deep_input_emb = Flatten()(deep_input_emb)
dnn_input = combined_dnn_input([deep_input_emb], dense_value_list)
output = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn, dnn_dropout,
dnn_use_bn, seed)(dnn_input)
final_logit = Dense(1, use_bias=False)(output)
output = PredictionLayer(task)(final_logit)
model = Model(inputs=inputs_list, outputs=output)
return model
def _model_fn(features, labels, mode, config):
train_flag = (mode == tf.estimator.ModeKeys.TRAIN)
with variable_scope(DNN_SCOPE_NAME):
sparse_feature_columns = []
dense_feature_columns = []
varlen_sparse_feature_columns = []
for feat in dnn_feature_columns:
new_feat_name = list(feat.parse_example_spec.keys())[0]
if new_feat_name in ['hist_price_id', 'hist_des_id']:
varlen_sparse_feature_columns.append(
VarLenSparseFeat(SparseFeat(new_feat_name,
vocabulary_size=100,
embedding_dim=32,
use_hash=False),
maxlen=3))
elif is_embedding(feat):
sparse_feature_columns.append(
SparseFeat(new_feat_name,
vocabulary_size=feat[0]._num_buckets + 1,
embedding_dim=feat.dimension))
else:
dense_feature_columns.append(DenseFeat(new_feat_name))
history_feature_columns = []
sparse_varlen_feature_columns = []
history_fc_names = list(
map(lambda x: "hist_" + x, history_feature_list))
for fc in varlen_sparse_feature_columns:
feature_name = fc.name
if feature_name in history_fc_names:
history_feature_columns.append(fc)
else:
sparse_varlen_feature_columns.append(fc)
my_feature_columns = sparse_feature_columns + dense_feature_columns + varlen_sparse_feature_columns
embedding_dict = create_embedding_matrix(my_feature_columns,
l2_reg_embedding,
seed,
prefix="")
query_emb_list = embedding_lookup(embedding_dict,
features,
sparse_feature_columns,
history_feature_list,
history_feature_list,
to_list=True)
print('query_emb_list', query_emb_list)
print('embedding_dict', embedding_dict)
print('haha')
print('history_feature_columns', history_feature_columns)
print('haha')
keys_emb_list = embedding_lookup(embedding_dict,
features,
history_feature_columns,
history_fc_names,
history_fc_names,
to_list=True)
print('keys_emb_list', keys_emb_list)
dnn_input_emb_list = embedding_lookup(
embedding_dict,
features,
sparse_feature_columns,
mask_feat_list=history_feature_list,
to_list=True)
print('dnn_input_emb_list', dnn_input_emb_list)
dense_value_list = get_dense_input(features, dense_feature_columns)
sequence_embed_dict = varlen_embedding_lookup(
embedding_dict, features, sparse_varlen_feature_columns)
sequence_embed_list = get_varlen_pooling_list(
sequence_embed_dict,
features,
sparse_varlen_feature_columns,
to_list=True)
dnn_input_emb_list += sequence_embed_list
keys_emb = concat_func(keys_emb_list, mask=True)
deep_input_emb = concat_func(dnn_input_emb_list)
query_emb = concat_func(query_emb_list, mask=True)
hist = AttentionSequencePoolingLayer(
att_hidden_size,
att_activation,
weight_normalization=att_weight_normalization,
supports_masking=True)([query_emb, keys_emb])
deep_input_emb = tf.keras.layers.Concatenate()(
[NoMask()(deep_input_emb), hist])
deep_input_emb = tf.keras.layers.Flatten()(deep_input_emb)
dnn_input = combined_dnn_input([deep_input_emb], dense_value_list)
output = DNN(dnn_hidden_units,
dnn_activation,
l2_reg_dnn,
dnn_dropout,
dnn_use_bn,
seed=seed)(dnn_input)
final_logit = tf.keras.layers.Dense(
1,
use_bias=False,
kernel_initializer=tf.keras.initializers.glorot_normal(seed))(
output)
# logits_list.append(final_logit)
# logits = add_func(logits_list)
# print(labels)
# tf.summary.histogram(final_logit + '/final_logit', final_logit)
return deepctr_model_fn(features,
mode,
final_logit,
labels,
task,
linear_optimizer,
dnn_optimizer,
training_chief_hooks=training_chief_hooks)
def YoutubeDNN(user_feature_columns, item_feature_columns, num_sampled=5,
user_dnn_hidden_units=(64, 32),
dnn_activation='relu', dnn_use_bn=False,
l2_reg_dnn=0, l2_reg_embedding=1e-6, dnn_dropout=0, output_activation='linear', seed=1024, ):
"""Instantiates the YoutubeDNN Model architecture.
