def __init__(self, in_features, out_features,
hids=[16],
acts=['relu'],
dropout=0.5,
weight_decay=5e-4,
lr=0.01, bias=False):
x = Input(batch_shape=[None, in_features],
dtype=floatx(), name='node_attr')
adj = Input(batch_shape=[None, None], dtype=floatx(),
sparse=False, name='adj_matrix')
h = x
for hid, act in zip(hids, acts):
h = DenseConvolution(hid, use_bias=bias,
activation=act,
kernel_regularizer=regularizers.l2(weight_decay))([h, adj])
h = Dropout(rate=dropout)(h)
h = DenseConvolution(out_features, use_bias=bias)([h, adj])
super().__init__(inputs=[x, adj], outputs=h)
self.compile(loss=SparseCategoricalCrossentropy(from_logits=True),
optimizer=Adam(lr=lr), metrics=['accuracy'])
def __init__(self,
in_channels,
out_channels,
hiddens=[32],
n_filters=[8, 8],
activations=[None, None],
dropout=0.8,
weight_decay=5e-4,
lr=0.1,
use_bias=False,
K=8):
x = Input(batch_shape=[None, in_channels],
dtype=floatx(),
name='node_attr')
adj = Input(batch_shape=[None, None],
dtype=floatx(),
sparse=False,
name='adj_matrix')
mask = Input(batch_shape=[None], dtype='bool', name='node_mask')
h = x
for idx, hidden in enumerate(hiddens):
h = Dropout(rate=dropout)(h)
h = DenseConvolution(
hidden,
use_bias=use_bias,
activation=activations[idx],
kernel_regularizer=regularizers.l2(weight_decay))([h, adj])
for idx, n_filter in enumerate(n_filters):
top_k_h = Top_k_features(K=K)([h, adj])
cur_h = LGConvolution(
n_filter,
kernel_size=K,
use_bias=use_bias,
dropout=dropout,
activation=activations[idx],
kernel_regularizer=regularizers.l2(weight_decay))(top_k_h)
cur_h = BatchNormalization()(cur_h)
h = Concatenate()([h, cur_h])
h = Dropout(rate=dropout)(h)
h = DenseConvolution(
out_channels,
use_bias=use_bias,
activation=activations[-1],
kernel_regularizer=regularizers.l2(weight_decay))([h, adj])
h = Mask()([h, mask])
super().__init__(inputs=[x, adj, mask], outputs=h)
self.compile(loss=SparseCategoricalCrossentropy(from_logits=True),
optimizer=Nadam(lr=lr),
metrics=['accuracy'])
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