def _call_one_graph(self, input):
x = input[0]
self.laplacians = input[1]
num_features_nonzero = input[2]
# dropout
if self.sparse_inputs:
x = sparse_dropout(x, 1 - self.dropout, num_features_nonzero)
else:
x = tf.nn.dropout(x, 1 - self.dropout)
# convolve
support_list = []
for i in range(len(self.laplacians)):
if not self.featureless:
pre_sup = dot(x, self.vars['weights_' + str(i)],
sparse=self.sparse_inputs)
else:
pre_sup = self.vars['weights_' + str(i)]
support = dot(self.laplacians[i], pre_sup, sparse=True)
support_list.append(support)
output = tf.add_n(support_list)
# bias
if self.bias:
output += self.vars['bias']
return self.act(output)
def _gcn(self, input):
x = input[0]
self.laplacians = input[1]
num_features_nonzero = input[2]
# dropout
if self.sparse_inputs:
x = sparse_dropout(x, 1 - self.dropout, num_features_nonzero)
else:
x = tf.nn.dropout(x, 1 - self.dropout)
# convolve
support_list = []
for i in range(len(self.laplacians)):
if not self.featureless:
pre_sup = dot(x,
self.vars['weights_' + str(i)],
sparse=self.sparse_inputs)
else:
pre_sup = self.vars['weights_' + str(i)]
support = dot(self.laplacians[i], pre_sup, sparse=True)
support_list.append(support)
output = tf.add_n(support_list)
# bias
if self.bias:
output += self.vars['bias']
# normalize
if FLAGS.node_embs_norm:
output = tf.nn.l2_normalize(output, axis=1) # along each row
return self.act(output)
def _gmn(self, g1, g2):
if logging_enabled == True:
print("- Entered layers::GraphConvolution::_gmn Private Method")
g1x = g1[0]
g1_edge_index = self._to_dense(tf.sparse_transpose(g1[3]))
incidence_mat1 = tf.cast(g1[4], tf.float32)
g2x = g2[0]
g2_edge_index = self._to_dense(tf.sparse_transpose(g2[3]))
incidence_mat2 = tf.cast(g2[4], tf.float32)
if self.sparse_inputs:
g1x = self._to_dense(g1x)
g2x = self._to_dense(g2x)
# tf.concat([tf.gather(g1_edge_index, tf.constant(0)), tf.gather(g2_edge_index, tf.constant(0))], 1)
row1 = tf.gather(g1_edge_index, tf.constant(0))
# tf.concat([tf.gather(g1_edge_index, tf.constant(1)), tf.gather(g2_edge_index, tf.constant(1))], 1)
col1 = tf.gather(g1_edge_index, tf.constant(1))
row2 = tf.gather(g2_edge_index, tf.constant(0))
col2 = tf.gather(g2_edge_index, tf.constant(1))
h1_i = tf.gather(g1x, row1)
h1_j = tf.gather(g1x, col1)
h2_i = tf.gather(g2x, row2)
h2_j = tf.gather(g2x, col2)
m1 = tf.concat([h1_i, h1_j], 1)
m2 = tf.concat([h2_i, h2_j], 1)
for l in self.f_message:
m1 = l(m1)
m2 = l(m2)
m1_sum = dot(incidence_mat1, m1, sparse=True)
m2_sum = dot(incidence_mat2, m2, sparse=True)
u1_sum = self._gmn_f_match(g1x, g2x)
u2_sum = self._gmn_f_match(g2x, g1x)
h1_prime = tf.concat([g1x, m1_sum, u1_sum], axis=1)
h2_prime = tf.concat([g2x, m2_sum, u2_sum], axis=1)
for l in self.f_node:
h1_prime = l(h1_prime)
h2_prime = l(h2_prime)
return (h1_prime, h2_prime)
def _gcn(self, input):
if logging_enabled == True:
print("- Entered layers::GraphConvolution::_gcn Private Method")
x = input[0]
self.laplacians = input[1]
num_features_nonzero = input[2]
# dropout
if self.sparse_inputs:
x = sparse_dropout(x, 1 - self.dropout, num_features_nonzero)
else:
x = tf.nn.dropout(x, rate=ec.dropout_rate)
# convolve
support_list = []
for i in range(len(self.laplacians)):
if not self.featureless:
pre_sup = dot(x,
self.vars['weights_' + str(i)],
sparse=self.sparse_inputs)
else:
pre_sup = self.vars['weights_' + str(i)]
support = dot(self.laplacians[i], pre_sup, sparse=True)
support_list.append(support)
output = tf.add_n(support_list)
# bias
if self.bias:
output += self.vars['bias']
# normalize
if ec.node_embs_norm:
output = tf.nn.l2_normalize(output, axis=1) # along each row
return self.act(output)
def _call_one_mat(self, inputs):
x = inputs
# dropout
x = tf.nn.dropout(x, 1 - self.dropout)
# transform
output = dot(x, self.vars['weights'])
# bias
if self.bias:
output += self.vars['bias']
return self.act(output)
def _call_one_mat(self, inputs):
if logging_enabled == True:
print("- Entered layers::Layer::_call_one_mat Private Method")
x = inputs
# dropout
x = tf.nn.dropout(x, rate=ec.dropout_rate)
# transform
output = dot(x, self.vars['weights'])
# bias
if self.bias:
output += self.vars['bias']
return self.act(output)