def model_fn_sparse(features, labels, mode, params):
# hyper parameter
data_params = params['data_params']
field_size = data_params['field_size']
feature_size = data_params['feature_size']
embedding_size = data_params['embedding_size']
# extract feature
feat_ids = tf.reshape(features['feat_ids'],
shape=[-1, field_size]) # batch * field_size
feat_vals = tf.reshape(features['feat_vals'],
shape=[-1, field_size]) # batch * field_size
# extract embedding
with tf.variable_scope('extract_embedding'):
embedding_matrix = sparse_embedding(
feature_size,
embedding_size,
field_size,
feat_ids,
feat_vals,
add_summary=True) # (batch, field_size, embedding_size)
dense_input = tf.reshape(embedding_matrix,
[-1, field_size * embedding_size
]) # (batch, field_size * embedding_size)
# linear part
linear_output = sparse_linear(feature_size,
feat_ids,
feat_vals,
add_summary=True)
# Deep part
dense_output = stack_dense_layer(dense_input,
params['hidden_units'],
params['dropout_rate'],
params['batch_norm'],
mode,
add_summary=True)
# CIN part
cin_output = cin_layer(embedding_matrix, params['cin_layer_size'],
embedding_size, field_size)
# concat and output
with tf.variable_scope('output'):
y = tf.concat([dense_output, cin_output, linear_output], axis=1)
y = tf.layers.dense(y, units=1)
add_layer_summary('output', y)
return y
def model_fn_sparse(features, labels, mode, params):
# hyper parameter
data_params = params['data_params']
field_size = data_params['field_size']
feature_size = data_params['feature_size']
embedding_size = data_params['embedding_size']
# extract feature
feat_ids = tf.reshape(features['feat_ids'],
shape=[-1, field_size]) # batch * field_size
feat_vals = tf.reshape(features['feat_vals'],
shape=[-1, field_size]) # batch * field_size
# extract embedding
embedding_matrix = sparse_embedding(feature_size,
embedding_size,
field_size,
feat_ids,
feat_vals,
add_summary=True)
# linear output
linear_output = sparse_linear(feature_size,
feat_ids,
feat_vals,
add_summary=True)
with tf.variable_scope('BI_Pooling'):
sum_square = tf.pow(tf.reduce_sum(embedding_matrix, axis=1), 2)
square_sum = tf.reduce_sum(tf.pow(embedding_matrix, 2), axis=1)
dense = tf.subtract(sum_square, square_sum)
add_layer_summary(dense.name, dense)
# fully connected stacked dense layers
dense = stack_dense_layer(dense,
params['hidden_units'],
dropout_rate=params['dropout_rate'],
batch_norm=params['batch_norm'],
mode=mode,
add_summary=True)
with tf.variable_scope('output'):
y = linear_output + dense
add_layer_summary('output', y)
return y
def model_fn_sparse(features, labels, mode, params):
# hyper parameter
data_params = params['data_params']
field_size = data_params['field_size']
feature_size = data_params['feature_size']
embedding_size = data_params['embedding_size']
# extract feature
feat_ids = tf.reshape(features['feat_ids'],
shape=[-1, field_size]) # batch * field_size
feat_vals = tf.reshape(features['feat_vals'],
shape=[-1, field_size]) # batch * field_size
# extract embedding
embedding_matrix = sparse_embedding(feature_size,
embedding_size,
field_size,
feat_ids,
feat_vals,
add_summary=True)
# linear output
linear_output = sparse_linear(feature_size,
feat_ids,
feat_vals,
add_summary=True)
with tf.variable_scope('Elementwise_Interaction'):
elementwise_list = []
for i in range(field_size):
for j in range(i + 1, field_size):
vi = tf.gather(embedding_matrix,
indices=i,
axis=1,
batch_dims=0,
name='vi') # batch * emb_size
vj = tf.gather(embedding_matrix,
indices=j,
axis=1,
batch_dims=0,
name='vj')
elementwise_list.append(tf.multiply(vi,
vj)) # batch * emb_size
elementwise_matrix = tf.stack(
elementwise_list) # (N*(N-1)/2) * batch * emb_size
elementwise_matrix = tf.transpose(
elementwise_matrix, [1, 0, 2]) # batch * (N*(N-1)/2) * emb_size
with tf.variable_scope('Attention_Net'):
# 2 fully connected layer
dense = tf.layers.dense(elementwise_matrix,
units=params['attention_factor'],
activation='relu') # batch * (N*(N-1)/2) * t
add_layer_summary(dense.name, dense)
attention_weight = tf.layers.dense(
dense, units=1, activation='softmax') # batch *(N*(N-1)/2) * 1
add_layer_summary(attention_weight.name, attention_weight)
with tf.variable_scope('Attention_pooling'):
interaction_output = tf.reduce_sum(tf.multiply(elementwise_matrix,
attention_weight),
axis=1) # batch * k
interaction_output = tf.layers.dense(interaction_output,
units=1) # batch * 1
with tf.variable_scope('output'):
y = interaction_output + linear_output
add_layer_summary('output', y)
return y
def model_fn_sparse(features, labels, mode, params):
# hyper parameter
data_params = params['data_params']
field_size = data_params['field_size']
feature_size = data_params['feature_size']
embedding_size = data_params['embedding_size']
# extract feature
feat_ids = tf.reshape(features['feat_ids'],
shape=[-1, field_size]) # batch * field_size
feat_vals = tf.reshape(features['feat_vals'],
shape=[-1, field_size]) # batch * field_size
# extract embedding
with tf.variable_scope('extract_embedding'):
embedding_matrix = sparse_embedding(
feature_size,
embedding_size,
field_size,
feat_ids,
feat_vals,
add_summary=True) # (batch, field_size, embedding_size)
# linear part
linear_output = sparse_linear(feature_size,
feat_ids,
feat_vals,
add_summary=True)
# SENET_layer to get new embedding matrix
senet_embedding_matrix = SENET_layer(embedding_matrix,
field_size,
embedding_size,
pool_op=params['pool_op'],
ratio=params['senet_ratio'])
# combination layer & BI_interaction
BI_org = Bilinear_layer(embedding_matrix,
field_size,
embedding_size,
type=params['model_type'],
name='org')
BI_senet = Bilinear_layer(senet_embedding_matrix,
field_size,
embedding_size,
type=params['model_type'],
name='senet')
combination_layer = tf.concat([BI_org, BI_senet], axis=1)
# Deep part
dense_output = stack_dense_layer(combination_layer,
params['hidden_units'],
params['dropout_rate'],
params['batch_norm'],
mode,
add_summary=True)
with tf.variable_scope('output'):
y = dense_output + linear_output
add_layer_summary('output', y)
return y