def __init__(self, in_channels, out_channels,
hiddens=[16],
activations=['relu'],
dropout=0.5,
weight_decay=5e-4,
lr=0.01, order=2, use_bias=False):
x = Input(batch_shape=[None, in_channels],
dtype=floatx(), name='node_attr')
adj = [Input(batch_shape=[None, None],
dtype=floatx(), sparse=True,
name=f'adj_matrix_{i}') for i in range(order + 1)]
index = Input(batch_shape=[None], dtype=intx(), name='node_index')
h = x
for hidden, activation in zip(hiddens, activations):
h = ChebyConvolution(hidden, order=order, use_bias=use_bias,
activation=activation,
kernel_regularizer=regularizers.l2(weight_decay))([h, adj])
h = Dropout(rate=dropout)(h)
h = ChebyConvolution(out_channels,
order=order, use_bias=use_bias)([h, adj])
h = Gather()([h, index])
super().__init__(inputs=[x, *adj, index], outputs=h)
self.compile(loss=SparseCategoricalCrossentropy(from_logits=True),
optimizer=Adam(lr=lr), metrics=['accuracy'])
def build(self,
hiddens=[16],
activations=['relu'],
dropout=0.5,
weight_decay=5e-4,
use_bias=False,
lr=0.01,
p1=1.4,
p2=0.7):
if self.backend == "torch":
raise RuntimeError(
f"Currently {self.name} only supports for tensorflow backend.")
with tf.device(self.device):
x = Input(batch_shape=[None, self.graph.num_node_attrs],
dtype=self.floatx,
name='node_attr')
adj = Input(batch_shape=[None, None],
dtype=self.floatx,
sparse=True,
name='adj_matrix')
index = Input(batch_shape=[None],
dtype=self.intx,
name='node_index')
GCN_layers = []
for hidden, activation in zip(hiddens, activations):
GCN_layers.append(
GraphConvolution(
hidden,
activation=activation,
use_bias=use_bias,
kernel_regularizer=regularizers.l2(weight_decay)))
GCN_layers.append(
GraphConvolution(self.graph.num_node_classes,
use_bias=use_bias))
self.GCN_layers = GCN_layers
self.dropout = Dropout(rate=dropout)
logit = self.forward(x, adj)
output = Gather()([logit, index])
model = TFKeras(inputs=[x, adj, index], outputs=output)
model.compile(loss=SparseCategoricalCrossentropy(from_logits=True),
optimizer=Adam(lr=lr),
metrics=['accuracy'])
self.r_vadv = tf.Variable(TruncatedNormal(stddev=0.01)(
shape=[self.graph.num_nodes, self.graph.num_node_attrs]),
name="r_vadv")
entropy_loss = entropy_y_x(logit)
vat_loss = self.virtual_adversarial_loss(x, adj, logit)
model.add_loss(p1 * vat_loss + p2 * entropy_loss)
self.model = model
self.adv_optimizer = Adam(lr=lr / 10)
def build(self,
hiddens=[16],
activations=['relu'],
dropout=0.,
lr=0.01,
weight_decay=5e-4,
p1=1.4,
p2=0.7,
use_bias=False,
epsilon=0.01):
with tf.device(self.device):
x = Input(batch_shape=[None, self.graph.num_node_attrs],
dtype=self.floatx,
name='node_attr')
adj = Input(batch_shape=[None, None],
dtype=self.floatx,
sparse=True,
name='adj_matrix')
index = Input(batch_shape=[None],
dtype=self.intx,
name='node_index')
GCN_layers = []
for hidden, activation in zip(hiddens, activations):
GCN_layers.append(
GraphConvolution(
hidden,
activation=activation,
use_bias=use_bias,
kernel_regularizer=regularizers.l2(weight_decay)))
GCN_layers.append(
GraphConvolution(self.graph.num_node_classes,
use_bias=use_bias))
self.GCN_layers = GCN_layers
self.dropout = Dropout(rate=dropout)
logit = self.forward(x, adj)
output = Gather()([logit, index])
model = TFKeras(inputs=[x, adj, index], outputs=output)
