def main():
# Training settings
parser = argparse.ArgumentParser(description='PyTorch implementation of pre-training of graph neural networks')
parser.add_argument('--device', type=int, default=0,
help='which gpu to use if any (default: 0)')
parser.add_argument('--batch_size', type=int, default=256,
help='input batch size for training (default: 256)')
parser.add_argument('--epochs', type=int, default=100,
help='number of epochs to train (default: 100)')
parser.add_argument('--lr', type=float, default=0.001,
help='learning rate (default: 0.001)')
parser.add_argument('--decay', type=float, default=0,
help='weight decay (default: 0)')
parser.add_argument('--num_layer', type=int, default=5,
help='number of GNN message passing layers (default: 5).')
parser.add_argument('--emb_dim', type=int, default=300,
help='embedding dimensions (default: 300)')
parser.add_argument('--dropout_ratio', type=float, default=0,
help='dropout ratio (default: 0)')
parser.add_argument('--JK', type=str, default="last",
help='how the node features across layers are combined. last, sum, max or concat')
parser.add_argument('--dataset', type=str, default = 'zinc_standard_agent', help='root directory of dataset. For now, only classification.')
parser.add_argument('--output_model_file', type = str, default = '', help='filename to output the pre-trained model')
parser.add_argument('--gnn_type', type=str, default="gin")
parser.add_argument('--num_workers', type=int, default = 8, help='number of workers for dataset loading')
args = parser.parse_args()
torch.manual_seed(0)
np.random.seed(0)
device = torch.device("cuda:" + str(args.device)) if torch.cuda.is_available() else torch.device("cpu")
if torch.cuda.is_available():
torch.cuda.manual_seed_all(0)
#set up dataset
dataset = MoleculeDataset("dataset/" + args.dataset, dataset=args.dataset, transform = NegativeEdge())
print(dataset[0])
loader = DataLoaderAE(dataset, batch_size=args.batch_size, shuffle=True, num_workers = args.num_workers)
#set up model
model = GNN(args.num_layer, args.emb_dim, JK = args.JK, drop_ratio = args.dropout_ratio, gnn_type = args.gnn_type)
model.to(device)
#set up optimizer
optimizer = optim.Adam(model.parameters(), lr=args.lr, weight_decay=args.decay)
print(optimizer)
for epoch in range(1, args.epochs+1):
print("====epoch " + str(epoch))
train_acc, train_loss = train(args, model, device, loader, optimizer)
print(train_acc)
print(train_loss)
if not args.output_model_file == "":
torch.save(model.state_dict(), args.output_model_file + ".pth")
model = GNN(*data_train.size, embed_size, dropout).to(device)
criterion = nn.MSELoss()
optimizer = optim.Adam(model.parameters(), lr=learning_rate)
for epoch in range(num_epochs):
model.train()
y_pred = model(data_train).reshape(-1)
y = data_train.edge_type.float()
loss = criterion(y_pred, y)
optimizer.zero_grad()
loss.backward()
optimizer.step()
rmse_loss_train = loss.item()**0.5
model.eval()
with torch.no_grad():
y_pred = model(data_test).reshape(-1)
y = data_test.edge_type.float()
rmse_loss_test = criterion(y_pred, y).item()**0.5
print(f' [Epoch {epoch + 1:3}/{num_epochs}]', end=' ')
print(
f'RMSE Loss (Train: {rmse_loss_train:6.4f} | Test: {rmse_loss_test:6.4f})'
)
torch.save(model.state_dict(), f'model/model.ckpt')
def main():
# Training settings
parser = argparse.ArgumentParser(
description=
'PyTorch implementation of pre-training of graph neural networks')
parser.add_argument('--device',
type=int,
default=0,
help='which gpu to use if any (default: 0)')
parser.add_argument('--batch_size',
type=int,
default=2,
help='input batch size for training (default: 256)')
parser.add_argument('--epochs',
type=int,
default=100,
help='number of epochs to train (default: 100)')
parser.add_argument('--lr',
type=float,
default=0.001,
help='learning rate (default: 0.001)')
parser.add_argument('--decay',
type=float,
default=0,
help='weight decay (default: 0)')
parser.add_argument(
'--num_layer',
type=int,
default=5,
help='number of GNN message passing layers (default: 5).')
parser.add_argument('--l1', type=int, default=1, help='l1 (default: 1).')
parser.add_argument('--center',
type=int,
default=0,
help='center (default: 0).')
