def __init__(self, net_params):
super().__init__()
in_dim = net_params['in_dim']
hidden_dim = net_params['hidden_dim']
n_classes = net_params['n_classes']
dropout = net_params['dropout']
self.n_layers = net_params['L']
n_mlp_layers = net_params['n_mlp_GIN'] # GIN
learn_eps = net_params['learn_eps_GIN'] # GIN
neighbor_aggr_type = net_params['neighbor_aggr_GIN'] # GIN
graph_norm = net_params['graph_norm']
batch_norm = net_params['batch_norm']
residual = net_params['residual']
# List of MLPs
self.ginlayers = torch.nn.ModuleList()
self.embedding_h = nn.Linear(in_dim, hidden_dim)
# Input layer
mlp = MLP(1, in_dim, hidden_dim, hidden_dim)
self.ginlayers.append(
GINLayer(ApplyNodeFunc(mlp),
neighbor_aggr_type,
dropout,
graph_norm,
batch_norm,
residual,
0,
learn_eps,
activation=F.relu))
# Hidden layers
for layer in range(self.n_layers - 1):
mlp = MLP(n_mlp_layers, hidden_dim, hidden_dim, hidden_dim)
self.ginlayers.append(
GINLayer(ApplyNodeFunc(mlp),
neighbor_aggr_type,
dropout,
graph_norm,
batch_norm,
residual,
0,
learn_eps,
activation=F.relu))
# Output layer
mlp = MLP(1, hidden_dim, n_classes, n_classes)
self.ginlayers.append(
GINLayer(ApplyNodeFunc(mlp), neighbor_aggr_type, dropout,
graph_norm, batch_norm, residual, 0, learn_eps))
def __init__(self, net_params):
super().__init__()
in_dim = net_params['in_dim']
hidden_dim = net_params['hidden_dim']
n_classes = net_params['n_classes']
dropout = net_params['dropout']
self.n_layers = net_params['L']
n_mlp_layers = net_params['n_mlp_GIN'] # GIN
learn_eps = net_params['learn_eps_GIN'] # GIN
neighbor_aggr_type = net_params['neighbor_aggr_GIN'] # GIN
readout = net_params['readout'] # this is graph_pooling_type
batch_norm = net_params['batch_norm']
residual = net_params['residual']
self.n_classes = n_classes
self.device = net_params['device']
# List of MLPs
self.ginlayers = torch.nn.ModuleList()
self.embedding_h = nn.Embedding(in_dim, hidden_dim)
for layer in range(self.n_layers):
mlp = MLP(n_mlp_layers, hidden_dim, hidden_dim, hidden_dim)
self.ginlayers.append(
GINLayer(ApplyNodeFunc(mlp), neighbor_aggr_type, dropout,
batch_norm, residual, 0, learn_eps))
# Linear function for output of each layer
# which maps the output of different layers into a prediction score
self.linears_prediction = torch.nn.ModuleList()
for layer in range(self.n_layers + 1):
self.linears_prediction.append(nn.Linear(hidden_dim, n_classes))
def __init__(self, net_params):
super().__init__()
self.n_layers = 2
self.embedding_h = nn.Linear(net_params.in_dim, net_params.hidden_dim)
self.ginlayers = torch.nn.ModuleList()
for layer in range(net_params.L):
mlp = MLP(net_params.n_mlp_GIN, net_params.hidden_dim,
net_params.hidden_dim, net_params.hidden_dim)
self.ginlayers.append(
GINLayer(ApplyNodeFunc(mlp), net_params.neighbor_aggr_GIN,
net_params.dropout, net_params.graph_norm,
net_params.batch_norm, net_params.residual, 0,
net_params.learn_eps_GIN))
pass
# Linear function for graph poolings (readout) of output of each layer
# which maps the output of different layers into a prediction score
self.linears_prediction = torch.nn.ModuleList()
for layer in range(self.n_layers + 1):
self.linears_prediction.append(
nn.Linear(net_params.hidden_dim, net_params.n_classes))
pass
if net_params.readout == 'sum':
self.pool = SumPooling()
elif net_params.readout == 'mean':
self.pool = AvgPooling()
elif net_params.readout == 'max':
self.pool = MaxPooling()
else:
raise NotImplementedError
pass
def __init__(self, net_params):
super().__init__()
in_dim = net_params['in_dim']
hidden_dim = net_params['hidden_dim']
out_dim = net_params['out_dim']
dropout = net_params['dropout']
self.n_layers = net_params['L']
n_mlp_layers = net_params['n_mlp_GIN'] # GIN
learn_eps = net_params['learn_eps_GIN'] # GIN
neighbor_aggr_type = net_params['neighbor_aggr_GIN'] # GIN
readout = net_params['readout'] # this is graph_pooling_type
batch_norm = net_params['batch_norm']
residual = net_params['residual']
activation_name = net_params['activation']
# List of MLPs
self.ginlayers = torch.nn.ModuleList()
self.embedding_h = nn.Linear(in_dim, hidden_dim)
for layer in range(self.n_layers - 1):
mlp = MLP(n_mlp_layers, hidden_dim, hidden_dim, hidden_dim,
activations[activation_name])
