python pack_nbrs.py --max_nbrs=5 \
labeled_data.tfr \
unlabeled_data.tfr \
graph.tsv \
merged_examples.tfr 

import neural_structured_learning as nsl
# Create a custom model — sequential, functional, or subclass. 
base_model = tf.keras.Sequential(…)

# Wrap the custom model with graph regularization. 
graph_config = nsl.configs.GraphRegConfig(neighbor_config=nsl.configs.GraphNeighborConfig(max_neighbors=1)) 
graph_model = nsl.keras.GraphRegularization(base_model, graph_config)

# Compile, train, and evaluate. 
graph_model.compile(optimizer=’adam’, loss=tf.keras.losses.SparseCategoricalCrossentropy(), metrics=[‘accuracy’]) 
graph_model.fit(train_dataset, epochs=5) 
graph_model.evaluate(test_dataset)

如果没有任何显式结构怎么办？

import neural_structured_learning as nsl

# Create a base model — sequential, functional, or subclass. 
model = tf.keras.Sequential(…)

# Wrap the model with adversarial regularization. 
adv_config = nsl.configs.make_adv_reg_config(multiplier=0.2, adv_step_size=0.05) 
adv_model = nsl.keras.AdversarialRegularization(model, adv_config=adv_config)

# Compile, train, and evaluate. 
adv_model.compile(optimizer=’adam’, loss=’sparse_categorical_crossentropy’, metrics=[‘accuracy’]) 
adv_model.fit({‘feature’: x_train, ‘label’: y_train}, epochs=5)
adv_model.evaluate({‘feature’: x_test, ‘label’: y_test})

致谢