def main():
parser = argparse.ArgumentParser(description='OGBN-Arxiv (GNN)')
parser.add_argument('--device', type=int, default=0)
parser.add_argument('--log_steps', type=int, default=1)
parser.add_argument('--use_sage', action='store_true')
parser.add_argument('--num_layers', type=int, default=3)
parser.add_argument('--hidden_channels', type=int, default=256)
parser.add_argument('--dropout', type=float, default=0.5)
parser.add_argument('--lr', type=float, default=0.01)
parser.add_argument('--epochs', type=int, default=500)
parser.add_argument('--runs', type=int, default=10)
parser.add_argument('--kind', type=str, default="ReLU")
args = parser.parse_args()
print(args)
device = f'cuda:{args.device}' if torch.cuda.is_available() else 'cpu'
device = 'cpu'
device = torch.device(device)
dataset = PygNodePropPredDataset(name='ogbn-arxiv',
transform=T.ToSparseTensor())
data = dataset[0]
data.adj_t = data.adj_t.to_symmetric()
data = data.to(device)
split_idx = dataset.get_idx_split()
train_idx = split_idx['train'].to(device)
if args.use_sage:
model = SAGE(data.num_features, args.hidden_channels,
dataset.num_classes, args.num_layers,
args.dropout, kind=args.kind).to(device)
else:
model = GCN(data.num_features, args.hidden_channels,
dataset.num_classes, args.num_layers,
args.dropout, kind=args.kind).to(device)
evaluator = Evaluator(name='ogbn-arxiv')
logger = Logger(args.runs, args)
for run in range(args.runs):
model.reset_parameters()
optimizer = torch.optim.Adam(model.parameters(), lr=args.lr)
for epoch in range(1, 1 + args.epochs):
loss = train(model, data, train_idx, optimizer)
result = test(model, data, split_idx, evaluator)
logger.add_result(run, result)
if epoch % args.log_steps == 0:
train_acc, valid_acc, test_acc = result
print(f'Run: {run + 1:02d}, '
f'Epoch: {epoch:02d}, '
f'Loss: {loss:.4f}, '
f'Train: {100 * train_acc:.2f}%, '
f'Valid: {100 * valid_acc:.2f}% '
f'Test: {100 * test_acc:.2f}%')
logger.print_statistics(run)
logger.print_statistics()
def load_data(dataset_name="Cora", seed=10, n_splits=5):
# Path in which the data will be stored
path = osp.join(osp.dirname(osp.realpath(__file__)), '..', 'data',
dataset_name)
if dataset_name in ["CS", "Physics"]:
dataset = Coauthor(path, dataset_name, T.NormalizeFeatures())
elif dataset_name in ["Computers", "Photo"]:
dataset = Amazon(path, dataset_name, T.NormalizeFeatures())
elif dataset_name in ["Cora", "Citeseer", "Pubmed"]:
dataset = Planetoid(path,
dataset_name,
split='public',
transform=T.NormalizeFeatures())
elif dataset_name in ["Arxiv", "Papers", "Products"]:
dataset = PygNodePropPredDataset(name=ogb_data_name_conv[dataset_name],
root=path,
transform=T.NormalizeFeatures())
elif dataset_name == "MAG":
dataset = PygNodePropPredDataset(name=ogb_data_name_conv[dataset_name],
root=path)
else:
raise Exception("[!] Dataset not found: ", str(dataset_name))
if dataset_name in obg_datasets:
data = split_ogb_data(dataset, dataset_name)
else:
data = dataset[0] # pyg graph object
data = split_data(data, seed, n_splits)
data.num_classes = dataset.num_classes
return data
def eval_with_partition(args):
model_load_path = args.model_load_path
print("Starting evaluating model stored at", model_load_path)
device = torch.device("cuda")
dataset = PygNodePropPredDataset(name=args.dataset, root=args.data_folder)
graph = dataset[0]
adj = SparseTensor(row=graph.edge_index[0], col=graph.edge_index[1])
if args.self_loop:
adj = adj.set_diag()
graph.edge_index = add_self_loops(edge_index=graph.edge_index,
num_nodes=graph.num_nodes)[0]
split_idx = dataset.get_idx_split()
evaluator = Evaluator(args.dataset)
args.in_channels = graph.x.size(-1)
args.num_tasks = dataset.num_classes
# print('%s' % args)
model = DeeperGCN(args).to(device)
ckpt = torch.load(model_load_path)
model.load_state_dict(ckpt['model_state_dict'])
res = test_with_partition(model,
graph,
adj,
split_idx,
num_clusters=args.eval_cluster_number,
partition_method=args.partition_method,
evaluator=evaluator,
device=device)
print(res)
return res
def __init__(self, path):
dataset = "ogbn-proteins"
# path = osp.join(osp.dirname(osp.realpath(__file__)), "../..", "data", dataset)
PygNodePropPredDataset(name=dataset, root=path)
super(OGBNproteinsDataset, self).__init__(dataset, path)
dataset_t = PygNodePropPredDataset(name=dataset,
root=path,
transform=T.ToSparseTensor())