model.compile(loss=SparseCategoricalCrossentropy(from_logits=True),
optimizer=Adam(lr=lr),
metrics=['accuracy'])
entropy_loss = entropy_y_x(logit)
vat_loss = self.virtual_adversarial_loss(x, adj, logit, epsilon)
model.add_loss(p1 * vat_loss + p2 * entropy_loss)
self.model = model
def __init__(self, in_channels, out_channels,
hiddens=[64],
activations=['relu'],
dropout=0.5,
weight_decay=5e-4,
lr=0.01, kl=5e-4, gamma=1.,
use_bias=False):
_floatx = floatx()
x = Input(batch_shape=[None, in_channels],
dtype=_floatx, name='node_attr')
adj = [Input(batch_shape=[None, None], dtype=_floatx,
sparse=True, name='adj_matrix_1'),
Input(batch_shape=[None, None], dtype=_floatx, sparse=True,
name='adj_matrix_2')]
index = Input(batch_shape=[None], dtype=intx(), name='node_index')
h = x
if hiddens:
mean, var = GaussionConvolution_F(hiddens[0], gamma=gamma,
use_bias=use_bias,
activation=activations[0],
kernel_regularizer=regularizers.l2(weight_decay))([h, *adj])
if kl:
KL_divergence = 0.5 * \
tf.reduce_mean(tf.math.square(mean) + var -
tf.math.log(1e-8 + var) - 1, axis=1)
KL_divergence = tf.reduce_sum(KL_divergence)
# KL loss
kl_loss = kl * KL_divergence
# additional layers (usually unnecessay)
for hidden, activation in zip(hiddens[1:], activations[1:]):
mean, var = GaussionConvolution_D(
hidden, gamma=gamma, use_bias=use_bias, activation=activation)([mean, var, *adj])
mean = Dropout(rate=dropout)(mean)
var = Dropout(rate=dropout)(var)
mean, var = GaussionConvolution_D(
out_channels, gamma=gamma, use_bias=use_bias)([mean, var, *adj])
h = Sample()([mean, var])
h = Gather()([h, index])
super().__init__(inputs=[x, *adj, index], outputs=h)
self.compile(loss=SparseCategoricalCrossentropy(from_logits=True),
optimizer=Adam(lr=lr), metrics=['accuracy'])
if hiddens and kl:
self.add_loss(kl_loss)
def build(self,
hiddens=[32],
activations=['relu'],
dropout=0.5,
weight_decay=5e-4,
lr=0.01,
use_bias=False,
eps1=0.3,
eps2=1.2,
lamb1=0.8,
lamb2=0.8):
with tf.device(self.device):
x = Input(batch_shape=[None, self.graph.num_node_attrs],
dtype=self.floatx,
name='features')
adj = Input(batch_shape=[None, None],
dtype=self.floatx,
name='adj_matrix')
index = Input(batch_shape=[None], dtype=self.intx, name='index')
h = x
for hid, activation in zip(hiddens, activations):
h = DenseConvolution(
hid,
use_bias=use_bias,
activation=activation,
kernel_regularizer=regularizers.l2(weight_decay))([h, adj])
h = Dropout(rate=dropout)(h)
h = DenseConvolution(self.graph.num_node_classes,
use_bias=use_bias)([h, adj])
h = Gather()([h, index])
model = TFKeras(inputs=[x, adj, index], outputs=h)
model.compile(loss=SparseCategoricalCrossentropy(from_logits=True),
optimizer=Adam(lr=lr),
metrics=['accuracy'])
self.eps1 = eps1
self.eps2 = eps2
self.lamb1 = lamb1
self.lamb2 = lamb2
self.model = model
def __init__(self,
in_channels,
out_channels,
hiddens=[64],
activations=['relu'],
dropout=0.5,
weight_decay=5e-3,
lr=0.01,
use_bias=False,
K=10):
x = Input(batch_shape=[None, in_channels],
dtype=floatx(),
name='node_attr')
adj = Input(batch_shape=[None, None],
dtype=floatx(),
sparse=True,
name='adj_matrix')
index = Input(batch_shape=[None], dtype=intx(), name='node_index')
h = x
