def CCPM(feature_dim_dict, embedding_size=8, conv_kernel_width=(6, 5), conv_filters=(4, 4), dnn_hidden_units=(256,),
l2_reg_linear=1e-5, l2_reg_embedding=1e-5, l2_reg_dnn=0, dnn_dropout=0, init_std=0.0001, seed=1024,
task='binary', ):
"""Instantiates the Convolutional Click Prediction Model architecture.
:param feature_dim_dict: dict,to indicate sparse field and dense field like {'sparse':{'field_1':4,'field_2':3,'field_3':2},'dense':['field_4','field_5']}
:param embedding_size: positive integer,sparse feature embedding_size
:param conv_kernel_width: list,list of positive integer or empty list,the width of filter in each conv layer.
:param conv_filters: list,list of positive integer or empty list,the number of filters in each conv layer.
:param dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of DNN.
: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_dnn: float. L2 regularizer strength applied to DNN
: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)
if len(conv_kernel_width) != len(conv_filters):
raise ValueError(
"conv_kernel_width must have same element with conv_filters")
deep_emb_list, linear_emb_list, dense_input_dict, inputs_list = preprocess_input_embedding(feature_dim_dict,
embedding_size,
l2_reg_embedding,
l2_reg_linear, init_std,
seed,
create_linear_weight=True)
linear_logit = get_linear_logit(
linear_emb_list, dense_input_dict, l2_reg_linear)
n = len(deep_emb_list)
l = len(conv_filters)
conv_input = concat_fun(deep_emb_list, axis=1)
pooling_result = tf.keras.layers.Lambda(
lambda x: tf.expand_dims(x, axis=3))(conv_input)
for i in range(1, l + 1):
filters = conv_filters[i - 1]
width = conv_kernel_width[i - 1]
k = max(1, int((1 - pow(i / l, l - i)) * n)) if i < l else 3
conv_result = tf.keras.layers.Conv2D(filters=filters, kernel_size=(width, 1), strides=(1, 1), padding='same',
activation='tanh', use_bias=True, )(pooling_result)
pooling_result = KMaxPooling(
k=min(k, conv_result.shape[1].value), axis=1)(conv_result)
flatten_result = tf.keras.layers.Flatten()(pooling_result)
final_logit = DNN(dnn_hidden_units, l2_reg=l2_reg_dnn,
dropout_rate=dnn_dropout)(flatten_result)
final_logit = tf.keras.layers.Dense(1, use_bias=False)(final_logit)
final_logit = tf.keras.layers.add([final_logit, linear_logit])
output = PredictionLayer(task)(final_logit)
model = tf.keras.models.Model(inputs=inputs_list, outputs=output)
return model
def AFM(
feature_dim_dict,
embedding_size=8,
use_attention=True,
attention_factor=8,
l2_reg_linear=1e-5,
l2_reg_embedding=1e-5,
l2_reg_att=1e-5,
afm_dropout=0,
init_std=0.0001,
seed=1024,
task='binary',
):
"""Instantiates the Attentonal Factorization Machine architecture.
:param feature_dim_dict: dict,to indicate sparse field and dense field like {'sparse':{'field_1':4,'field_2':3,'field_3':2},'dense':['field_4','field_5']}
:param embedding_size: positive integer,sparse feature embedding_size
: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 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)
deep_emb_list, linear_emb_list, dense_input_dict, inputs_list = preprocess_input_embedding(
feature_dim_dict,
embedding_size,
l2_reg_embedding,
l2_reg_linear,
init_std,
seed,
create_linear_weight=True)
linear_logit = get_linear_logit(linear_emb_list, dense_input_dict,
l2_reg_linear)
fm_input = concat_fun(deep_emb_list, axis=1)
if use_attention:
fm_logit = AFMLayer(attention_factor, l2_reg_att, afm_dropout,
seed)(deep_emb_list, )
else:
fm_logit = FM()(fm_input)
final_logit = tf.keras.layers.add([linear_logit, fm_logit])
output = PredictionLayer(task)(final_logit)
model = tf.keras.models.Model(inputs=inputs_list, outputs=output)
return model
def FNN(
feature_dim_dict,
embedding_size=8,
dnn_hidden_units=(128, 128),
l2_reg_embedding=1e-5,
l2_reg_linear=1e-5,
l2_reg_dnn=0,
init_std=0.0001,
seed=1024,
dnn_dropout=0,
dnn_activation='relu',
task='binary',
):
"""Instantiates the Factorization-supported Neural Network architecture.
