def __init__(
self,
in_feats: int,
hidden_size: int,
out_feats: int,
pooling_layer: int,
pooling_rates: List[float],
n_dropout: float = 0.5,
adj_dropout: float = 0.3,
activation: str = "elu",
improved: bool = False,
aug_adj: bool = False,
):
super(GraphUnet, self).__init__()
self.improved = improved
self.n_dropout = n_dropout
self.adj_dropout = adj_dropout
self.act = get_activation(activation)
assert pooling_layer <= len(pooling_rates)
pooling_rates = pooling_rates[:pooling_layer]
pooling_rates = [float(x) for x in pooling_rates]
self.unet = GraphUnetLayer(hidden_size, pooling_layer, pooling_rates,
activation, n_dropout, aug_adj)
self.in_gcn = GCNLayer(in_feats, hidden_size)
self.out_gcn = GCNLayer(hidden_size, out_feats)
def __init__(
self,
hidden_size: int,
pooling_layer: int,
pooling_rates: List[float],
activation: str = "elu",
dropout: float = 0.5,
aug_adj: bool = False,
):
super(GraphUnetLayer, self).__init__()
self.dropout = dropout
self.activation = activation
self.pooling_layer = pooling_layer
self.gcn = GCNLayer(hidden_size, hidden_size)
self.act = get_activation(activation)
self.down_gnns = nn.ModuleList(
[GCNLayer(hidden_size, hidden_size) for _ in range(pooling_layer)])
self.up_gnns = nn.ModuleList(
[GCNLayer(hidden_size, hidden_size) for _ in range(pooling_layer)])
self.poolings = nn.ModuleList([
Pool(hidden_size, pooling_rates[i], aug_adj, dropout)
for i in range(pooling_layer)
])
self.unpoolings = nn.ModuleList(
[UnPool() for _ in range(pooling_layer)])
def __init__(self, nfeat, nhid, nclass, dropout, pooling_ratio,
pooling_layer_type):
def __get_layer_from_str__(str):
if str == "gcnconv":
return GCNLayer
return GCNLayer
super(SAGPoolNetwork, self).__init__()
self.nfeat = nfeat
self.nhid = nhid
self.nclass = nclass
self.dropout = dropout
self.pooling_ratio = pooling_ratio
self.conv_layer_1 = GCNLayer(self.nfeat, self.nhid)
self.conv_layer_2 = GCNLayer(self.nhid, self.nhid)
self.conv_layer_3 = GCNLayer(self.nhid, self.nhid)
self.pool_layer_1 = SAGPoolLayers(
self.nhid,
Conv=__get_layer_from_str__(pooling_layer_type),
ratio=self.pooling_ratio)
self.pool_layer_2 = SAGPoolLayers(
self.nhid,
Conv=__get_layer_from_str__(pooling_layer_type),
ratio=self.pooling_ratio)
self.pool_layer_3 = SAGPoolLayers(
self.nhid,
Conv=__get_layer_from_str__(pooling_layer_type),
ratio=self.pooling_ratio)
self.lin_layer_1 = torch.nn.Linear(self.nhid * 2, self.nhid)
self.lin_layer_2 = torch.nn.Linear(self.nhid, self.nhid // 2)
self.lin_layer_3 = torch.nn.Linear(self.nhid // 2, self.nclass)
def __init__(self, num_features, hidden_size):
super(VGAE, self).__init__()
self.num_features = num_features
self.hidden_size = hidden_size
self.conv1 = GCNLayer(self.num_features, self.hidden_size)
self.conv2_mean = GCNLayer(self.hidden_size, self.hidden_size)
self.conv2_var = GCNLayer(self.hidden_size, self.hidden_size)
def __init__(
self,
in_feats,
hidden_size,
out_feats,
num_layers,
dropout,
activation="relu",
residual=False,
norm=None,
):
super(GCN, self).__init__()
shapes = [in_feats] + [hidden_size] * (num_layers - 1) + [out_feats]
self.layers = nn.ModuleList(
[
GCNLayer(
shapes[i],
shapes[i + 1],
dropout=dropout if i != num_layers - 1 else 0,
residual=residual if i != num_layers - 1 else None,
norm=norm if i != num_layers - 1 else None,
activation=activation if i != num_layers - 1 else None,
)
for i in range(num_layers)
]
)
self.num_layers = num_layers
def __init__(
self,
in_feats,
out_feats,
hidden_size,
num_layers,
dropout=0.5,
drop_edge_rate=0.1,
activation="relu",
norm="batchnorm",
group=2,
):
super(RevGCN, self).__init__()
self.dropout = dropout
self.drop_edge_rate = drop_edge_rate
self.num_layers = num_layers
self.layers = nn.ModuleList()
self.norm = get_norm_layer(norm, hidden_size)
self.act = get_activation(activation)
for i in range(num_layers):
if i == 0:
self.layers.append(
GCNLayer(
in_feats,
hidden_size,
residual=True,
)
)
elif i == num_layers - 1:
self.layers.append(GCNLayer(hidden_size, out_feats, residual=True))
else:
conv = GCNLayer(
hidden_size // group,
hidden_size // group,
)