for hidden, activation in zip(hiddens, activations):
h = Dense(hidden,
use_bias=use_bias,
activation=activation,
kernel_regularizer=regularizers.l2(weight_decay))(h)
h = Dropout(dropout)(h)
h = Dense(out_channels,
use_bias=use_bias,
activation=activations[-1],
kernel_regularizer=regularizers.l2(weight_decay))(h)
h = Dropout(dropout)(h)
h = PropConvolution(
K,
use_bias=use_bias,
activation='sigmoid',
kernel_regularizer=regularizers.l2(weight_decay))([h, adj])
h = Gather()([h, index])
super().__init__(inputs=[x, adj, index], outputs=h)
self.compile(loss=SparseCategoricalCrossentropy(from_logits=True),
optimizer=Adam(lr=lr),
metrics=['accuracy'])
def __init__(self,
in_channels,
out_channels,
num_nodes,
hiddens=[16],
activations=['relu'],
dropout=0.5,
weight_decay=5e-4,
lr=0.01,
use_bias=False):
_floatx = floatx()
x = Input(batch_shape=[None, in_channels],
dtype=_floatx,
name='node_attr')
wavelet = Input(batch_shape=[num_nodes, num_nodes],
dtype=_floatx,
sparse=True,
name='wavelet_matrix')
inverse_wavelet = Input(batch_shape=[num_nodes, num_nodes],
dtype=_floatx,
sparse=True,
name='inverse_wavelet_matrix')
index = Input(batch_shape=[None], dtype=intx(), name='node_index')
h = x
for hidden, activation in zip(hiddens, activations):
h = WaveletConvolution(
hidden,
activation=activation,
use_bias=use_bias,
kernel_regularizer=regularizers.l2(weight_decay))(
[h, wavelet, inverse_wavelet])
h = Dropout(rate=dropout)(h)
h = WaveletConvolution(
out_channels, use_bias=use_bias)([h, wavelet, inverse_wavelet])
h = Gather()([h, index])
super().__init__(inputs=[x, wavelet, inverse_wavelet, index],
outputs=h)
self.compile(loss=SparseCategoricalCrossentropy(from_logits=True),
optimizer=Adam(lr=lr),
metrics=['accuracy'])
def __init__(self,
in_channels,
out_channels,
hiddens=[16],
n_heads=[8],
activations=['elu'],
dropout=0.6,
weight_decay=5e-4,
lr=0.01,
use_bias=True):
x = Input(batch_shape=[None, in_channels],
dtype=floatx(),
name='node_attr')
adj = Input(batch_shape=[None, None],
dtype=floatx(),
sparse=True,
name='adj_matrix')
index = Input(batch_shape=[None], dtype=intx(), name='node_index')
h = x
for hidden, n_head, activation in zip(hiddens, n_heads, activations):
h = GraphAttention(
hidden,
attn_heads=n_head,
reduction='concat',
use_bias=use_bias,
activation=activation,
kernel_regularizer=regularizers.l2(weight_decay),
attn_kernel_regularizer=regularizers.l2(weight_decay),
)([h, adj])
h = Dropout(rate=dropout)(h)
h = GraphAttention(out_channels,
use_bias=use_bias,
attn_heads=1,
reduction='average')([h, adj])
h = Gather()([h, index])
super().__init__(inputs=[x, adj, index], outputs=h)
self.compile(loss=SparseCategoricalCrossentropy(from_logits=True),
optimizer=Adam(lr=lr),
metrics=['accuracy'])
def build_GCN(x):
h = x
for hidden, activation in zip(hiddens, activations):
h = GraphConvolution(
hidden,
use_bias=use_bias,
activation=activation,
kernel_regularizer=regularizers.l2(weight_decay))(
[h, adj])
h = Dropout(rate=dropout)(h)
h = GraphConvolution(self.graph.num_node_classes,
use_bias=use_bias)([h, adj])
h = Gather()([h, index])
model = TFKeras(inputs=[x, adj, index], outputs=h)
model.compile(loss=CategoricalCrossentropy(from_logits=True),
optimizer=RMSprop(lr=lr),
metrics=['accuracy'])
return model