:param feature_dim_dict: dict,to indicate sparse field and dense field like {'sparse':{'field_1':4,'field_2':3,'field_3':2},'dense':['field_4','field_5']}
:param embedding_size: positive integer,sparse feature embedding_size
:param dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of deep net
:param l2_reg_embedding: float. L2 regularizer strength applied to embedding vector
:param l2_reg_linear: float. L2 regularizer strength applied to linear weight
:param l2_reg_dnn: float . L2 regularizer strength applied to DNN
:param init_std: float,to use as the initialize std of embedding vector
:param seed: integer ,to use as random seed.
:param dnn_dropout: float in [0,1), the probability we will drop out a given DNN coordinate.
:param dnn_activation: Activation function to use in DNN
:param task: str, ``"binary"`` for binary logloss or ``"regression"`` for regression loss
:return: A Keras model instance.
"""
check_feature_config_dict(feature_dim_dict)
deep_emb_list, linear_emb_list, dense_input_dict, inputs_list = preprocess_input_embedding(
feature_dim_dict,
embedding_size,
l2_reg_embedding,
l2_reg_linear,
init_std,
seed,
create_linear_weight=True)
linear_logit = get_linear_logit(linear_emb_list, dense_input_dict,
l2_reg_linear)
deep_input = tf.keras.layers.Flatten()(concat_fun(deep_emb_list))
deep_out = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn, dnn_dropout,
False, seed)(deep_input)
deep_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(deep_out)
final_logit = tf.keras.layers.add([deep_logit, linear_logit])
output = PredictionLayer(task)(final_logit)
model = tf.keras.models.Model(inputs=inputs_list, outputs=output)
return model
def DeepFM(feature_dim_dict,
embedding_size=8,
use_fm=True,
dnn_hidden_units=(128, 128),
l2_reg_linear=0.00001,
l2_reg_embedding=0.00001,
l2_reg_dnn=0,
init_std=0.0001,
seed=1024,
dnn_dropout=0,
dnn_activation='relu',
dnn_use_bn=False,
task='binary'):
"""Instantiates the DeepFM Network architecture.
:param feature_dim_dict: dict,to indicate sparse field and dense field like {'sparse':{'field_1':4,'field_2':3,'field_3':2},'dense':['field_4','field_5']}
:param embedding_size: positive integer,sparse feature embedding_size
:param use_fm: bool,use FM part or not
:param dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of DNN
: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_dnn: float. L2 regularizer strength applied to DNN
:param init_std: float,to use as the initialize std of embedding vector
:param seed: integer ,to use as random seed.
:param dnn_dropout: float in [0,1), the probability we will drop out a given DNN coordinate.
:param dnn_activation: Activation function to use in DNN
:param dnn_use_bn: bool. Whether use BatchNormalization before activation or not in DNN
:param task: str, ``"binary"`` for binary logloss or ``"regression"`` for regression loss
:return: A Keras model instance.
