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 DeepFM(linear_feature_columns,
dnn_feature_columns,
embedding_size=8,
use_fm=True,
use_only_dnn=False,
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 linear_feature_columns: An iterable containing all the features used by linear part of the model.
:param dnn_feature_columns: An iterable containing all the features used by deep part of the model.
: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.
"""
features = build_input_features(linear_feature_columns +
dnn_feature_columns)
inputs_list = list(features.values())
sparse_embedding_list, dense_value_list = input_from_feature_columns(
features, dnn_feature_columns, embedding_size, l2_reg_embedding,
init_std, seed)
linear_logit = get_linear_logit(features,
linear_feature_columns,
l2_reg=l2_reg_linear,
init_std=init_std,
seed=seed,
prefix='linear')
fm_input = concat_fun(sparse_embedding_list, axis=1)
fm_logit = FM()(fm_input)
dnn_input = combined_dnn_input(sparse_embedding_list, dense_value_list)
# dnn_out = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn, dnn_dropout,
# dnn_use_bn, seed)(dnn_input)
dnn_out_1 = Dense(128, dnn_activation)(dnn_input)
dnn_out_2 = Dense(128, dnn_activation)(dnn_out_1)
dnn_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(dnn_out_2)
if use_only_dnn == True:
final_logit = dnn_logit
elif 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_logit])
elif len(dnn_hidden_units) > 0 and use_fm == False: # linear + Deep
final_logit = tf.keras.layers.add([linear_logit, dnn_logit])
elif len(dnn_hidden_units) > 0 and use_fm == True: # linear + FM + Deep
final_logit = tf.keras.layers.add([linear_logit, fm_logit, dnn_logit])
else:
raise NotImplementedError
output = PredictionLayer(task)(final_logit)
model = tf.keras.models.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,
bias_encoding=False):
check_feature_config_dict(feature_dim_dict)
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,
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 DSSM(user_feature_columns,
item_feature_columns,
user_dnn_hidden_units=(64, 32),
item_dnn_hidden_units=(64, 32),
dnn_activation='tanh',
dnn_use_bn=False,
l2_reg_dnn=0,
l2_reg_embedding=1e-6,
dnn_dropout=0,
init_std=0.0001,
seed=1024,
metric='cos'):
embedding_matrix_dict = create_embedding_matrix(user_feature_columns +
item_feature_columns,
l2_reg_embedding,
init_std,
seed,
seq_mask_zero=True)
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,
init_std,
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())
item_sparse_embedding_list, item_dense_value_list = input_from_feature_columns(
item_features,
item_feature_columns,
l2_reg_embedding,
init_std,
seed,
embedding_matrix_dict=embedding_matrix_dict)
item_dnn_input = combined_dnn_input(item_sparse_embedding_list,
item_dense_value_list)
user_dnn_out = DNN(
user_dnn_hidden_units,
dnn_activation,
l2_reg_dnn,
dnn_dropout,
dnn_use_bn,
seed,
)(user_dnn_input)
item_dnn_out = DNN(item_dnn_hidden_units, dnn_activation, l2_reg_dnn,
dnn_dropout, dnn_use_bn, seed)(item_dnn_input)
score = Similarity(type=metric)([user_dnn_out, item_dnn_out])
output = PredictionLayer("binary", False)(score)
model = Model(inputs=user_inputs_list + item_inputs_list, outputs=output)
plot_model(model, to_file='dnn.png', show_shapes=True)
print("go")
model.__setattr__("user_input", user_inputs_list)
model.__setattr__("item_input", item_inputs_list)
model.__setattr__("user_embedding", user_dnn_out)
model.__setattr__("item_embedding", item_dnn_out)
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
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 MMOE(dnn_feature_columns,
num_tasks,
tasks,
num_experts=4,
expert_dim=8,
dnn_hidden_units=(128, 128),
l2_reg_embedding=1e-5,
l2_reg_dnn=0,
task_dnn_units=None,
seed=1024,
dnn_dropout=0,
dnn_activation='relu'):
"""Instantiates the Multi-gate Mixture-of-Experts architecture.