# Move edge features to node features.
self.data.x = dataset_t[0].adj_t.mean(dim=1)
# dataset_t[0].adj_t.set_value_(None)
del dataset_t
setattr(OGBNproteinsDataset, "metric", "ROC-AUC")
setattr(OGBNproteinsDataset, "loss",
"binary_cross_entropy_with_logits")
split_idx = self.get_idx_split()
datalist = []
for d in self:
setattr(d, "train_mask",
index_to_mask(split_idx['train'], d.y.shape[0]))
setattr(d, "val_mask",
index_to_mask(split_idx['valid'], d.y.shape[0]))
setattr(d, "test_mask",
index_to_mask(split_idx['test'], d.y.shape[0]))
datalist.append(d)
self.data, self.slices = self.collate(datalist)
def get_product_clusters():
dataset_name = "ogbn-products"
dataset = PygNodePropPredDataset(name=dataset_name)
print('The {} dataset has {} graph'.format(dataset_name, len(dataset)))
data = dataset[0]
print(data)
split_idx = dataset.get_idx_split()
train_idx = split_idx['train']
val_idx = split_idx['valid']
test_idx = split_idx['test']
train_mask = torch.zeros(data.num_nodes, dtype=torch.bool)
train_mask[train_idx] = True
data['train_mask'] = train_mask
val_mask = torch.zeros(data.num_nodes, dtype=torch.bool)
val_mask[val_idx] = True
data['valid_mask'] = val_mask
test_mask = torch.zeros(data.num_nodes, dtype=torch.bool)
test_mask[test_idx] = True
data['test_mask'] = test_mask
cluster_data = ClusterData(data, num_parts=15000, save_dir="dataset")
return cluster_data, dataset, data, split_idx
def main():
parser = argparse.ArgumentParser(description='OGBN-Proteins (MLP)')
parser.add_argument('--device', type=int, default=0)
parser.add_argument('--log_steps', type=int, default=1)
parser.add_argument('--use_node_embedding', action='store_true')
parser.add_argument('--num_layers', type=int, default=3)
parser.add_argument('--hidden_channels', type=int, default=256)
parser.add_argument('--dropout', type=float, default=0.5)
parser.add_argument('--lr', type=float, default=0.01)
parser.add_argument('--epochs', type=int, default=1000)
parser.add_argument('--eval_steps', type=int, default=5)
parser.add_argument('--runs', type=int, default=10)
args = parser.parse_args()
print(args)
device = f'cuda:{args.device}' if torch.cuda.is_available() else 'cpu'
device = torch.device(device)
dataset = PygNodePropPredDataset(name='ogbn-proteins')
split_idx = dataset.get_idx_split()
data = dataset[0]
x = scatter(data.edge_attr, data.edge_index[0], dim=0,
dim_size=data.num_nodes, reduce='mean').to('cpu')
if args.use_node_embedding:
embedding = torch.load('embedding.pt', map_location='cpu')
x = torch.cat([x, embedding], dim=-1)
x = x.to(device)
y_true = data.y.to(device)
train_idx = split_idx['train'].to(device)
model = MLP(x.size(-1), args.hidden_channels, 112, args.num_layers,
args.dropout).to(device)
evaluator = Evaluator(name='ogbn-proteins')
logger = Logger(args.runs, args)
for run in range(args.runs):
model.reset_parameters()
optimizer = torch.optim.Adam(model.parameters(), lr=args.lr)
for epoch in range(1, 1 + args.epochs):
loss = train(model, x, y_true, train_idx, optimizer)
if epoch % args.eval_steps == 0:
result = test(model, x, y_true, split_idx, evaluator)
logger.add_result(run, result)
if epoch % args.log_steps == 0:
train_rocauc, valid_rocauc, test_rocauc = result