"""
check_feature_config_dict(feature_dim_dict)
deep_emb_list, linear_emb_list, dense_input_dict, inputs_list = preprocess_input_embedding(
feature_dim_dict,
embedding_size,
l2_reg_embedding,
l2_reg_linear,
init_std,
seed,
create_linear_weight=True)
linear_logit = get_linear_logit(linear_emb_list, dense_input_dict,
l2_reg_linear) # 各种输入线性转化并相加的结果
fm_input = concat_fun(deep_emb_list,
axis=1) # 各种特征进行embedding之后再拼接 (?,X,embedding_size)
deep_input = tf.keras.layers.Flatten()(fm_input) # (?,X*embedding_size)
fm_out = FM()(fm_input)
deep_out = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn, dnn_dropout,
dnn_use_bn, seed)(deep_input)
deep_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(deep_out)
if len(dnn_hidden_units) == 0 and use_fm == False: # only linear
final_logit = linear_logit
elif len(dnn_hidden_units) == 0 and use_fm == True: # linear + FM
final_logit = tf.keras.layers.add([linear_logit, fm_out])
elif len(dnn_hidden_units) > 0 and use_fm == False: # linear + Deep
final_logit = tf.keras.layers.add([linear_logit, deep_logit])
elif len(dnn_hidden_units) > 0 and use_fm == True: # linear + FM + Deep
final_logit = tf.keras.layers.add([linear_logit, fm_out, deep_logit])
else:
raise NotImplementedError
output = PredictionLayer(task)(final_logit)
model = tf.keras.models.Model(inputs=inputs_list, outputs=output)
return model
def DCN(
feature_dim_dict,
embedding_size='auto',
cross_num=2,
dnn_hidden_units=(
128,
128,
),
l2_reg_embedding=1e-5,
l2_reg_cross=1e-5,
l2_reg_dnn=0,
init_std=0.0001,
seed=1024,
dnn_dropout=0,
dnn_use_bn=False,
dnn_activation='relu',
task='binary',
):
"""Instantiates the Deep&Cross Network architecture.
:param feature_dim_dict: dict,to indicate sparse field and dense field like {'sparse':{'field_1':4,'field_2':3,'field_3':2},'dense':['field_4','field_5']}
:param embedding_size: positive int or str,sparse feature embedding_size.If set to "auto",it will be 6*pow(cardinality,025)
:param cross_num: positive integet,cross layer number
:param dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of DNN
:param l2_reg_embedding: float. L2 regularizer strength applied to embedding vector
:param l2_reg_cross: float. L2 regularizer strength applied to cross net
:param l2_reg_dnn: float. L2 regularizer strength applied to DNN
:param init_std: float,to use as the initialize std of embedding vector
:param seed: integer ,to use as random seed.
: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 DNN
:param dnn_activation: Activation function to use in DNN
:param task: str, ``"binary"`` for binary logloss or ``"regression"`` for regression loss
:return: A Keras model instance.
"""
if len(dnn_hidden_units) == 0 and cross_num == 0:
raise ValueError("Either hidden_layer or cross layer 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,
create_linear_weight=False)
deep_input = tf.keras.layers.Flatten()(concat_fun(deep_emb_list))
if len(dnn_hidden_units) > 0 and cross_num > 0: # Deep & Cross
deep_out = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn,
dnn_dropout, dnn_use_bn, seed)(deep_input)
cross_out = CrossNet(cross_num, l2_reg=l2_reg_cross)(deep_input)
stack_out = tf.keras.layers.Concatenate()([cross_out, deep_out])
final_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(stack_out)
elif len(dnn_hidden_units) > 0: # Only Deep
deep_out = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn,
dnn_dropout, dnn_use_bn, seed)(deep_input)
final_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(deep_out)
elif cross_num > 0: # Only Cross
cross_out = CrossNet(cross_num, l2_reg=l2_reg_cross)(deep_input)
final_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(cross_out)
else: # Error
raise NotImplementedError
output = PredictionLayer(task)(final_logit)
model = tf.keras.models.Model(inputs=inputs_list, outputs=output)
return model
def xDeepFM(
feature_dim_dict,
embedding_size=8,
dnn_hidden_units=(256, 256),
cin_layer_size=(
128,
128,
),
cin_split_half=True,
cin_activation='relu',
l2_reg_linear=0.00001,
l2_reg_embedding=0.00001,
l2_reg_dnn=0,
l2_reg_cin=0,
init_std=0.0001,
seed=1024,
dnn_dropout=0,
dnn_activation='relu',
dnn_use_bn=False,
task='binary',
):
"""Instantiates the xDeepFM architecture.
:param feature_dim_dict: dict,to indicate sparse field and dense field like {'sparse':{'field_1':4,'field_2':3,'field_3':2},'dense':['field_4','field_5']}
:param embedding_size: positive integer,sparse feature embedding_size
:param dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of deep net
:param cin_layer_size: list,list of positive integer or empty list, the feature maps in each hidden layer of Compressed Interaction Network
:param cin_split_half: bool.if set to True, half of the feature maps in each hidden will connect to output unit
:param cin_activation: activation function used on feature maps
:param l2_reg_linear: float. L2 regularizer strength applied to linear part
:param l2_reg_embedding: L2 regularizer strength applied to embedding vector
:param l2_reg_dnn: L2 regularizer strength applied to deep net
:param l2_reg_cin: L2 regularizer strength applied to CIN.