:param dnn_feature_columns: An iterable containing all the features used by deep part of the model.
:param num_tasks: integer, number of tasks, equal to number of outputs, must be greater than 1.
:param tasks: list of str, indicating the loss of each tasks, ``"binary"`` for binary logloss, ``"regression"`` for regression loss. e.g. ['binary', 'regression']
:param num_experts: integer, number of experts.
:param expert_dim: integer, the hidden units of each expert.
:param dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of shared-bottom DNN
:param l2_reg_embedding: float. L2 regularizer strength applied to embedding vector
:param l2_reg_dnn: float. L2 regularizer strength applied to DNN
:param task_dnn_units: list,list of positive integer or empty list, the layer number and units in each layer of task-specific DNN
: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
:return: a Keras model instance
"""
if num_tasks <= 1:
raise ValueError("num_tasks must be greater than 1")
if len(tasks) != num_tasks:
raise ValueError("num_tasks must be equal to the length of tasks")
for task in tasks:
if task not in ['binary', 'regression']:
raise ValueError(
"task must be binary or regression, {} is illegal".format(
task))
features = build_input_features(dnn_feature_columns)
inputs_list = list(features.values())
sparse_embedding_list, dense_value_list = input_from_feature_columns(
features, dnn_feature_columns, l2_reg_embedding, seed)
dnn_input = combined_dnn_input(sparse_embedding_list, dense_value_list)
dnn_out = DNN(dnn_hidden_units,
dnn_activation,
l2_reg_dnn,
dnn_dropout,
False,
seed=seed)(dnn_input)
mmoe_outs = MMOELayer(num_tasks, num_experts, expert_dim)(dnn_out)
if task_dnn_units != None:
mmoe_outs = [
DNN(task_dnn_units,
dnn_activation,
l2_reg_dnn,
dnn_dropout,
False,
seed=seed)(mmoe_out) for mmoe_out in mmoe_outs
]
task_outputs = []
for mmoe_out, task in zip(mmoe_outs, tasks):
logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(mmoe_out)
output = PredictionLayer(task)(logit)
task_outputs.append(output)
model = tf.keras.models.Model(inputs=inputs_list, outputs=task_outputs)
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 Baseline(feature_dim_dict,
attention_feature_name=None,
with_linear=False,
embedding_size=5,
dnn_hidden_units=(135, 67),
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 Baseline 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 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,
use_var_attention=(
True if attention_feature_name else False),
attention_feature_name=attention_feature_name)
linear_logit = get_linear_logit(linear_emb_list, dense_input_dict,
l2_reg_linear)
deep_input = concat_fun(deep_emb_list, axis=1)
deep_input = tf.keras.layers.Flatten()(deep_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: # only linear
final_logit = linear_logit
elif len(dnn_hidden_units) > 0 and with_linear: # linear + Deep
final_logit = tf.keras.layers.add([linear_logit, deep_logit])
elif len(dnn_hidden_units) > 0 and not with_linear:
final_logit = deep_logit
else:
raise NotImplementedError
output = PredictionLayer(task)(final_logit)
model = tf.keras.models.Model(inputs=inputs_list, outputs=output)
return model
def DSSM(user_feature_columns,
item_feature_columns,
user_dnn_hidden_units=(64, 32),
item_dnn_hidden_units=(64, 32),
dnn_activation='tanh',
dnn_use_bn=False,
l2_reg_dnn=0,
l2_reg_embedding=1e-6,
dnn_dropout=0,
init_std=0.0001,
seed=1024,
metric='cos'):
"""Instantiates the Deep Structured Semantic 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 user_dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of user tower
:param item_dnn_hidden_units: list,list of positive integer or empty list, the layer number and units in each layer of item 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 init_std: float,to use as the initialize std of embedding vector
:param seed: integer ,to use as random seed.
:param metric: str, ``"cos"`` for cosine or ``"ip"`` for inner product
:return: A Keras model instance.