parser.add_argument('--emb_dim',
type=int,
default=300,
help='embedding dimensions (default: 300)')
parser.add_argument('--dropout_ratio',
type=float,
default=0,
help='dropout ratio (default: 0)')
parser.add_argument(
'--neg_samples',
type=int,
default=1,
help='number of negative contexts per positive context (default: 1)')
parser.add_argument(
'--JK',
type=str,
default="last",
help=
'how the node features are combined across layers. last, sum, max or concat'
)
parser.add_argument('--context_pooling',
type=str,
default="mean",
help='how the contexts are pooled (sum, mean, or max)')
parser.add_argument('--gnn_type', type=str, default="gat")
parser.add_argument('--mode',
type=str,
default="cbow",
help="cbow or skipgram")
parser.add_argument('--model_file',
type=str,
default='',
help='filename to output the model')
parser.add_argument('--num_workers',
type=int,
default=4,
help='number of workers for dataset loading')
args = parser.parse_args()
torch.manual_seed(0)
np.random.seed(0)
device = torch.device(
"cuda:" +
str(args.device)) if torch.cuda.is_available() else torch.device("cpu")
if torch.cuda.is_available():
torch.cuda.manual_seed_all(0)
print(args.mode)
#set up dataset
root_unsupervised = 'dataset/unsupervised'
dataset = BioDataset(root_unsupervised,
data_type='unsupervised',
transform=ExtractSubstructureContextPair(
l1=args.l1, center=args.center))
print(dataset[0], "\n", dataset[1], "\n", len(dataset))
print("l1: " + str(args.l1))
print("center: " + str(args.center))
loader = DataLoaderSubstructContext(dataset,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.num_workers)
#print(dataset[0])
#set up models, one for pre-training and one for context embeddings
model_substruct = GNN(args.num_layer,
args.emb_dim,
JK=args.JK,
drop_ratio=args.dropout_ratio,
gnn_type=args.gnn_type).to(device)
model_context = GNN(3,
args.emb_dim,
JK=args.JK,
drop_ratio=args.dropout_ratio,
gnn_type=args.gnn_type).to(device)
#set up optimizer for the two GNNs
optimizer_substruct = optim.Adam(model_substruct.parameters(),
lr=args.lr,
weight_decay=args.decay)
optimizer_context = optim.Adam(model_context.parameters(),
lr=args.lr,
weight_decay=args.decay)
for epoch in range(1, args.epochs + 1):
print("====epoch " + str(epoch))
train_loss, train_acc = train(args, model_substruct, model_context,
loader, optimizer_substruct,
optimizer_context, device)
print(train_loss, train_acc)
if not args.model_file == "":
torch.save(model_substruct.state_dict(), args.model_file + ".pth")
def main():
# Training settings
parser = argparse.ArgumentParser(
description=
'PyTorch implementation of pre-training of graph neural networks')
parser.add_argument('--device',
type=int,
default=0,
help='which gpu to use if any (default: 0)')
parser.add_argument('--batch_size',
type=int,
default=256,
help='input batch size for training (default: 256)')
parser.add_argument('--epochs',
type=int,
default=100,
help='number of epochs to train (default: 100)')
parser.add_argument('--lr',
type=float,
default=0.001,
help='learning rate (default: 0.001)')
parser.add_argument('--decay',
type=float,
default=0,
help='weight decay (default: 0)')
parser.add_argument(
'--num_layer',
type=int,
default=5,
help='number of GNN message passing layers (default: 5).')
parser.add_argument('--emb_dim',
type=int,
default=300,
help='embedding dimensions (default: 300)')
parser.add_argument('--dropout_ratio',
type=float,
default=0,
help='dropout ratio (default: 0)')
parser.add_argument('--mask_rate',
type=float,
default=0.15,
help='dropout ratio (default: 0.15)')
parser.add_argument(
'--mask_edge',
type=int,
default=0,
help='whether to mask edges or not together with atoms')
parser.add_argument(
'--JK',
type=str,
default="last",
help=
'how the node features are combined across layers. last, sum, max or concat'
)
parser.add_argument('--dataset',
type=str,
default='zinc_standard_agent',
help='root directory of dataset for pretraining')
parser.add_argument('--output_model_file',
type=str,
default='',
help='filename to output the model')
parser.add_argument('--gnn_type', type=str, default="gin")
parser.add_argument('--seed',
type=int,
default=0,
help="Seed for splitting dataset.")
parser.add_argument('--num_workers',
type=int,
default=8,
help='number of workers for dataset loading')
args = parser.parse_args()
torch.manual_seed(0)
np.random.seed(0)
device = torch.device(
"cuda:" +
str(args.device)) if torch.cuda.is_available() else torch.device("cpu")
if torch.cuda.is_available():
torch.cuda.manual_seed_all(0)
print("num layer: %d mask rate: %f mask edge: %d" %
(args.num_layer, args.mask_rate, args.mask_edge))
#set up dataset and transform function.