self.ginlayers.append(
GINLayer(ApplyNodeFunc(mlp), neighbor_aggr_type, dropout,
batch_norm, residual, 0, learn_eps,
activations[activation_name]))
self.ginlayers.append(
GINLayer(
ApplyNodeFunc(
MLP(n_mlp_layers, hidden_dim, hidden_dim, out_dim,
activations[activation_name])), neighbor_aggr_type,
dropout, batch_norm, residual, 0, learn_eps,
activations[activation_name]))
def __init__(self, net_params):
super().__init__()
num_atom_type = net_params['num_atom_type']
hidden_dim = net_params['hidden_dim']
out_dim = net_params['out_dim']
dropout = net_params['dropout']
self.n_layers = net_params['L']
n_mlp_layers = net_params['n_mlp_GIN'] # GIN
learn_eps = net_params['learn_eps_GIN'] # GIN
neighbor_aggr_type = net_params['neighbor_aggr_GIN'] # GIN
self.readout = net_params['readout'] # this is graph_pooling_type
self.graph_norm = net_params['graph_norm']
self.batch_norm = net_params['batch_norm']
self.layer_norm = net_params['layer_norm']
self.residual = net_params['residual']
self.task = net_params['task']
if self.task == 'classification':
self.num_classes = net_params['num_classes']
else:
self.num_classes = 1
# List of MLPs
self.ginlayers = torch.nn.ModuleList()
self.embedding_lin = nn.Linear(num_atom_type, hidden_dim, False)
for layer in range(self.n_layers):
mlp = MLP(hidden_dim, hidden_dim, hidden_dim, self.batch_norm,
self.layer_norm)
self.ginlayers.append(
GINLayer(ApplyNodeFunc(mlp), neighbor_aggr_type, dropout,
self.graph_norm, self.batch_norm, self.layer_norm, 0,
learn_eps))
# Linear function for graph poolings (readout) of output of each layer
# which maps the output of different layers into a prediction score
self.linear_ro = nn.Linear(hidden_dim, out_dim, bias=False)
self.linear_prediction = nn.Linear(out_dim,
self.num_classes,
bias=True)
# additional parameters for gated residual connection
if self.residual == 'gated':
self.W_g = nn.Linear(2 * hidden_dim, hidden_dim, False)
def __init__(self, net_params):
super().__init__()
num_node_type = net_params['num_node_type']
hidden_dim = net_params['hidden_dim']
n_classes = net_params['n_classes']
dropout = net_params['dropout']
self.n_layers = net_params['L']
n_mlp_layers = net_params['n_mlp_GIN'] # GIN
learn_eps = net_params['learn_eps_GIN'] # GIN
neighbor_aggr_type = net_params['neighbor_aggr_GIN'] # GIN
readout = net_params['readout'] # this is graph_pooling_type
batch_norm = net_params['batch_norm']
residual = net_params['residual']
self.pos_enc = net_params['pos_enc']
if self.pos_enc:
pos_enc_dim = net_params['pos_enc_dim']
self.embedding_pos_enc = nn.Linear(pos_enc_dim, hidden_dim)
else:
in_dim = 1
self.embedding_h = nn.Embedding(in_dim, hidden_dim)
# List of MLPs
self.ginlayers = torch.nn.ModuleList()
for layer in range(self.n_layers):
mlp = MLP(n_mlp_layers, hidden_dim, hidden_dim, hidden_dim)
self.ginlayers.append(
GINLayer(ApplyNodeFunc(mlp), neighbor_aggr_type, dropout,
batch_norm, residual, 0, learn_eps))
# Linear function for graph poolings (readout) of output of each layer
# which maps the output of different layers into a prediction score
self.linears_prediction = torch.nn.ModuleList()
for layer in range(self.n_layers + 1):
self.linears_prediction.append(nn.Linear(hidden_dim, n_classes))
if readout == 'sum':
self.pool = SumPooling()
elif readout == 'mean':
self.pool = AvgPooling()
elif readout == 'max':
self.pool = MaxPooling()
else:
raise NotImplementedError
def __init__(self, net_params):
super().__init__()
in_dim = net_params['in_dim']
hidden_dim = net_params['hidden_dim']
dropout = net_params['dropout']
self.n_layers = net_params['L']
n_mlp_layers = net_params['n_mlp_GIN'] # GIN
learn_eps = net_params['learn_eps_GIN'] # GIN
neighbor_aggr_type = net_params['neighbor_aggr_GIN'] # GIN
batch_norm = net_params['batch_norm']
residual = net_params['residual']
self.device = net_params['device']
self.embedding_h = nn.Linear(in_dim, hidden_dim)
# List of MLPs
self.ginlayers = torch.nn.ModuleList()
for layer in range(self.n_layers):
mlp = MLP(n_mlp_layers, hidden_dim, hidden_dim, hidden_dim)
self.ginlayers.append(
GINLayer(ApplyNodeFunc(mlp), neighbor_aggr_type, dropout,
batch_norm, residual, 0, learn_eps))
self.MLP_layer = MLPReadout(2 * hidden_dim, 1)