print(f'Run: {run + 1:02d}, '
f'Epoch: {epoch:02d}, '
f'Loss: {loss:.4f}, '
f'Train: {100 * train_rocauc:.2f}%, '
f'Valid: {100 * valid_rocauc:.2f}% '
f'Test: {100 * test_rocauc:.2f}%')
logger.print_statistics(run)
logger.print_statistics()
def main():
args = ArgsInit().args
dataset = PygNodePropPredDataset(name=args.dataset)
graph = dataset[0]
if args.self_loop:
graph.edge_index = add_self_loops(edge_index=graph.edge_index,
num_nodes=graph.num_nodes)[0]
split_idx = dataset.get_idx_split()
evaluator = Evaluator(args.dataset)
args.in_channels = graph.x.size(-1)
args.num_tasks = dataset.num_classes
print(args)
model = DeeperGCN(args)
print(model)
model.load_state_dict(torch.load(args.model_load_path)['model_state_dict'])
result = test(model, graph.x, graph.edge_index, graph.y, split_idx,
evaluator)
print(result)
model.print_params(final=True)
def main():
parser = argparse.ArgumentParser(description="OGBN-Arxiv (MLP)")
parser.add_argument("--device", type=int, default=0)
parser.add_argument("--log_steps", type=int, default=1)
parser.add_argument("--use_node_embedding", action="store_true")
parser.add_argument("--num_layers", type=int, default=3)
parser.add_argument("--hidden_channels", type=int, default=256)
parser.add_argument("--dropout", type=float, default=0.5)
parser.add_argument("--lr", type=float, default=0.01)
parser.add_argument("--epochs", type=int, default=500)
parser.add_argument("--runs", type=int, default=10)
args = parser.parse_args()
print(args)
device = f"cuda:{args.device}" if torch.cuda.is_available() else "cpu"
device = torch.device(device)
dataset = PygNodePropPredDataset(name="ogbn-arxiv")
split_idx = dataset.get_idx_split()
data = dataset[0]
x = data.x
if args.use_node_embedding:
embedding = torch.load("embedding.pt", map_location="cpu")
x = torch.cat([x, embedding], dim=-1)
x = x.to(device)
y_true = data.y.to(device)
train_idx = split_idx["train"].to(device)
model = MLP(
x.size(-1),
args.hidden_channels,
dataset.num_classes,
args.num_layers,
args.dropout,
).to(device)
evaluator = Evaluator(name="ogbn-arxiv")
logger = Logger(args.runs, args)
for run in range(args.runs):
model.reset_parameters()
optimizer = torch.optim.Adam(model.parameters(), lr=args.lr)
for epoch in range(1, 1 + args.epochs):
loss = train(model, x, y_true, train_idx, optimizer)
result = test(model, x, y_true, split_idx, evaluator)
logger.add_result(run, result)
if epoch % args.log_steps == 0:
train_acc, valid_acc, test_acc = result
print(f"Run: {run + 1:02d}, "
f"Epoch: {epoch:02d}, "
f"Loss: {loss:.4f}, "
f"Train: {100 * train_acc:.2f}%, "
f"Valid: {100 * valid_acc:.2f}%, "
f"Test: {100 * test_acc:.2f}%")
logger.print_statistics(run)
logger.print_statistics()
def main():
parser = argparse.ArgumentParser(description='OGBN-Arxiv (GNN)')
parser.add_argument('--device', type=int, default=0)
parser.add_argument('--log_steps', type=int, default=1)
parser.add_argument('--use_sage', action='store_true')
parser.add_argument('--num_layers', type=int, default=3)
parser.add_argument('--hidden_channels', type=int, default=256)
parser.add_argument('--dropout', type=float, default=0.5)
parser.add_argument('--lr', type=float, default=0.01)