"""
embedding_matrix_dict = create_embedding_matrix(user_feature_columns +
item_feature_columns,
l2_reg_embedding,
init_std,
seed,
seq_mask_zero=True)
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,
init_std,
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())
item_sparse_embedding_list, item_dense_value_list = input_from_feature_columns(
item_features,
item_feature_columns,
l2_reg_embedding,
init_std,
seed,
embedding_matrix_dict=embedding_matrix_dict)
item_dnn_input = combined_dnn_input(item_sparse_embedding_list,
item_dense_value_list)
user_dnn_out = DNN(
user_dnn_hidden_units,
dnn_activation,
l2_reg_dnn,
dnn_dropout,
dnn_use_bn,
seed,
)(user_dnn_input)
item_dnn_out = DNN(item_dnn_hidden_units, dnn_activation, l2_reg_dnn,
dnn_dropout, dnn_use_bn, seed)(item_dnn_input)
score = Similarity(type=metric)([user_dnn_out, item_dnn_out])
output = PredictionLayer("binary", False)(score)
model = Model(inputs=user_inputs_list + item_inputs_list, outputs=output)
model.__setattr__("user_input", user_inputs_list)
model.__setattr__("item_input", item_inputs_list)
model.__setattr__("user_embedding", user_dnn_out)
model.__setattr__("item_embedding", item_dnn_out)
return model
def xDeepFM_MTL(linear_feature_columns,
dnn_feature_columns,
dnn_hidden_units=(256, 256),
task_net_size=(128, ),
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,
seed=1024,
dnn_dropout=0,
dnn_activation='relu',
dnn_use_bn=False,
task='binary'):
"""Instantiates the xDeepFM architecture.
:param linear_feature_columns: An iterable containing all the features used by linear part of the model.
:param dnn_feature_columns: An iterable containing all the features used by deep part of the model.
: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 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.
"""
features = build_input_features(linear_feature_columns +
dnn_feature_columns)
inputs_list = list(features.values())
linear_logit = get_linear_logit(features,
linear_feature_columns,
seed=seed,
prefix='linear',
l2_reg=l2_reg_linear)
sparse_embedding_list, dense_value_list = input_from_feature_columns(
features, dnn_feature_columns, l2_reg_embedding, seed)
fm_input = concat_func(sparse_embedding_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, kernel_initializer=tf.keras.initializers.glorot_normal(seed))(
exFM_out)
dnn_input = combined_dnn_input(sparse_embedding_list, dense_value_list)
dnn_output = DNN(dnn_hidden_units,
dnn_activation,
l2_reg_dnn,
dnn_dropout,
dnn_use_bn,
seed=seed)(dnn_input)
finish_out = DNN(task_net_size)(dnn_output)
finish_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(finish_out)
like_out = DNN(task_net_size)(dnn_output)
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('binary', name='finish')(finish_logit)
output_like = PredictionLayer('binary', name='like')(like_logit)
model = tf.keras.models.Model(inputs=inputs_list,
outputs=[output_finish, output_like])
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-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 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 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
def DeepFM(linear_feature_columns,
dnn_feature_columns,
embedding_size=8,
use_fm=True,
only_dnn=False,
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 linear_feature_columns: An iterable containing all the features used by linear part of the model.
:param dnn_feature_columns: An iterable containing all the features used by deep part of the model.
: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.
"""
## 为每个特征创建Input[1,]； feature == > {'feature1': Input[1,], ...}
features = build_input_features(linear_feature_columns +
dnn_feature_columns)
## [Input1, Input2, ... ]
inputs_list = list(features.values())
sparse_embedding_list, dense_value_list = input_from_feature_columns(
features, dnn_feature_columns, embedding_size, l2_reg_embedding,
init_std, seed)