:param init_std: float,to use as the initialize std of embedding vector
:param seed: integer ,to use as random seed.
:param dnn_dropout: float in [0,1), the probability we will drop out a given DNN coordinate.
:param dnn_activation: Activation function to use in DNN
:param dnn_use_bn: bool. Whether use BatchNormalization before activation or not in DNN
:param task: str, ``"binary"`` for binary logloss or ``"regression"`` for regression loss
:return: A Keras model instance.
"""
check_feature_config_dict(feature_dim_dict)
deep_emb_list, linear_emb_list, dense_input_dict, inputs_list = preprocess_input_embedding(
feature_dim_dict,
embedding_size,
l2_reg_embedding,
l2_reg_linear,
init_std,
seed,
create_linear_weight=True)
linear_logit = get_linear_logit(linear_emb_list, dense_input_dict,
l2_reg_linear)
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,
l2_reg_cin, seed)(fm_input)
exFM_logit = tf.keras.layers.Dense(
1,
activation=None,
)(exFM_out)
deep_input = tf.keras.layers.Flatten()(fm_input)
deep_out = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn, dnn_dropout,
dnn_use_bn, seed)(deep_input)
deep_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(deep_out)
if len(dnn_hidden_units) == 0 and len(cin_layer_size) == 0: # only linear
final_logit = linear_logit
elif len(
dnn_hidden_units) == 0 and len(cin_layer_size) > 0: # linear + CIN
final_logit = tf.keras.layers.add([linear_logit, exFM_logit])
elif len(dnn_hidden_units) > 0 and len(
cin_layer_size) == 0: # linear + Deep
final_logit = tf.keras.layers.add([linear_logit, deep_logit])
elif len(dnn_hidden_units) > 0 and len(
cin_layer_size) > 0: # linear + CIN + Deep
final_logit = tf.keras.layers.add(
[linear_logit, deep_logit, exFM_logit])
else:
raise NotImplementedError
output = PredictionLayer(task)(final_logit)
model = tf.keras.models.Model(inputs=inputs_list, outputs=output)
return model
def NFFM(
feature_dim_dict,
embedding_size=4,
dnn_hidden_units=(128, 128),
l2_reg_embedding=1e-5,
l2_reg_linear=1e-5,
l2_reg_dnn=0,
dnn_dropout=0,
init_std=0.0001,
seed=1024,
include_linear=True,
use_bn=True,
reduce_sum=False,
task='binary',
):
"""Instantiates the Field-aware Neural Factorization Machine architecture.
:param feature_dim_dict: dict,to indicate sparse field and dense field like {'sparse':{'field_1':4,'field_2':3,'field_3':2},'dense':['field_4','field_5']}
:param embedding_size: positive integer,sparse feature embedding_size
:param dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of deep net
:param l2_reg_embedding: float. L2 regularizer strength applied to embedding vector
:param l2_reg_linear: float. L2 regularizer strength applied to linear part.
:param l2_reg_dnn: float . L2 regularizer strength applied to DNN
:param init_std: float,to use as the initialize std of embedding vector
:param seed: integer ,to use as random seed.
:param dnn_dropout: float in [0,1), the probability we will drop out a given DNN coordinate.