:param user_feature_columns: An iterable containing user's features used by the model.
:param item_feature_columns: An iterable containing item's features used by the model.
:param num_sampled: int, the number of classes to randomly sample per batch.
:param user_dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of user tower
:param dnn_activation: Activation function to use in deep net
:param dnn_use_bn: bool. Whether use BatchNormalization before activation or not in deep net
:param l2_reg_dnn: float. L2 regularizer strength applied to DNN
:param l2_reg_embedding: float. L2 regularizer strength applied to embedding vector
:param dnn_dropout: float in [0,1), the probability we will drop out a given DNN coordinate.
:param seed: integer ,to use as random seed.
:param output_activation: Activation function to use in output layer
:return: A Keras model instance.
"""
if len(item_feature_columns) > 1:
raise ValueError("Now YoutubeNN only support 1 item feature like item_id")
item_feature_name = item_feature_columns[0].name
item_vocabulary_size = item_feature_columns[0].vocabulary_size
embedding_matrix_dict = create_embedding_matrix(user_feature_columns + item_feature_columns, l2_reg_embedding,
seed=seed)
user_features = build_input_features(user_feature_columns)
user_inputs_list = list(user_features.values())
user_sparse_embedding_list, user_dense_value_list = input_from_feature_columns(user_features, user_feature_columns,
l2_reg_embedding, seed=seed,
embedding_matrix_dict=embedding_matrix_dict)
user_dnn_input = combined_dnn_input(user_sparse_embedding_list, user_dense_value_list)
item_features = build_input_features(item_feature_columns)
item_inputs_list = list(item_features.values())
user_dnn_out = DNN(user_dnn_hidden_units, dnn_activation, l2_reg_dnn, dnn_dropout,
dnn_use_bn, output_activation=output_activation, seed=seed)(user_dnn_input)
item_index = EmbeddingIndex(list(range(item_vocabulary_size)))(item_features[item_feature_name])
item_embedding_matrix = embedding_matrix_dict[
item_feature_name]
item_embedding_weight = NoMask()(item_embedding_matrix(item_index))
pooling_item_embedding_weight = PoolingLayer()([item_embedding_weight])
output = SampledSoftmaxLayer(num_sampled=num_sampled)(
[pooling_item_embedding_weight, user_dnn_out, item_features[item_feature_name]])
model = Model(inputs=user_inputs_list + item_inputs_list, outputs=output)
model.__setattr__("user_input", user_inputs_list)
model.__setattr__("user_embedding", user_dnn_out)
model.__setattr__("item_input", item_inputs_list)
model.__setattr__("item_embedding",
get_item_embedding(pooling_item_embedding_weight, item_features[item_feature_name]))
return model
def DIN(feature_dim_dict,
seq_feature_list,
embedding_size=8,
hist_len_max=16,
dnn_use_bn=False,
dnn_hidden_units=(200, 80),
dnn_activation='relu',
att_hidden_size=(80, 40),
att_activation="dice",
att_weight_normalization=False,
l2_reg_dnn=0,
l2_reg_embedding=1e-6,
dnn_dropout=0,
init_std=0.0001,
seed=1024,
task='binary'):
"""Instantiates the Deep Interest Network architecture.
:param feature_dim_dict: dict,to indicate sparse field (**now only support sparse feature**)like {'sparse':{'field_1':4,'field_2':3,'field_3':2},'dense':[]}
:param seq_feature_list: list,to indicate sequence sparse field (**now only support sparse feature**),must be a subset of ``feature_dim_dict["sparse"]``
:param embedding_size: positive integer,sparse feature embedding_size.
:param hist_len_max: positive int, to indicate the max length of seq input
:param dnn_use_bn: bool. Whether use BatchNormalization before activation or not in deep net
:param dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of deep net
:param dnn_activation: Activation function to use in deep net
:param att_hidden_size: list,list of positive integer , the layer number and units in each layer of attention net
:param att_activation: Activation function to use in attention net
:param att_weight_normalization: bool.Whether normalize the attention score of local activation unit.
