def get_input(feature_dim_dict, seq_feature_list, seq_max_len):
sparse_input, dense_input = create_singlefeat_inputdict(feature_dim_dict)
user_behavior_input = OrderedDict()
for i, feat in enumerate(seq_feature_list):
user_behavior_input[feat] = Input(shape=(seq_max_len, ),
name='seq_' + str(i) + '-' + feat)
return sparse_input, dense_input, user_behavior_input
def preprocess_input_embedding(
feature_dim_dict,
embedding_size,
l2_reg_embedding,
l2_reg_linear,
init_std,
seed,
return_linear_logit=True,
):
sparse_input_dict, dense_input_dict = create_singlefeat_inputdict(
feature_dim_dict)
sequence_input_dict, sequence_input_len_dict, sequence_max_len_dict = create_varlenfeat_inputdict(
feature_dim_dict)
inputs_list, deep_emb_list, linear_emb_list = get_inputs_embedding(
feature_dim_dict,
embedding_size,
l2_reg_embedding,
l2_reg_linear,
init_std,
seed,
sparse_input_dict,
dense_input_dict,
sequence_input_dict,
sequence_input_len_dict,
sequence_max_len_dict,
return_linear_logit,
prefix='')
_, fg_deep_emb_list, _ = get_inputs_embedding(feature_dim_dict,
embedding_size,
l2_reg_embedding,
l2_reg_linear,
init_std,
seed,
sparse_input_dict,
dense_input_dict,
sequence_input_dict,
sequence_input_len_dict,
sequence_max_len_dict,
False,
prefix='fg')
if return_linear_logit:
linear_logit = get_linear_logit(linear_emb_list, dense_input_dict,
l2_reg_linear)
else:
linear_logit = None
return deep_emb_list, fg_deep_emb_list, linear_logit, inputs_list
def WDL(
deep_feature_dim_dict,
wide_feature_dim_dict,
embedding_size=8,
dnn_hidden_units=(128, 128),
l2_reg_linear=1e-5,
l2_reg_embedding=1e-5,
l2_reg_dnn=0,
init_std=0.0001,
seed=1024,
dnn_dropout=0,
dnn_activation='relu',
task='binary',
):
"""Instantiates the Wide&Deep Learning architecture.
:param deep_feature_dim_dict: dict,to indicate sparse field and dense field in deep part like {'sparse':{'field_1':4,'field_2':3,'field_3':2},'dense':['field_4','field_5']}
:param wide_feature_dim_dict: dict,to indicate sparse field and dense field in wide part 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 wide 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 task: str, ``"binary"`` for binary logloss or ``"regression"`` for regression loss
:return: A Keras model instance.
"""
if not isinstance(
deep_feature_dim_dict, dict
) or "sparse" not in deep_feature_dim_dict or "dense" not in deep_feature_dim_dict:
raise ValueError(
"feature_dim must be a dict like {'sparse':{'field_1':4,'field_2':3,'field_3':2},'dense':['field_5',]}"
)
sparse_input, dense_input, = create_singlefeat_inputdict(
deep_feature_dim_dict)
bias_sparse_input, bias_dense_input = create_singlefeat_inputdict(
wide_feature_dim_dict, 'bias')
sparse_embedding = create_embedding_dict(deep_feature_dim_dict,
embedding_size, init_std, seed,
l2_reg_embedding)
wide_linear_embedding = create_embedding_dict(wide_feature_dim_dict, 1,
init_std, seed,
l2_reg_linear, 'linear')
embed_list = get_embedding_vec_list(sparse_embedding, sparse_input,
deep_feature_dim_dict['sparse'])
deep_input = Concatenate()(
embed_list) if len(embed_list) > 1 else embed_list[0]
deep_input = Flatten()(deep_input)
if len(dense_input) > 0:
deep_input = Concatenate()([deep_input] + list(dense_input.values()))
deep_out = DNN(dnn_hidden_units, dnn_activation, l2_reg_dnn, dnn_dropout,
False, seed)(deep_input)
deep_logit = Dense(1, use_bias=False, activation=None)(deep_out)
final_logit = deep_logit
if len(wide_feature_dim_dict['dense']) + len(
wide_feature_dim_dict['sparse']) > 0:
if len(wide_feature_dim_dict['sparse']) > 0:
bias_embed_list = get_embedding_vec_list(
wide_linear_embedding, bias_sparse_input,
wide_feature_dim_dict['sparse'])
linear_term = add(bias_embed_list) if len(
bias_embed_list) > 1 else bias_embed_list[0]
final_logit = add([final_logit, linear_term])
if len(wide_feature_dim_dict['dense']) > 0:
wide_dense_term = Dense(
1, use_bias=False,
activation=None)(Concatenate()(list(bias_dense_input.values(
))) if len(bias_dense_input) > 1 else list(bias_dense_input.
values())[0])
final_logit = add([final_logit, wide_dense_term])
output = PredictionLayer(task)(final_logit)
inputs_list = get_inputs_list(
[sparse_input, dense_input, bias_sparse_input, bias_dense_input])
model = 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