:param include_linear: bool,whether include linear term or not
:param use_bn: bool,whether use bn after ffm out or not
:param reduce_sum: bool,whether apply reduce_sum on cross vector
: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 'sequence' in feature_dim_dict and len(
feature_dim_dict['sequence']) > 0:
raise ValueError("now sequence input is not supported in NFFM"
) #TODO:support sequence input
sparse_input_dict, dense_input_dict = create_singlefeat_inputdict(
feature_dim_dict)
sparse_embedding, dense_embedding, linear_embedding = create_embedding_dict(
feature_dim_dict,
embedding_size,
init_std,
seed,
l2_reg_embedding,
l2_reg_linear,
)
embed_list = []
for i, j in itertools.combinations(feature_dim_dict['sparse'], 2):
i_input = sparse_input_dict[i.name]
if i.hash_flag:
i_input = Hash(i.dimension)(i_input)
j_input = sparse_input_dict[j.name]
if j.hash_flag:
j_input = Hash(j.dimension)(j_input)
element_wise_prod = multiply([
sparse_embedding[i.name][j.name](i_input),
sparse_embedding[j.name][i.name](j_input)
])
if reduce_sum:
element_wise_prod = Lambda(lambda element_wise_prod: K.sum(
element_wise_prod, axis=-1))(element_wise_prod)
embed_list.append(element_wise_prod)
for i, j in itertools.combinations(feature_dim_dict['dense'], 2):
element_wise_prod = multiply([
dense_embedding[i.name][j.name](dense_input_dict[i.name]),
dense_embedding[j.name][i.name](dense_input_dict[j.name])
])
if reduce_sum:
element_wise_prod = Lambda(lambda element_wise_prod: K.sum(
element_wise_prod, axis=-1))(element_wise_prod)
embed_list.append(
Lambda(lambda x: K.expand_dims(x, axis=1))(element_wise_prod))
for i in feature_dim_dict['sparse']:
i_input = sparse_input_dict[i.name]
if i.hash_flag:
i_input = Hash(i.dimension)(i_input)
for j in feature_dim_dict['dense']:
element_wise_prod = multiply([
sparse_embedding[i.name][j.name](i_input),
dense_embedding[j.name][i.name](dense_input_dict[j.name])
])
if reduce_sum:
element_wise_prod = Lambda(lambda element_wise_prod: K.sum(
element_wise_prod, axis=-1))(element_wise_prod)
embed_list.append(element_wise_prod)
ffm_out = tf.keras.layers.Flatten()(concat_fun(embed_list, axis=1))
if use_bn:
ffm_out = tf.keras.layers.BatchNormalization()(ffm_out)
ffm_out = DNN(dnn_hidden_units,
l2_reg=l2_reg_dnn,
dropout_rate=dnn_dropout)(ffm_out)
final_logit = Dense(1, use_bias=False)(ffm_out)
linear_emb_list = get_embedding_vec_list(linear_embedding,
sparse_input_dict,
feature_dim_dict['sparse'])
linear_logit = get_linear_logit(linear_emb_list, dense_input_dict,
l2_reg_linear)
if include_linear:
final_logit = add([final_logit, linear_logit])
output = PredictionLayer(task)(final_logit)
inputs_list = get_inputs_list([sparse_input_dict, dense_input_dict])
model = Model(inputs=inputs_list, outputs=output)
return model
def PNN(feature_dim_dict,
embedding_size=8,
dnn_hidden_units=(128, 128),
l2_reg_embedding=1e-5,
l2_reg_dnn=0,
init_std=0.0001,
seed=1024,
dnn_dropout=0,
dnn_activation='relu',
use_inner=True,
use_outter=False,
kernel_type='mat',
task='binary'):
"""Instantiates the Product-based Neural Network architecture.
:param feature_dim_dict: dict,to indicate sparse field and dense field like {'sparse':{'field_1':4,'field_2':3,'field_3':2},'dense':['field_4','field_5']}
:param embedding_size: positive integer,sparse feature embedding_size
:param dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of deep net
:param l2_reg_embedding: float . L2 regularizer strength applied to embedding vector
:param l2_reg_dnn: float. L2 regularizer strength applied to DNN
:param init_std: float,to use as the initialize std of embedding vector
:param seed: integer ,to use as random seed.
:param dnn_dropout: float in [0,1), the probability we will drop out a given DNN coordinate.
:param dnn_activation: Activation function to use in DNN
:param use_inner: bool,whether use inner-product or not.
:param use_outter: bool,whether use outter-product or not.
:param kernel_type: str,kernel_type used in outter-product,can be ``'mat'`` , ``'vec'`` or ``'num'``
:param task: str, ``"binary"`` for binary logloss or ``"regression"`` for regression loss
:return: A Keras whole_model instance.