## [feature_1对应的embedding层，下连接对应feature1的Input[1,]层,...], [feature_1对应的Input[1,]层,...]
linear_logit = get_linear_logit(features,
linear_feature_columns,
l2_reg=l2_reg_linear,
init_std=init_std,
seed=seed,
prefix='linear')
## 线性变换层，没有激活函数
fm_input = concat_fun(sparse_embedding_list, axis=1)
## 稀疏embedding层concate在一起
fm_logit = FM()(fm_input)
## FM的二次项部分输出，不包含一次项和bias
dnn_input = combined_dnn_input(sparse_embedding_list, dense_value_list)
# dnn_out = Dense(128, dnn_activation, l2_reg_dnn, dnn_dropout,
# dnn_use_bn, seed)(dnn_input)
dnn_out = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn, dnn_dropout,
dnn_use_bn, seed)(dnn_input)
finish_out = Dense(128, dnn_activation,
kernel_regularizer=l2(l2_reg_dnn))(dnn_out)
finish_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(finish_out)
like_out = Dense(128, dnn_activation,
kernel_regularizer=l2(l2_reg_dnn))(dnn_out)
like_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(like_out)
dnn_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(dnn_out)
# if len(dnn_hidden_units) > 0 and only_dnn == True:
# final_logit = dnn_logit
# elif 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_logit])
# elif len(dnn_hidden_units) > 0 and use_fm == False: # linear + Deep
# final_logit = tf.keras.layers.add([linear_logit, dnn_logit])
# elif len(dnn_hidden_units) > 0 and use_fm == True: # linear + FM + Deep
# final_logit = tf.keras.layers.add([linear_logit, fm_logit, dnn_logit])
# else:
# raise NotImplementedError
# finish_logit = tf.keras.layers.add([linear_logit, fm_logit, finish_logit])
# like_logit = tf.keras.layers.add([linear_logit, fm_logit, like_logit])
output_finish = PredictionLayer('binary',
name='finish_output')(finish_logit)
output_like = PredictionLayer('binary', name='like_output')(like_logit)
model = tf.keras.models.Model(inputs=inputs_list,
outputs=[output_finish, output_like])
return model
def xDeepFM_MTL(
linear_feature_columns,
dnn_feature_columns,
embedding_size=8,
dnn_hidden_units=(256, 256),
cin_layer_size=(
256,
256,
),
cin_split_half=True,
init_std=0.0001,
l2_reg_dnn=0,
dnn_dropout=0,
dnn_activation='relu',
dnn_use_bn=False,
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')
features = build_input_features(linear_feature_columns +
dnn_feature_columns)
inputs_list = list(features.values())
sparse_embedding_list, dense_value_list = input_from_feature_columns(
features, dnn_feature_columns, embedding_size, l2_reg_embedding,
init_std, seed)
linear_logit = get_linear_logit(features,
linear_feature_columns,
l2_reg=l2_reg_linear,
init_std=init_std,
seed=seed,
prefix='linear')
fm_input = concat_fun(sparse_embedding_list, axis=1)
if len(cin_layer_size) > 0:
exFM_out = CIN(cin_layer_size, 'relu', cin_split_half, 0,
seed)(fm_input)
exFM_logit = tf.keras.layers.Dense(
1,
activation=None,
)(exFM_out)
dnn_input = combined_dnn_input(sparse_embedding_list, dense_value_list)
deep_out = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn, dnn_dropout,
dnn_use_bn, seed)(dnn_input)
like_out = DNN(task_net_size)(deep_out)
like_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(like_out)
like_logit = tf.keras.layers.add([linear_logit, like_logit, exFM_logit])
output_like = PredictionLayer('binary', name='like')(like_logit)
model = tf.keras.models.Model(inputs=inputs_list, outputs=output_like)
return model
def create_model(linear_feature_columns,
dnn_feature_columns,
fm_group=[DEFAULT_GROUP_NAME],
dnn_hidden_units=(128, 128),
l2_reg_linear=0.00001,
l2_reg_embedding=0.00001,
l2_reg_dnn=0,
seed=1024,
dnn_dropout=0,
dnn_activation='relu',
dnn_use_bn=False,
task='binary'):
K.clear_session()
#!################################################################################################################
inputs_all = [
# get_input_feature_layer(name = 'user_0',feature_shape = dense_feature_size),
# get_input_feature_layer(name = 'item_0',feature_shape = dense_feature_size),
get_input_feature_layer(name='user_1',
feature_shape=dense_feature_size),
get_input_feature_layer(name='item_1',
feature_shape=dense_feature_size)
]
# slotid_nettype
# layer_user_0 = inputs_all[0]
# layer_user_0 = K.expand_dims(layer_user_0, 1)
# layer_item_0 = inputs_all[1]
# layer_item_0 = K.expand_dims(layer_item_0, 1)
layer_user_1 = inputs_all[0]
layer_user_1 = K.expand_dims(layer_user_1, 1)
layer_item_1 = inputs_all[1]
layer_item_1 = K.expand_dims(layer_item_1, 1)
# cross_emb_out0 = cross_net(layer_user_0,layer_item_0)
cross_emb_out1 = cross_net(layer_user_1, layer_item_1)
# cross_emb_out = tf.keras.layers.concatenate([cross_emb_out0,cross_emb_out1])
cross_emb_out = tf.squeeze(cross_emb_out1, [1])
#!################################################################################################################
seq_inputs_dict = get_seq_input_layers(cols=arr_name_list)
inputs_all = inputs_all + list(seq_inputs_dict.values()) # 输入层list
masks = tf.equal(seq_inputs_dict['task_id'], 0)
# 普通序列+label序列
layers2concat = []
for index, col in enumerate(arr_name_list):
print(col, 'get embedding!')