parser.add_argument('--epochs', type=int, default=3000)
parser.add_argument('--runs', type=int, default=1)
args = parser.parse_args()
print(args)
device = f'cuda:{args.device}' if torch.cuda.is_available() else 'cpu'
device = torch.device(device)
dataset = PygNodePropPredDataset(name='ogbn-arxiv',root='/mnt/ogbdata',
transform=T.ToSparseTensor())
data = dataset[0]
data.adj_t = data.adj_t.to_symmetric()
data = data.to(device)
split_idx = dataset.get_idx_split()
print(split_idx['train'].nonzero().size(0)/len(split_idx['train']),
split_idx['valid'].nonzero().size(0)/len(split_idx['train']),
split_idx['test'].nonzero().size(0)/len(split_idx['train']))
def eval_model(params):
model_load_path, args = params
if os.path.isdir(args.model_load_path):
model_load_dir = args.model_load_path
model_load_path = os.path.join(model_load_dir, model_load_path)
print("Starting evaluating model stored at", model_load_path)
dataset = PygNodePropPredDataset(name=args.dataset, root=args.data_folder)
graph = dataset[0]
if args.self_loop:
graph.edge_index = add_self_loops(edge_index=graph.edge_index,
num_nodes=graph.num_nodes)[0]
split_idx = dataset.get_idx_split()
evaluator = Evaluator(args.dataset)
args.in_channels = graph.x.size(-1)
args.num_tasks = dataset.num_classes
model = DeeperGCN(args)
ckpt = torch.load(model_load_path, map_location=torch.device('cpu'))
model.load_state_dict(ckpt['model_state_dict'])
test_res = test(model, graph.x, graph.edge_index, graph.y, split_idx,
evaluator)
test_res["model_load_path"] = model_load_path
return test_res
def main():
parser = argparse.ArgumentParser(description='OGBN-Products (MLP)')
parser.add_argument('--device', type=int, default=0)
parser.add_argument('--log_steps', type=int, default=1)
parser.add_argument('--use_node_embedding', action='store_true')
parser.add_argument('--num_layers', type=int, default=3)
parser.add_argument('--hidden_channels', type=int, default=256)
parser.add_argument('--dropout', type=float, default=0.0)
parser.add_argument('--lr', type=float, default=0.01)
parser.add_argument('--epochs', type=int, default=300)
parser.add_argument('--runs', type=int, default=10)
args = parser.parse_args()
print(args)
device = f'cuda:{args.device}' if torch.cuda.is_available() else 'cpu'
device = torch.device(device)
dataset = PygNodePropPredDataset(name='ogbn-products')
split_idx = dataset.get_idx_split()
data = dataset[0]
x = data.x
if args.use_node_embedding:
embedding = np.load('./embed_results/embeddings.npy')
embedding = torch.from_numpy(embedding).float()
x = torch.cat([x, embedding], dim=-1)
x = x.to(device)
y_true = data.y.to(device)
train_idx = split_idx['train'].to(device)
model = MLP(x.size(-1), args.hidden_channels, dataset.num_classes,
args.num_layers, args.dropout).to(device)
evaluator = Evaluator(name='ogbn-products')
logger = Logger(args.runs, args)
for run in range(args.runs):
model.reset_parameters()
optimizer = torch.optim.Adam(model.parameters(), lr=args.lr)
for epoch in range(1, 1 + args.epochs):
loss = train(model, x, y_true, train_idx, optimizer)
result = test(model, x, y_true, split_idx, evaluator)
logger.add_result(run, result)
if epoch % args.log_steps == 0:
train_acc, valid_acc, test_acc = result
print(f'Run: {run + 1:02d}, '
f'Epoch: {epoch:02d}, '
f'Loss: {loss:.4f}, '
f'Train: {100 * train_acc:.2f}%, '
f'Valid: {100 * valid_acc:.2f}%, '
f'Test: {100 * test_acc:.2f}%')
logger.print_statistics(run)
logger.print_statistics()
total_params = sum(p.numel() for p in model.parameters())
print(f'mlp total params are {total_params}')
def main_fixed_mask(args):
device = torch.device("cuda:" + str(args.device))
dataset = PygNodePropPredDataset(name=args.dataset)
data = dataset[0]
split_idx = dataset.get_idx_split()
evaluator = Evaluator(args.dataset)
x = data.x.to(device)
y_true = data.y.to(device)
train_idx = split_idx['train'].to(device)
edge_index = data.edge_index.to(device)
edge_index = to_undirected(edge_index, data.num_nodes)
if args.self_loop:
edge_index = add_self_loops(edge_index, num_nodes=data.num_nodes)[0]
args.in_channels = data.x.size(-1)
args.num_tasks = dataset.num_classes
model = DeeperGCN(args).to(device)
pruning.add_mask(model, args.num_layers)
for name, param in model.named_parameters():
if 'mask' in name:
param.requires_grad = False
optimizer = torch.optim.Adam(model.parameters(), lr=args.lr)
results = {'highest_valid': 0, 'final_train': 0, 'final_test': 0, 'highest_train': 0, 'epoch': 0}
start_epoch = 1
for epoch in range(start_epoch, args.epochs + 1):
epoch_loss = train_fixed(model, x, edge_index, y_true, train_idx, optimizer, args)
result = test(model, x, edge_index, y_true, split_idx, evaluator)
train_accuracy, valid_accuracy, test_accuracy = result
if valid_accuracy > results['highest_valid']:
results['highest_valid'] = valid_accuracy
results['final_train'] = train_accuracy
results['final_test'] = test_accuracy
results['epoch'] = epoch
print(time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()) + ' | ' +
'Baseline (FIX Mask) Epoch:[{}/{}]\t LOSS:[{:.4f}] Train :[{:.2f}] Valid:[{:.2f}] Test:[{:.2f}] | Update Test:[{:.2f}] at epoch:[{}]'
.format(epoch, args.epochs, epoch_loss, train_accuracy * 100,
valid_accuracy * 100,
test_accuracy * 100,
results['final_test'] * 100,
results['epoch']))
print("=" * 120)
print("syd final: Baseline, Train:[{:.2f}] Best Val:[{:.2f}] at epoch:[{}] | Final Test Acc:[{:.2f}]"
.format( results['final_train'] * 100,
results['highest_valid'] * 100,
results['epoch'],
results['final_test'] * 100))
print("=" * 120)
def main():
parser = argparse.ArgumentParser(description='OGBN-Products (SIGN)')
parser.add_argument('--device', type=int, default=0)
parser.add_argument('--log_steps', type=int, default=1)
parser.add_argument('--num_layers', type=int, default=3)
parser.add_argument('--hidden_channels', type=int, default=256)
parser.add_argument('--dropout', type=float, default=0.5)
parser.add_argument('--lr', type=float, default=0.01)
parser.add_argument('--epochs', type=int, default=200)
parser.add_argument('--runs', type=int, default=10)
args = parser.parse_args()
print(args)
device = f'cuda:{args.device}' if torch.cuda.is_available() else 'cpu'
device = torch.device(device)
dataset = PygNodePropPredDataset(name='ogbn-products')
split_idx = dataset.get_idx_split()
data = SIGN(args.num_layers)(dataset[0]) # This might take a while.