"""
check_feature_config_dict(feature_dim_dict)
if kernel_type not in ['mat', 'vec', 'num']:
raise ValueError("kernel_type must be mat,vec or num")
deep_emb_list, _, _, inputs_list = preprocess_input_embedding(
feature_dim_dict,
embedding_size,
l2_reg_embedding,
0,
init_std,
seed,
create_linear_weight=False)
inner_product = tf.keras.layers.Flatten()(
InnerProductLayer()(deep_emb_list))
outter_product = OutterProductLayer(kernel_type)(deep_emb_list)
# ipnn deep input
linear_signal = tf.keras.layers.Reshape(
[len(deep_emb_list) * embedding_size])(concat_fun(deep_emb_list))
if use_inner and use_outter:
deep_input = tf.keras.layers.Concatenate()(
[linear_signal, inner_product, outter_product])
elif use_inner:
deep_input = tf.keras.layers.Concatenate()(
[linear_signal, inner_product])
elif use_outter:
deep_input = tf.keras.layers.Concatenate()(
[linear_signal, outter_product])
else:
deep_input = linear_signal
deep_out = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn, dnn_dropout,
False, seed)(deep_input)
deep_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(deep_out)
output = PredictionLayer(task)(deep_logit)
model = tf.keras.models.Model(inputs=inputs_list, outputs=output)
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 whole_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 AutoInt(
feature_dim_dict,
embedding_size=8,
att_layer_num=3,
att_embedding_size=8,
att_head_num=2,
att_res=True,
dnn_hidden_units=(256, 256),
dnn_activation='relu',
l2_reg_dnn=0,
l2_reg_embedding=1e-5,
dnn_use_bn=False,
dnn_dropout=0,
init_std=0.0001,
seed=1024,
task='binary',
):
"""Instantiates the AutoInt Network architecture.
:param feature_dim_dict: dict,to indicate sparse field and dense field like {'sparse':{'field_1':4,'field_2':3,'field_3':2},'dense':['field_4','field_5']}
:param embedding_size: positive integer,sparse feature embedding_size
:param att_layer_num: int.The InteractingLayer number to be used.
:param att_embedding_size: int.The embedding size in multi-head self-attention network.
:param att_head_num: int.The head number in multi-head self-attention network.
:param att_res: bool.Whether or not use standard residual connections before output.
: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_use_bn: bool. Whether use BatchNormalization before activation or not in DNN
: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 whole_model instance.
"""
if len(dnn_hidden_units) <= 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,
create_linear_weight=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))
if len(dnn_hidden_units
) > 0 and att_layer_num > 0: # Deep & Interacting Layer
deep_out = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn,
dnn_dropout, dnn_use_bn, seed)(deep_input)
stack_out = tf.keras.layers.Concatenate()([att_output, deep_out])
final_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(stack_out)
elif len(dnn_hidden_units) > 0: # Only Deep
deep_out = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn,
dnn_dropout, dnn_use_bn, seed)(deep_input)
final_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(deep_out)
elif att_layer_num > 0: # Only Interacting Layer
final_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(att_output)
else: # Error
raise NotImplementedError
output = PredictionLayer(task)(final_logit)
model = tf.keras.models.Model(inputs=inputs_list, outputs=output)
return model
def DIEN(feature_dim_dict, seq_feature_list, embedding_size=8, hist_len_max=16,
gru_type="GRU", use_negsampling=False, alpha=1.0, use_bn=False, dnn_hidden_units=(200, 80),
dnn_activation='relu',
att_hidden_units=(64, 16), att_activation="dice", att_weight_normalization=True,
l2_reg_dnn=0, l2_reg_embedding=1e-5, 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 gru_type: str,can be GRU AIGRU AUGRU AGRU
:param use_negsampling: bool, whether or not use negtive sampling
:param alpha: float ,weight of auxiliary_loss
: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 att_hidden_units: 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, 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"])}