emb_layer = get_emb_layer(col,
trainable=TRAINABLE_DICT[col],
emb_matrix=id_list_dict_emb_all[col][1])
x = emb_layer(seq_inputs_dict[col])
if conv1d_info_dict[col] > -1:
cov_layer = tf.keras.layers.Conv1D(filters=conv1d_info_dict[col],
kernel_size=1,
activation='relu')
x = cov_layer(x)
layers2concat.append(x)
x = keras.layers.concatenate(layers2concat)
#!################################################################################################################
#!mix1
x = trans_net(x, masks, hidden_unit=256)
max_pool = tf.keras.layers.GlobalMaxPooling1D()
average_pool = tf.keras.layers.GlobalAveragePooling1D()
xmaxpool = max_pool(x)
xmeanpool = average_pool(x)
trans_output = tf.keras.layers.concatenate([xmaxpool, xmeanpool])
#!################################################################################################################
#!mix2
features = build_input_features(linear_feature_columns +
dnn_feature_columns)
inputs_list = list(features.values())
linear_logit = get_linear_logit(features,
linear_feature_columns,
seed=seed,
prefix='linear',
l2_reg=l2_reg_linear)
group_embedding_dict, dense_value_list = input_from_feature_columns(
features,
dnn_feature_columns,
l2_reg_embedding,
seed,
support_group=True)
fm_logit = add_func([
FM()(concat_func(v, axis=1)) for k, v in group_embedding_dict.items()
if k in fm_group
])
dnn_input = combined_dnn_input(
list(chain.from_iterable(group_embedding_dict.values())),
dense_value_list)
mix = concatenate([cross_emb_out, trans_output, dnn_input],
axis=-1) # !#mix
dnn_output = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn, dnn_dropout,
dnn_use_bn, seed)(mix)
dnn_logit = tf.keras.layers.Dense(1, use_bias=False,
activation=None)(dnn_output)
final_logit = add_func([linear_logit, fm_logit, dnn_logit])
output = PredictionLayer(task)(final_logit)
#!################################################################################################################
model = Model(inputs=inputs_all + [features], outputs=[output])
print(model.summary())
return model
def DSSM(user_dnn_feature_columns,
item_dnn_feature_columns,
gamma=1,
dnn_use_bn=True,
dnn_hidden_units=(300, 300, 128),
dnn_activation='tanh',
l2_reg_dnn=0,
l2_reg_embedding=1e-6,
dnn_dropout=0,
init_std=0.0001,
seed=1024,
task='binary'):
"""Instantiates the Deep Structured Semantic Model architecture.
:param user_dnn_feature_columns:An iterable containing user's features used by deep part of the model.
:param item_dnn_feature_columns:An iterable containing item's the features used by deep part of the model.
:param gamma: smoothing factor in the softmax function for DSSM
: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 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.