:param l2_reg_dnn: float. L2 regularizer strength applied to DNN
:param l2_reg_embedding: float. L2 regularizer strength applied to embedding vector
:param dnn_dropout: float in [0,1), the probability we will drop out a given DNN coordinate.
:param init_std: float,to use as the initialize std of embedding vector
:param seed: integer ,to use as random seed.
:param task: str, ``"binary"`` for binary logloss or ``"regression"`` for regression loss
:return: A Keras model instance.
"""
check_feature_config_dict(feature_dim_dict)
sparse_input, dense_input, user_behavior_input = get_input(
feature_dim_dict, seq_feature_list, hist_len_max)
sparse_embedding_dict = {
feat.name:
Embedding(feat.dimension,
embedding_size,
embeddings_initializer=RandomNormal(mean=0.0,
stddev=init_std,
seed=seed),
embeddings_regularizer=l2(l2_reg_embedding),
name='sparse_emb_' + str(i) + '-' + feat.name,
mask_zero=(feat.name in seq_feature_list))
for i, feat in enumerate(feature_dim_dict["sparse"])
}
query_emb_list = get_embedding_vec_list(sparse_embedding_dict,
sparse_input,
feature_dim_dict['sparse'],
seq_feature_list, seq_feature_list)
keys_emb_list = get_embedding_vec_list(sparse_embedding_dict,
user_behavior_input,
feature_dim_dict['sparse'],
seq_feature_list, seq_feature_list)
deep_input_emb_list = get_embedding_vec_list(
sparse_embedding_dict,
sparse_input,
feature_dim_dict['sparse'],
mask_feat_list=seq_feature_list)
keys_emb = concat_fun(keys_emb_list)
deep_input_emb = concat_fun(deep_input_emb_list)
query_emb = concat_fun(query_emb_list)
hist = AttentionSequencePoolingLayer(
att_hidden_size,
att_activation,
weight_normalization=att_weight_normalization,
supports_masking=True)([query_emb, keys_emb])
deep_input_emb = Concatenate()([NoMask()(deep_input_emb), hist])
deep_input_emb = Flatten()(deep_input_emb)
if len(dense_input) > 0:
deep_input_emb = Concatenate()([deep_input_emb] +
list(dense_input.values()))
output = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn, dnn_dropout,
dnn_use_bn, seed)(deep_input_emb)
final_logit = Dense(1, use_bias=False)(output)
output = PredictionLayer(task)(final_logit)
model_input_list = get_inputs_list(
[sparse_input, dense_input, user_behavior_input])
model = Model(inputs=model_input_list, outputs=output)
return model
def DSIN(
feature_dim_dict,
sess_feature_list,
embedding_size=8,
sess_max_count=5,
sess_len_max=10,
bias_encoding=False,
att_embedding_size=1,
att_head_num=8,
dnn_hidden_units=(200, 80),
dnn_activation='sigmoid',
dnn_dropout=0,
dnn_use_bn=False,
l2_reg_dnn=0,
l2_reg_embedding=1e-6,
init_std=0.0001,
seed=1024,
task='binary',
):
"""Instantiates the Deep Session Interest Network architecture.
:param feature_dim_dict: dict,to indicate sparse field (**now only support sparse feature**)like {'sparse':{'field_1':4,'field_2':3,'field_3':2},'dense':[]}
:param sess_feature_list: list,to indicate session feature sparse field (**now only support sparse feature**),must be a subset of ``feature_dim_dict["sparse"]``
:param embedding_size: positive integer,sparse feature embedding_size.
:param sess_max_count: positive int, to indicate the max number of sessions
:param sess_len_max: positive int, to indicate the max length of each session
:param bias_encoding: bool. Whether use bias encoding or postional encoding
:param att_embedding_size: positive int, the embedding size of each attention head
:param att_head_num: positive int, the number of attention head
:param dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of deep net
:param dnn_activation: Activation function to use in deep net
:param dnn_dropout: float in [0,1), the probability we will drop out a given DNN coordinate.
:param dnn_use_bn: bool. Whether use BatchNormalization before activation or not in deep net
:param l2_reg_dnn: float. L2 regularizer strength applied to DNN
:param l2_reg_embedding: float. L2 regularizer strength applied to embedding vector
:param init_std: float,to use as the initialize std of embedding vector
:param seed: integer ,to use as random seed.
:param task: str, ``"binary"`` for binary logloss or ``"regression"`` for regression loss
:return: A Keras model instance.