dataset = MoleculeDataset("dataset/" + args.dataset,
dataset=args.dataset,
transform=MaskAtom(num_atom_type=119,
num_edge_type=5,
mask_rate=args.mask_rate,
mask_edge=args.mask_edge))
loader = DataLoaderMasking(dataset,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.num_workers)
#set up models, one for pre-training and one for context embeddings
model = GNN(args.num_layer,
args.emb_dim,
JK=args.JK,
drop_ratio=args.dropout_ratio,
gnn_type=args.gnn_type).to(device)
linear_pred_atoms = torch.nn.Linear(args.emb_dim, 119).to(device)
linear_pred_bonds = torch.nn.Linear(args.emb_dim, 4).to(device)
model_list = [model, linear_pred_atoms, linear_pred_bonds]
#set up optimizers
optimizer_model = optim.Adam(model.parameters(),
lr=args.lr,
weight_decay=args.decay)
optimizer_linear_pred_atoms = optim.Adam(linear_pred_atoms.parameters(),
lr=args.lr,
weight_decay=args.decay)
optimizer_linear_pred_bonds = optim.Adam(linear_pred_bonds.parameters(),
lr=args.lr,
weight_decay=args.decay)
optimizer_list = [
optimizer_model, optimizer_linear_pred_atoms,
optimizer_linear_pred_bonds
]
for epoch in range(1, args.epochs + 1):
print("====epoch " + str(epoch))
train_loss, train_acc_atom, train_acc_bond = train(
args, model_list, loader, optimizer_list, device)
print(train_loss, train_acc_atom, train_acc_bond)
if not args.output_model_file == "":
torch.save(model.state_dict(), args.output_model_file + ".pth")
def main():
# Training settings
parser = argparse.ArgumentParser(
description=
'PyTorch implementation of pre-training of graph neural networks')
parser.add_argument('--device',
type=int,
default=0,
help='which gpu to use if any (default: 0)')
parser.add_argument('--batch_size',
type=int,
default=32,
help='input batch size for training (default: 256)')
parser.add_argument('--epochs',
type=int,
default=100,
help='number of epochs to train (default: 100)')
parser.add_argument('--lr',
type=float,
default=0.001,
help='learning rate (default: 0.001)')
parser.add_argument('--decay',
type=float,
default=0,
help='weight decay (default: 0)')
parser.add_argument(
'--num_layer',
type=int,
default=5,
help='number of GNN message passing layers (default: 5).')
parser.add_argument('--emb_dim',
type=int,
default=300,
help='embedding dimensions (default: 300)')
parser.add_argument('--dropout_ratio',
type=float,
default=0,
help='dropout ratio (default: 0)')
parser.add_argument('--mask_rate',
type=float,
default=0.15,
help='dropout ratio (default: 0.15)')
parser.add_argument(
'--JK',
type=str,
default="last",
help=
'how the node features are combined across layers. last, sum, max or concat'
)
parser.add_argument('--gnn_type', type=str, default="gsan")
parser.add_argument('--model_file',
type=str,
default='',
help='filename to output the model')
parser.add_argument('--seed',
type=int,
default=0,
help="Seed for splitting dataset.")