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)
deep_input_emb = concat_fun(deep_input_emb_list)
if use_negsampling:
neg_user_behavior_input = OrderedDict()
for i, feat in enumerate(seq_feature_list):
neg_user_behavior_input[feat] = Input(shape=(hist_len_max,), name='neg_seq_' + str(i) + '-' + feat)
neg_uiseq_embed_list = get_embedding_vec_list(sparse_embedding_dict,neg_user_behavior_input,feature_dim_dict["sparse"],seq_feature_list,)
# [sparse_embedding_dict[feat](
# neg_user_behavior_input[feat]) for feat in seq_feature_list]
neg_concat_behavior = concat_fun(neg_uiseq_embed_list)
else:
neg_concat_behavior = None
hist, aux_loss_1 = interest_evolution(keys_emb, query_emb, user_behavior_length, gru_type=gru_type,
use_neg=use_negsampling, neg_concat_behavior=neg_concat_behavior,
embedding_size=embedding_size, att_hidden_size=att_hidden_units,
att_activation=att_activation,
att_weight_normalization=att_weight_normalization, )
deep_input_emb = Concatenate()([deep_input_emb, hist])
deep_input_emb = tf.keras.layers.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, 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])
if use_negsampling:
model_input_list += list(neg_user_behavior_input.values())
model_input_list += [user_behavior_length]
model = tf.keras.models.Model(inputs=model_input_list, outputs=output)
if use_negsampling:
model.add_loss(alpha * aux_loss_1)
tf.keras.backend.get_session().run(tf.global_variables_initializer())
return model
def FGCNN(
feature_dim_dict,
embedding_size=8,
conv_kernel_width=(7, 7, 7, 7),
conv_filters=(14, 16, 18, 20),
new_maps=(3, 3, 3, 3),
pooling_width=(2, 2, 2, 2),
dnn_hidden_units=(128, ),
l2_reg_embedding=1e-5,
l2_reg_dnn=0,
dnn_dropout=0,
init_std=0.0001,
seed=1024,
task='binary',
):
"""Instantiates the Feature Generation by Convolutional Neural Network architecture.
:param feature_dim_dict: dict,to indicate sparse field and dense field like {'sparse':{'field_1':4,'field_2':3,'field_3':2},'dense':['field_4','field_5']}
:param embedding_size: positive integer,sparse feature embedding_size
:param conv_kernel_width: list,list of positive integer or empty list,the width of filter in each conv layer.
:param conv_filters: list,list of positive integer or empty list,the number of filters in each conv layer.
:param new_maps: list, list of positive integer or empty list, the feature maps of generated features.
:param pooling_width: list, list of positive integer or empty list,the width of pooling layer.
:param dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of deep net.
:param l2_reg_embedding: float. L2 regularizer strength applied to embedding vector
:param l2_reg_dnn: float. L2 regularizer strength applied to DNN
: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 whole_model instance.
"""
check_feature_config_dict(feature_dim_dict)
if not (len(conv_kernel_width) == len(conv_filters) == len(new_maps) ==
len(pooling_width)):
raise ValueError(
"conv_kernel_width,conv_filters,new_maps and pooling_width must have same length"
)
deep_emb_list, fg_deep_emb_list, _, inputs_list = preprocess_input_embedding(
feature_dim_dict, embedding_size, l2_reg_embedding, 0, init_std, seed,
False)
fg_input = concat_fun(fg_deep_emb_list, axis=1)
origin_input = concat_fun(deep_emb_list, axis=1)
if len(conv_filters) > 0:
new_features = FGCNNLayer(conv_filters, conv_kernel_width, new_maps,
pooling_width)(fg_input)
combined_input = concat_fun([origin_input, new_features], axis=1)
else:
combined_input = origin_input
inner_product = tf.keras.layers.Flatten()(InnerProductLayer()(
tf.keras.layers.Lambda(unstack,
mask=[None] *
combined_input.shape[1].value)(combined_input)))
linear_signal = tf.keras.layers.Flatten()(combined_input)
dnn_input = tf.keras.layers.Concatenate()([linear_signal, inner_product])
dnn_input = tf.keras.layers.Flatten()(dnn_input)
final_logit = DNN(dnn_hidden_units,
dropout_rate=dnn_dropout,
l2_reg=l2_reg_dnn)(dnn_input)
final_logit = tf.keras.layers.Dense(1, use_bias=False)(final_logit)
output = PredictionLayer(task)(final_logit)
model = tf.keras.models.Model(inputs=inputs_list, outputs=output)
return model
