def create_HinSAGE_model(graph, link_prediction=False):
if link_prediction:
generator = HinSAGELinkGenerator(graph,
batch_size=2,
num_samples=[2, 1])
edge_ids_train = np.array([[1, 2], [2, 3], [1, 3]])
train_gen = generator.flow(edge_ids_train, np.array([1, 1, 0]))
else:
generator = HinSAGENodeGenerator(graph,
batch_size=2,
num_samples=[2, 2])
train_gen = generator.flow([1, 2], np.array([[1, 0], [0, 1]]))
base_model = HinSAGE(layer_sizes=[8, 8],
generator=train_gen,
bias=True,
dropout=0.5)
if link_prediction:
# Define input and output sockets of hinsage:
x_inp, x_out = base_model.default_model()
# Final estimator layer
prediction = link_regression(edge_embedding_method="ip")(x_out)
else:
x_inp, x_out = base_model.default_model(flatten_output=True)
prediction = layers.Dense(units=2, activation="softmax")(x_out)
keras_model = Model(inputs=x_inp, outputs=prediction)
return base_model, keras_model, generator, train_gen
def train(
self,
layer_size,
num_samples,
train_size=0.7,
batch_size: int = 200,
num_epochs: int = 20,
learning_rate=5e-3,
dropout=0.0,
use_bias=True,
):
"""
Build and train the HinSAGE model for link attribute prediction on the specified graph G
with given parameters.
Args:
layer_size: a list of number of hidden nodes in each layer
num_samples: number of neighbours to sample at each layer
batch_size: size of mini batch
num_epochs: number of epochs to train the model (epoch = all training batches are streamed through the model once)
learning_rate: initial learning rate
dropout: dropout probability in the range [0, 1)
use_bias: tells whether to use a bias terms in HinSAGE model
Returns:
"""
# Training and test edges
edges = list(self.g.edges(data=True))
edges_train, edges_test = model_selection.train_test_split(
edges, train_size=train_size)
# Edgelists:
edgelist_train = [(e[0], e[1]) for e in edges_train]
edgelist_test = [(e[0], e[1]) for e in edges_test]
labels_train = [e[2]["score"] for e in edges_train]
labels_test = [e[2]["score"] for e in edges_test]
# Our machine learning task of learning user-movie ratings can be framed as a supervised Link Attribute Inference:
# given a graph of user-movie ratings, we train a model for rating prediction using the ratings edges_train,
# and evaluate it using the test ratings edges_test. The model also requires the user-movie graph structure.
# To proceed, we need to create a StellarGraph object from the ingested graph, for training the model:
# When sampling the GraphSAGE subgraphs, we want to treat user-movie links as undirected
self.g = sg.StellarGraph(self.g, node_features="feature")
# Next, we create the link generators for preparing and streaming training and testing data to the model.
# The mappers essentially sample k-hop subgraphs of G with randomly selected head nodes, as required by
# the HinSAGE algorithm, and generate minibatches of those samples to be fed to the input layer of the HinSAGE model.
generator = HinSAGELinkGenerator(
self.g,
batch_size,
num_samples,
)
train_gen = generator.flow(edgelist_train, labels_train)
test_gen = generator.flow(edgelist_test, labels_test)
# Build the model by stacking a two-layer HinSAGE model and a link regression layer on top.
assert len(layer_size) == len(
num_samples
), "layer_size and num_samples must be of the same length! Stopping."
hinsage = HinSAGE(layer_sizes=layer_size,
generator=train_gen,
bias=use_bias,
dropout=dropout)
# Define input and output sockets of hinsage:
x_inp, x_out = hinsage.default_model()
# Final estimator layer
score_prediction = link_regression(
edge_embedding_method=args.edge_embedding_method)(x_out)
# Create Keras model for training
model = Model(inputs=x_inp, outputs=score_prediction)
model.compile(
optimizer=optimizers.Adam(lr=learning_rate),
loss=losses.mean_squared_error,
metrics=[root_mean_square_error, metrics.mae],
)
# Train model
print("Training the model for {} epochs with initial learning rate {}".
format(num_epochs, learning_rate))
history = model.fit_generator(
train_gen,
validation_data=test_gen,
epochs=num_epochs,
verbose=2,
shuffle=True,
use_multiprocessing=True,
workers=multiprocessing.cpu_count() // 2,
)
# Evaluate and print metrics
test_metrics = model.evaluate_generator(test_gen)
print("Test Evaluation:")
for name, val in zip(model.metrics_names, test_metrics):
print("\t{}: {:0.4f}".format(name, val))