def call(self, node_embeddings, adjacency_lists, training=True):
adjacency_loop = [add_self_loop(adjacency_lists, len(node_embeddings))]
x = self.gc1(GNNInput(node_embeddings, adjacency_loop), training)
x = tf.nn.relu(x)
x = self.dropout(x, training=training)
x = self.gc2(GNNInput(x, adjacency_loop), training)
return tf.math.softmax(x, 1)
def call(self, node_embeddings, adjacency_lists, training=True):
node_embeddings = self.dropout1(node_embeddings, training=training)
x = self.gc1(GNNInput(node_embeddings, adjacency_lists), training)
x = tf.nn.elu(x)
x = self.dropout2(x, training=training)
x = self.gc2(GNNInput(x, adjacency_lists), training)
return tf.math.softmax(x, -1)
def call(self, inputs, training):
adjacency_lists = inputs.adjacency_lists
node_embeddings = inputs.node_embeddings
part1 = (1 + self.eps) * node_embeddings
part2 = self.propagate(GNNInput(node_embeddings, adjacency_lists),
training)
out = self.nn(part1 + part2, training=training)
return out
def call(self, inputs, training):
adjacency_lists = inputs.adjacency_lists
adjacency_lists = [remove_self_loop(adjacency_lists[0])]
node_embeddings = inputs.node_embeddings
part1 = (1 + self.eps) * node_embeddings
part2 = self.propagate(GNNInput(node_embeddings, adjacency_lists),
training)
out = self.nn(part1 + part2)
return out
def call(self, inputs):
adjacency_lists = inputs.adjacency_lists
node_embeddings = inputs.node_embeddings
if self.use_bias:
node_embeddings = tf.linalg.matmul(node_embeddings,
self.weight) + self.bias
else:
node_embeddings = tf.linalg.matmul(node_embeddings, self.weight)
aggr_out = self.propagate(GNNInput(node_embeddings, adjacency_lists))
return aggr_out
def call(self, inputs, training):
adjacency_lists = inputs.adjacency_lists
node_embeddings = inputs.node_embeddings
node_embeddings = tf.linalg.matmul(node_embeddings, self.weight)
aggr_out = self.propagate(GNNInput(node_embeddings, adjacency_lists),
training)
if self.concat is True:
aggr_out = tf.reshape(aggr_out,
[-1, self.heads * self.out_features])
else:
aggr_out = tf.reduce_mean(aggr_out, 1)
if self.use_bias:
aggr_out += self.bias
return aggr_out
def call(self, node_embeddings, adjacency_lists, training=True):
node_embeddings = self.drop_out1(node_embeddings, training=training)
x = tf.nn.relu(self.conv1(GNNInput(node_embeddings, adjacency_lists)))
x = self.drop_out2(x, training=training)
x = self.conv2(GNNInput(x, adjacency_lists))
return tf.math.softmax(x, -1)