def __init__(self, input_dim, output_dim, neigh_input_dim=None,
dropout=0., bias=False, act=tf.nn.relu,
name=None, concat=False, **kwargs):
super(MeanAggregator, self).__init__(**kwargs)
self.dropout = dropout
self.bias = bias
self.act = act
self.concat = concat
if neigh_input_dim is None:
neigh_input_dim = input_dim
if name is not None:
name = '/' + name
else:
name = ''
with tf.compat.v1.variable_scope(self.name + name + '_vars'):
self.vars['neigh_weights'] = glorot([neigh_input_dim, output_dim],
name='neigh_weights')
self.vars['self_weights'] = glorot([input_dim, output_dim],
name='self_weights')
if self.bias:
self.vars['bias'] = zeros([self.output_dim], name='bias')
if self.logging:
self._log_vars()
self.input_dim = input_dim
self.output_dim = output_dim
def reset_parameters(self):
glorot(self.lin_l.weight)
glorot(self.lin_r.weight)
zeros(self.lin_r.bias)
zeros(self.lin_r.bias)
if self.norm == 'neighbornorm':
self.normlayer_l.reset_parameters()
self.normlayer_r.reset_parameters()
def __init__(self, input_dim, output_dim, model_size="small", neigh_input_dim=None,
dropout=0., bias=False, act=tf.nn.relu, name=None, concat=False, **kwargs):
super(TwoMaxLayerPoolingAggregator, self).__init__(**kwargs)
self.dropout = dropout
self.bias = bias
self.act = act
self.concat = concat
if neigh_input_dim is None:
neigh_input_dim = input_dim
if name is not None:
name = '/' + name
else:
name = ''
if model_size == "small":
hidden_dim_1 = self.hidden_dim_1 = 512
hidden_dim_2 = self.hidden_dim_2 = 256
elif model_size == "big":
hidden_dim_1 = self.hidden_dim_1 = 1024
hidden_dim_2 = self.hidden_dim_2 = 512
self.mlp_layers = []
self.mlp_layers.append(Dense(input_dim=neigh_input_dim,
output_dim=hidden_dim_1,
act=tf.nn.relu,
dropout=dropout,
sparse_inputs=False,
logging=self.logging))
self.mlp_layers.append(Dense(input_dim=hidden_dim_1,
output_dim=hidden_dim_2,
act=tf.nn.relu,
dropout=dropout,
sparse_inputs=False,
logging=self.logging))
with tf.variable_scope(self.name + name + '_vars'):
self.vars['neigh_weights'] = glorot([hidden_dim_2, output_dim],
name='neigh_weights')
self.vars['self_weights'] = glorot([input_dim, output_dim],
name='self_weights')
if self.bias:
self.vars['bias'] = zeros([self.output_dim], name='bias')
if self.logging:
self._log_vars()
self.input_dim = input_dim
self.output_dim = output_dim
self.neigh_input_dim = neigh_input_dim
def reset_parameters(self):
glorot(self.lin.weight)
glorot(self.lin_residual.weight)
glorot(self.att_i)
glorot(self.att_j)
zeros(self.lin_residual.bias)
zeros(self.bias)
def __init__(self, input_dim, output_dim, model_size="small", neigh_input_dim=None,
dropout=0., bias=False, act=tf.nn.relu, name=None, concat=False, **kwargs):
super(SeqAggregator, self).__init__(**kwargs)
self.dropout = dropout
self.bias = bias
self.act = act
self.concat = concat
if neigh_input_dim is None:
neigh_input_dim = input_dim
if name is not None:
name = '/' + name
else:
name = ''
if model_size == "small":
hidden_dim = self.hidden_dim = 128
elif model_size == "big":
hidden_dim = self.hidden_dim = 256
with tf.variable_scope(self.name + name + '_vars'):
self.vars['neigh_weights'] = glorot([hidden_dim, output_dim],
name='neigh_weights')
self.vars['self_weights'] = glorot([input_dim, output_dim],
name='self_weights')
if self.bias:
self.vars['bias'] = zeros([self.output_dim], name='bias')
if self.logging:
self._log_vars()
self.input_dim = input_dim
self.output_dim = output_dim
self.neigh_input_dim = neigh_input_dim
self.cell = tf.contrib.rnn.BasicLSTMCell(self.hidden_dim)
def reset_parameters(self):
glorot(self.linear.weight)
zeros(self.linear.bias)
def reset_parameters(self):
glorot(self.lin_l.weight)
glorot(self.lin_r.weight)
zeros(self.lin_l.bias)
zeros(self.lin_r.bias)
def reset_parameters(self):
self.block.reset_parameters()
glorot(self.lin.weight)
zeros(self.lin.bias)
def reset_parameters(self):
self.conv1.reset_parameters()
for conv in self.convs:
conv.reset_parameters()
glorot(self.lin.weight)
zeros(self.lin.bias)
def reset_parameter(self):
glorot(self.lin.weight)
zeros(self.lin.bias)