"""
user_features = build_input_features(user_dnn_feature_columns)
user_inputs_list = list(user_features.values())
user_sparse_embedding_list, user_dense_value_list = input_from_feature_columns(
user_features, user_dnn_feature_columns, l2_reg_embedding, init_std,
seed)
user_dnn_input = combined_dnn_input(user_sparse_embedding_list,
user_dense_value_list)
item_features = build_input_features(item_dnn_feature_columns)
item_inputs_list = list(item_features.values())
item_sparse_embedding_list, item_dense_value_list = input_from_feature_columns(
item_features, item_dnn_feature_columns, l2_reg_embedding, init_std,
seed)
item_dnn_input = combined_dnn_input(item_sparse_embedding_list,
item_dense_value_list)
user_dnn_out = DNN(dnn_hidden_units,
dnn_activation,
l2_reg_dnn,
dnn_dropout,
dnn_use_bn,
seed,
name="user_embedding")(user_dnn_input)
item_dnn_out = DNN(dnn_hidden_units,
dnn_activation,
l2_reg_dnn,
dnn_dropout,
dnn_use_bn,
seed,
name="item_embedding")(item_dnn_input)
score = Cosine_Similarity(user_dnn_out, item_dnn_out, gamma=gamma)
output = PredictionLayer(task, False)(score)
model = Model(inputs=user_inputs_list + item_inputs_list, outputs=output)
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 DeepAutoInt(
linear_feature_columns,
dnn_feature_columns,
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_linear=1e-5,
l2_reg_embedding=1e-5,
l2_reg_dnn=0,
dnn_use_bn=False,
dnn_dropout=0,
seed=1024,
fm_group=[DEFAULT_GROUP_NAME],
task='binary',
):
"""Instantiates the AutoInt Network architecture.
:param linear_feature_columns: An iterable containing all the features used by linear part of the model.
:param dnn_feature_columns: An iterable containing all the features used by deep part of the model.
: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_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_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 seed: integer ,to use as random seed.
:param task: str, ``"binary"`` for binary logloss or ``"regression"`` for regression loss
:return: A Keras model instance.
"""
if len(dnn_hidden_units) <= 0 and att_layer_num <= 0:
raise ValueError("Either hidden_layer or att_layer_num must > 0")
features = build_input_features(dnn_feature_columns)
inputs_list = list(features.values())
linear_logit = get_linear_logit(features,
linear_feature_columns,
seed=seed,
prefix='linear',
l2_reg=l2_reg_linear)
group_embedding_dict, dense_value_list = input_from_feature_columns(
features,
dnn_feature_columns,
l2_reg_embedding,
seed,
support_group=True)
sparse_embedding_list = list(
chain.from_iterable(group_embedding_dict.values()))
fm_logit = add_func([
FM()(concat_func(v, axis=1)) for k, v in group_embedding_dict.items()
if k in fm_group
])
# sparse_embedding_list, dense_value_list = input_from_feature_columns(features, dnn_feature_columns,
# l2_reg_embedding, seed)
att_input = concat_func(sparse_embedding_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)
dnn_input = combined_dnn_input(sparse_embedding_list, dense_value_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=seed)(dnn_input)
stack_out = tf.keras.layers.Concatenate()([att_output, deep_out])
final_logit = tf.keras.layers.Dense(
1,
use_bias=False,
kernel_initializer=tf.keras.initializers.glorot_normal(seed))(
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=seed)(dnn_input)
final_logit = tf.keras.layers.Dense(
1,
use_bias=False,
kernel_initializer=tf.keras.initializers.glorot_normal(seed))(
deep_out)
elif att_layer_num > 0: # Only Interacting Layer
final_logit = tf.keras.layers.Dense(
1,
use_bias=False,
kernel_initializer=tf.keras.initializers.glorot_normal(seed))(
att_output)
else: # Error
raise NotImplementedError
# final_logit = tf.keras.layers.Dense(
# 1, use_bias=False, kernel_initializer=tf.keras.initializers.glorot_normal(seed))(att_output)
final_logit = add_func([linear_logit, fm_logit, final_logit])
output = PredictionLayer(task)(final_logit)
model = tf.keras.models.Model(inputs=inputs_list, outputs=output)
return model