xs = [data.x] + [data[f'x{i}'] for i in range(1, args.num_layers + 1)]
xs_train = [x[split_idx['train']].to(device) for x in xs]
xs_valid = [x[split_idx['valid']].to(device) for x in xs]
xs_test = [x[split_idx['test']].to(device) for x in xs]
y_train_true = data.y[split_idx['train']].to(device)
y_valid_true = data.y[split_idx['valid']].to(device)
y_test_true = data.y[split_idx['test']].to(device)
model = MLP(data.x.size(-1), args.hidden_channels, dataset.num_classes,
args.num_layers, args.dropout).to(device)
evaluator = Evaluator(name='ogbn-products')
logger = Logger(args.runs, args)
for run in range(args.runs):
model.reset_parameters()
optimizer = torch.optim.Adam(model.parameters(), lr=args.lr)
for epoch in range(1, 1 + args.epochs):
loss = train(model, xs_train, y_train_true, optimizer)
train_acc = test(model, xs_train, y_train_true, evaluator)
valid_acc = test(model, xs_valid, y_valid_true, evaluator)
test_acc = test(model, xs_test, y_test_true, evaluator)
result = (train_acc, valid_acc, test_acc)
logger.add_result(run, result)
if epoch % args.log_steps == 0:
train_acc, valid_acc, test_acc = result
print(f'Run: {run + 1:02d}, '
f'Epoch: {epoch:02d}, '
f'Loss: {loss:.4f}, '
f'Train: {100 * train_acc:.2f}%, '
f'Valid: {100 * valid_acc:.2f}%, '
f'Test: {100 * test_acc:.2f}%')
logger.print_statistics(run)
logger.print_statistics()
def load_ogb_2(dataset):
## Load the dataset
## Setup PyTorch
device_name = 'cuda:0' if torch.cuda.is_available() else 'cpu'
device = torch.device(device_name)
dataset = PygNodePropPredDataset(name=dataset,
transform=T.ToSparseTensor())
ogb_data = dataset[0]
# TODO: Not sure how to format adj_t...
ogb_data.adj_t = ogb_data.adj_t.to_symmetric()
ogb_data = ogb_data.to(device)
split_idx = dataset.get_idx_split()
train_idx, valid_idx, test_idx = split_idx["train"], split_idx[
"valid"], split_idx["test"]
train_idx, valid_idx, split_idx = train_idx.numpy(), valid_idx.numpy(
), test_idx.numpy()
# Convert OGB's data split pytorch index vectors to Wang's data split numpy boolean masks
train_mask_2 = indexes2booleanvec(ogb_data.num_nodes, train_idx)
val_mask_2 = indexes2booleanvec(ogb_data.num_nodes, valid_idx)
test_mask_2 = indexes2booleanvec(ogb_data.num_nodes, test_idx)
# Add 1's down the diagonal of adj_t
adj_t = ogb_data.adj_t.to_torch_sparse_coo_tensor()
adj_t = adj_t + sparse_identity(adj_t.shape[0])
# Convert OGB's adjacency SparseTensor to Wang's adjacency index matrix (Nx2)
adj_2_0 = adj_t.coalesce().indices().numpy()
adj_2_0 = adj_2_0.T.astype('int32')
##adj_2_0 = np.vstack((adj_2_0, np.array([[i,i] for i in range(ogb_data.num_nodes)])))
adj_2_1 = adj_t.coalesce().values().numpy().astype('float64')
adj_2_2 = tuple(adj_t.size())
#TODO: Fix the adjacency matrix, bc it probably is symmetric with identity
adj_2 = (adj_2_0, adj_2_1, adj_2_2)
from sklearn.preprocessing import OneHotEncoder
labels_2 = ogb_data.y.numpy()
labels_2 = OneHotEncoder(sparse=False).fit_transform(labels_2)
#TODO: I don't know if this feature vector will work
# OGB used a skip-gram encoding,
# whereas Wang's Citeseer just used normalized rows with 1-0 for different words
x = ogb_data.x + 1.5
norm_x = np.apply_along_axis(np.linalg.norm, 1, x)
x = x / norm_x[:, None]
x = x.to_sparse()
features_2_0 = x.indices().numpy().T.astype('int32')
features_2_1 = x.values().numpy()