"""
check_feature_config_dict(feature_dim_dict)
if (att_embedding_size * att_head_num !=
len(sess_feature_list) * embedding_size):
raise ValueError(
"len(session_feature_lsit) * embedding_size must equal to att_embedding_size * att_head_num ,got %d * %d != %d *%d"
% (len(sess_feature_list), embedding_size, att_embedding_size,
att_head_num))
sparse_input, dense_input, user_behavior_input_dict, _, user_sess_length = get_input(
feature_dim_dict, sess_feature_list, sess_max_count, sess_len_max)
sparse_embedding_dict = {
feat.name:
Embedding(feat.dimension,
embedding_size,
embeddings_initializer=RandomNormal(mean=0.0,
stddev=init_std,
seed=seed),
embeddings_regularizer=l2(l2_reg_embedding),
name='sparse_emb_' + str(i) + '-' + feat.name,
mask_zero=(feat.name in sess_feature_list))
for i, feat in enumerate(feature_dim_dict["sparse"])
}
query_emb_list = get_embedding_vec_list(sparse_embedding_dict,
sparse_input,
feature_dim_dict["sparse"],
sess_feature_list,
sess_feature_list)
query_emb = concat_fun(query_emb_list)
deep_input_emb_list = get_embedding_vec_list(
sparse_embedding_dict,
sparse_input,
feature_dim_dict["sparse"],
mask_feat_list=sess_feature_list)
deep_input_emb = concat_fun(deep_input_emb_list)
deep_input_emb = Flatten()(NoMask()(deep_input_emb))
tr_input = sess_interest_division(sparse_embedding_dict,
user_behavior_input_dict,
feature_dim_dict['sparse'],
sess_feature_list,
sess_max_count,
bias_encoding=bias_encoding)
Self_Attention = Transformer(att_embedding_size,
att_head_num,
dropout_rate=0,
use_layer_norm=False,
use_positional_encoding=(not bias_encoding),
seed=seed,
supports_masking=True,
blinding=True)
sess_fea = sess_interest_extractor(tr_input, sess_max_count,
Self_Attention)
interest_attention_layer = AttentionSequencePoolingLayer(
att_hidden_units=(64, 16),
weight_normalization=True,
supports_masking=False)([query_emb, sess_fea, user_sess_length])
lstm_outputs = BiLSTM(
len(sess_feature_list) * embedding_size,
layers=2,
res_layers=0,
dropout_rate=0.2,
)(sess_fea)
lstm_attention_layer = AttentionSequencePoolingLayer(
att_hidden_units=(64, 16),
weight_normalization=True)([query_emb, lstm_outputs, user_sess_length])
deep_input_emb = Concatenate()([
deep_input_emb,
Flatten()(interest_attention_layer),
Flatten()(lstm_attention_layer)
])
if len(dense_input) > 0:
deep_input_emb = Concatenate()([deep_input_emb] +
list(dense_input.values()))
output = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn, dnn_dropout,
dnn_use_bn, seed)(deep_input_emb)
output = Dense(1, use_bias=False, activation=None)(output)
output = PredictionLayer(task)(output)
sess_input_list = []
# sess_input_length_list = []
for i in range(sess_max_count):
sess_name = "sess_" + str(i)
sess_input_list.extend(
get_inputs_list([user_behavior_input_dict[sess_name]]))
# sess_input_length_list.append(user_behavior_length_dict[sess_name])
model_input_list = get_inputs_list(
[sparse_input, dense_input]) + sess_input_list + [user_sess_length]
model = Model(inputs=model_input_list, outputs=output)
return model
def BST(feature_dim_dict, seq_feature_list, embedding_size=4, hist_len_max=16, use_bn=False, dnn_hidden_units=(200, 80),
dnn_activation='relu', att_embedding_size=1, att_head_num=8,
l2_reg_dnn=0, l2_reg_embedding=1e-6, dnn_dropout=0, init_std=0.0001, seed=1024, task='binary'):
"""Instantiates the Deep Interest Evolution Network architecture.
:param feature_dim_dict: dict,to indicate sparse field (**now only support sparse feature**)like {'sparse':{'field_1':4,'field_2':3,'field_3':2},'dense':[]}
:param seq_feature_list: list,to indicate sequence sparse field (**now only support sparse feature**),must be a subset of ``feature_dim_dict["sparse"]``
:param embedding_size: positive integer,sparse feature embedding_size.