parser.add_argument('--num_workers',
type=int,
default=8,
help='number of workers for dataset loading')
args = parser.parse_args()
torch.manual_seed(0)
np.random.seed(0)
device = torch.device(
"cuda:" +
str(args.device)) if torch.cuda.is_available() else torch.device("cpu")
if torch.cuda.is_available():
torch.cuda.manual_seed_all(0)
print("num layer: %d mask rate: %f" % (args.num_layer, args.mask_rate))
#set up dataset
root_unsupervised = 'dataset/unsupervised'
dataset = BioDataset(root_unsupervised,
data_type='unsupervised',
transform=MaskEdge(mask_rate=args.mask_rate))
print(dataset)
loader = DataLoaderMasking(dataset,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.num_workers)
#set up models, one for pre-training and one for context embeddings
model = GNN(args.num_layer,
args.emb_dim,
JK=args.JK,
drop_ratio=args.dropout_ratio,
gnn_type=args.gnn_type).to(device)
#Linear layer for classifying different edge types
linear_pred_edges = torch.nn.Linear(args.emb_dim, 7).to(device)
model_list = [model, linear_pred_edges]
#set up optimizers
optimizer_model = optim.Adam(model.parameters(),
lr=args.lr,
weight_decay=args.decay)
optimizer_linear_pred_edges = optim.Adam(linear_pred_edges.parameters(),
lr=args.lr,
weight_decay=args.decay)
optimizer_list = [optimizer_model, optimizer_linear_pred_edges]
for epoch in range(1, args.epochs + 1):
print("====epoch " + str(epoch))
train_loss, train_acc = train(args, model_list, loader, optimizer_list,
device)
print("loss :", train_loss, "accuracy :", train_acc)
if not args.model_file == "":
torch.save(model.state_dict(), args.model_file + ".pth")
def main():
# Training settings
parser = argparse.ArgumentParser(
description=
"PyTorch implementation of pre-training of graph neural networks")
parser.add_argument("--device",
type=int,
default=0,
help="which gpu to use if any (default: 0)")
parser.add_argument(
"--batch_size",
type=int,
default=256,
help="input batch size for training (default: 256)",
)
parser.add_argument(
"--epochs",
type=int,
default=100,
help="number of epochs to train (default: 100)",
)
parser.add_argument("--lr",
type=float,
default=0.001,
help="learning rate (default: 0.001)")
parser.add_argument("--decay",
type=float,
default=0,
help="weight decay (default: 0)")
parser.add_argument(
"--num_layer",
type=int,
default=5,
help="number of GNN message passing layers (default: 5).",
)
parser.add_argument("--csize",
type=int,
default=3,
help="context size (default: 3).")
parser.add_argument("--emb_dim",
type=int,
default=300,
help="embedding dimensions (default: 300)")
parser.add_argument("--dropout_ratio",
type=float,
default=0,
help="dropout ratio (default: 0)")
parser.add_argument(
"--neg_samples",
type=int,
default=1,
help="number of negative contexts per positive context (default: 1)",
)
parser.add_argument(
"--JK",
type=str,
default="last",
help="how the node features are combined across layers."
"last, sum, max or concat",
)
parser.add_argument(
"--context_pooling",
type=str,
default="mean",
help="how the contexts are pooled (sum, mean, or max)",
)
parser.add_argument("--mode",
type=str,
default="cbow",
help="cbow or skipgram")
parser.add_argument(
"--dataset",
type=str,
default="contextPred/chem/dataset/zinc_standard_agent",
help="root directory of dataset for pretraining",
)
parser.add_argument("--output_model_file",
type=str,
default="",
help="filename to output the model")
parser.add_argument("--gnn_type", type=str, default="gin")
parser.add_argument("--seed",
type=int,
default=0,
help="Seed for splitting dataset.")
parser.add_argument(
"--num_workers",
type=int,
default=8,
help="number of workers for dataset loading",
)
args = parser.parse_args()
torch.manual_seed(0)
np.random.seed(0)
device = (torch.device("cuda:" + str(args.device))
if torch.cuda.is_available() else torch.device("cpu"))
if torch.cuda.is_available():
torch.cuda.manual_seed_all(0)
l1 = args.num_layer - 1
l2 = l1 + args.csize
print(args.mode)
print("num layer: %d l1: %d l2: %d" % (args.num_layer, l1, l2))
# set up dataset and transform function.
dataset = MoleculeDataset(
args.dataset,
dataset=os.path.basename(args.dataset),
transform=ExtractSubstructureContextPair(args.num_layer, l1, l2),
)
loader = DataLoaderSubstructContext(dataset,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.num_workers)
# set up models, one for pre-training and one for context embeddings
model_substruct = GNN(
args.num_layer,
args.emb_dim,
JK=args.JK,
drop_ratio=args.dropout_ratio,
gnn_type=args.gnn_type,
).to(device)
model_context = GNN(
int(l2 - l1),
args.emb_dim,
JK=args.JK,
drop_ratio=args.dropout_ratio,
gnn_type=args.gnn_type,
).to(device)
# set up optimizer for the two GNNs
optimizer_substruct = optim.Adam(model_substruct.parameters(),
lr=args.lr,
weight_decay=args.decay)
optimizer_context = optim.Adam(model_context.parameters(),
lr=args.lr,
weight_decay=args.decay)
for epoch in range(1, args.epochs + 1):
print("====epoch " + str(epoch))
train_loss, train_acc = train(
args,
model_substruct,
model_context,
loader,
optimizer_substruct,
optimizer_context,
device,
)
print(train_loss, train_acc)
if not args.output_model_file == "":
torch.save(model_substruct.state_dict(),
args.output_model_file + ".pth")