res_conv = ResGNNLayer(
conv,
hidden_size // group,
activation=activation,
norm=norm,
out_norm=norm,
out_channels=hidden_size // group,
)
self.layers.append(RevGNNLayer(res_conv, group))
def __init__(self, nfeat, nhid, nclass, dropout, alpha, t, k, eps,
gdctype):
super(GDC_GCN, self).__init__()
# preproc params
self.alpha = alpha
self.t = t
self.k = k
self.eps = eps
self.gdc_type = gdctype
self.data = None
# GCN init
self.nfeat = nfeat
self.gc1 = GCNLayer(nfeat, nhid)
self.gc2 = GCNLayer(nhid, nclass)
self.dropout = dropout
def __init__(self, num_features, num_classes, hidden_size, num_layers, dropout, norm=None, activation="relu"):
super(DrGCN, self).__init__()
self.num_features = num_features
self.num_classes = num_classes
self.hidden_size = hidden_size
self.num_layers = num_layers
self.dropout = dropout
shapes = [num_features] + [hidden_size] * (num_layers - 1) + [num_classes]
self.convs = nn.ModuleList(
[
GCNLayer(shapes[layer], shapes[layer + 1], activation=activation, norm=norm)
for layer in range(num_layers - 1)
]
)
self.convs.append(GCNLayer(shapes[-2], shapes[-1]))
self.ses = nn.ModuleList(
[SELayer(shapes[layer], se_channels=int(np.sqrt(shapes[layer]))) for layer in range(num_layers)]
)
def __init__(
self,
in_feats: int,
out_feats: int,
num_layers: int,
activation: str = "relu",
):
super(GraceEncoder, self).__init__()
shapes = [in_feats] + [2 * out_feats] * (num_layers - 1) + [out_feats]
self.layers = nn.ModuleList(
[GCNLayer(shapes[i], shapes[i + 1]) for i in range(num_layers)])
self.activation = get_activation(activation)
def gcn_model(in_feats, hidden_size, num_layers, out_feats, dropout, residual,
norm, activation):
shapes = [in_feats] + [hidden_size] * (num_layers - 1) + [out_feats]
return nn.ModuleList([
GCNLayer(
shapes[i],
shapes[i + 1],
dropout=dropout if i != num_layers - 1 else 0,
residual=residual if i != num_layers - 1 else None,
norm=norm if i != num_layers - 1 else None,
activation=activation if i != num_layers - 1 else None,
) for i in range(num_layers)
])
def __init__(self, num_features, num_classes, hidden_size, num_layers,
dropout):
super(DrGCN, self).__init__()
self.num_features = num_features
self.num_classes = num_classes
self.hidden_size = hidden_size
self.num_layers = num_layers
self.dropout = dropout
shapes = [num_features
] + [hidden_size] * (num_layers - 1) + [num_classes]
self.convs = nn.ModuleList([
GCNLayer(shapes[layer], shapes[layer + 1])
for layer in range(num_layers)
])
self.ses = nn.ModuleList([
SELayer(shapes[layer], se_channels=int(np.sqrt(shapes[layer])))
for layer in range(num_layers)
])
def __init__(self, num_edge, num_channels, w_in, w_out, num_class, num_nodes, num_layers):
super(GTN, self).__init__()
self.num_edge = num_edge
self.num_channels = num_channels
self.num_nodes = num_nodes
self.w_in = w_in
self.w_out = w_out
self.num_class = num_class
self.num_layers = num_layers
layers = []
for i in range(num_layers):
if i == 0:
layers.append(GTLayer(num_edge, num_channels, num_nodes, first=True))
else:
layers.append(GTLayer(num_edge, num_channels, num_nodes, first=False))
self.layers = nn.ModuleList(layers)
self.cross_entropy_loss = nn.CrossEntropyLoss()
self.gcn = GCNLayer(in_features=self.w_in, out_features=w_out)
self.linear1 = nn.Linear(self.w_out * self.num_channels, self.w_out)
self.linear2 = nn.Linear(self.w_out, self.num_class)
def __init__(self, in_feats, hidden_size, out_feats, dropout):
super(Gnn, self).__init__()
self.conv1 = GCNLayer(in_feats, hidden_size)
self.conv2 = GCNLayer(hidden_size, out_feats)
self.dropout = nn.Dropout(dropout)
def __init__(self, num_features, hidden_size, num_classes, dropout):
super(M3S, self).__init__()
self.dropout = dropout
self.gcn1 = GCNLayer(num_features, hidden_size)
self.gcn2 = GCNLayer(hidden_size, num_classes)
def __init__(self, in_feats, out_feats, hidden_size, num_layers):
super(JKNet, self).__init__()
shapes = [in_feats] + [hidden_size] * num_layers
self.layers = nn.ModuleList(
[GCNLayer(shapes[i], shapes[i + 1]) for i in range(num_layers)])
self.fc = nn.Linear(hidden_size * num_layers, out_feats)