:param hist_len_max: positive int, to indicate the max length of seq input
:param use_bn: bool. Whether use BatchNormalization before activation or not in deep net
:param dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of DNN
:param dnn_activation: Activation function to use in DNN
:param l2_reg_dnn: float. L2 regularizer strength applied to DNN
:param l2_reg_embedding: float. L2 regularizer strength applied to embedding vector
:param dnn_dropout: float in [0,1), the probability we will drop out a given DNN coordinate.
:param init_std: float,to use as the initialize std of embedding vector
:param seed: integer ,to use as random seed.
:param task: str, ``"binary"`` for binary logloss or ``"regression"`` for regression loss
:return: A Keras model instance.
"""
check_feature_config_dict(feature_dim_dict)
sparse_input, dense_input, user_behavior_input, user_behavior_length = get_input(
feature_dim_dict, seq_feature_list, hist_len_max)
# sparse_embedding_dict = {feat.name: Embedding(feat.dimension, embedding_size,
# embeddings_initializer=RandomNormal(
# mean=0.0, stddev=init_std, seed=seed),
# embeddings_regularizer=l2(
# l2_reg_embedding),
# name='sparse_emb_' + str(i) + '-' + feat.name) for i, feat in
# enumerate(feature_dim_dict["sparse"])}
# print(sparse_embedding_dict)
sparse_embedding_dict = {feat.name: Embedding(tf.cast(feat.dimension, tf.int32), embedding_size,
embeddings_initializer=RandomNormal(
mean=0.0, stddev=init_std, seed=seed),
embeddings_regularizer=l2(
l2_reg_embedding),
name='sparse_emb_' +
str(i) + '-' + feat.name,
mask_zero=(feat.name in seq_feature_list)) for i, feat in
enumerate(feature_dim_dict["sparse"])}
# deep_emb_list = get_embedding_vec_list(
# deep_sparse_emb_dict, sparse_input_dict, feature_dim_dict['sparse'])
query_emb_list = get_embedding_vec_list(sparse_embedding_dict, sparse_input, feature_dim_dict["sparse"],
return_feat_list=seq_feature_list)
keys_emb_list = get_embedding_vec_list(sparse_embedding_dict, user_behavior_input, feature_dim_dict['sparse'],
return_feat_list=seq_feature_list)
deep_input_emb_list = get_embedding_vec_list(sparse_embedding_dict, sparse_input, feature_dim_dict['sparse'])
query_emb = concat_fun(query_emb_list)
keys_emb = concat_fun(keys_emb_list)
print("prev: {0}".format(keys_emb))
# hist_cap = Capsule(
# num_capsule=8, dim_capsule=2,
# routings=3, share_weights=True)(NoMask()(keys_emb))
# print("now: {0}".format(hist_cap))
# # exit(0)
# # keys_emb = concat_fun(keys_emb_list)
# hist_cap = Reshape([1, 16])(hist_cap)
deep_input_emb = concat_fun(deep_input_emb_list)
print("deep input emb: ", deep_input_emb)
# print("hist_cap: ", hist_cap)
Self_Attention = Transformer(att_embedding_size, att_head_num, dropout_rate=0, use_layer_norm=False,
use_positional_encoding=True, seed=seed, supports_masking=False,
blinding=True)
# print("now: {0}".format(hist))
hists = []
for key_emb in keys_emb_list:
hist = Self_Attention([key_emb, key_emb, user_behavior_length, user_behavior_length])
hists.append(hist)
hist = concat_fun(hists)
# Tensor("concatenate_2/concat:0", shape=(?, 50, 8), dtype=float32)
# <tf.Tensor 'concatenate_3/concat:0' shape=(?, 4, 8) dtype=float32>
deep_input_emb = Concatenate()([deep_input_emb, hist])
# print(deep_input_emb)
deep_input_emb = tf.keras.layers.Flatten()(NoMask()(deep_input_emb))
if len(dense_input) > 0:
deep_input_emb = Concatenate()(
[deep_input_emb] + list(dense_input.values()))
output = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn,
dnn_dropout, use_bn, seed)(deep_input_emb)
final_logit = Dense(1, use_bias=False)(output)
output = PredictionLayer(task)(final_logit)
model_input_list = get_inputs_list(
[sparse_input, dense_input, user_behavior_input])
model_input_list += [user_behavior_length]
model = tf.keras.models.Model(inputs=model_input_list, outputs=output)
tf.keras.backend.get_session().run(tf.global_variables_initializer())
return model