#features_2_1 = 1.5 + features_2_1
features_2_1 = features_2_1.astype('float64')
features_2_2 = tuple(x.size())
features_2 = features_2_0, features_2_1, features_2_2
data2 = features_2, labels_2, adj_2, train_mask_2, val_mask_2, test_mask_2
return data2
def main():
parser = argparse.ArgumentParser(description='OGBN-Products (Cluster-GCN)')
parser.add_argument('--device', type=int, default=0)
parser.add_argument('--log_steps', type=int, default=1)
parser.add_argument('--num_partitions', type=int, default=15000)
parser.add_argument('--num_workers', type=int, default=6)
parser.add_argument('--num_layers', type=int, default=3)
parser.add_argument('--hidden_channels', type=int, default=256)
parser.add_argument('--dropout', type=float, default=0.0)
parser.add_argument('--batch_size', type=int, default=256)
parser.add_argument('--lr', type=float, default=0.01)
parser.add_argument('--epochs', type=int, default=20)
parser.add_argument('--runs', type=int, default=10)
args = parser.parse_args()
print(args)
device = f'cuda:{args.device}' if torch.cuda.is_available() else 'cpu'
device = torch.device(device)
dataset = PygNodePropPredDataset(name='ogbn-products')
splitted_idx = dataset.get_idx_split()
data = dataset[0]
# Convert split indices to boolean masks and add them to `data`.
for key, idx in splitted_idx.items():
mask = torch.zeros(data.num_nodes, dtype=torch.bool)
mask[idx] = True
data[f'{key}_mask'] = mask
cluster_data = ClusterData(data,
num_parts=args.num_partitions,
recursive=False,
save_dir=dataset.processed_dir)
loader = ClusterLoader(cluster_data,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.num_workers)
model = SAGE(data.x.size(-1), args.hidden_channels, 47, args.num_layers,
args.dropout).to(device)
evaluator = Evaluator(name='ogbn-products')
logger = Logger(args.runs, args)
for run in range(args.runs):
model.reset_parameters()
optimizer = torch.optim.Adam(model.parameters(), lr=args.lr)
for epoch in range(1, 1 + args.epochs):
loss = train(model, loader, optimizer, device)
if epoch % args.log_steps == 0:
print(f'Run: {run + 1:02d}, '
f'Epoch: {epoch:02d}, '
f'Loss: {loss:.4f}')
result = test(model, data, evaluator)
logger.add_result(run, result)
logger.print_statistics(run)
logger.print_statistics()
def arxiv_data(root):
# keep the same data loading logic for all architectures
dataset = PygNodePropPredDataset(
name="ogbn-arxiv",
root=root, # transform=T.ToSparseTensor(),
)
data = dataset[0]
# data.adj_t = data.adj_t.to_symmetric()
data.edge_index = to_undirected(data.edge_index)
split_idx = dataset.get_idx_split()
return data, split_idx
def get_data(args):
dataset = PygNodePropPredDataset(name=args['dataset_name'], transform=T.ToSparseTensor())
evaluator = Evaluator(name=args['dataset_name'])
data = dataset[0]
data.adj_t = data.adj_t.to_symmetric()
split_idx = dataset.get_idx_split()
device = 'cuda' if torch.cuda.is_available() else 'cpu'
data = data.to(device)
for setname in ['train', 'valid', 'test']:
split_idx[setname] = split_idx[setname].to(device)
return data, dataset, split_idx, evaluator
def get_dataset(path, name):
assert name in ['Cora', 'CiteSeer', 'PubMed', 'DBLP', 'Karate', 'WikiCS', 'Coauthor-CS', 'Coauthor-Phy',
'Amazon-Computers', 'Amazon-Photo', 'ogbn-arxiv', 'ogbg-code']
name = 'dblp' if name == 'DBLP' else name
root_path = osp.expanduser('~/datasets')
if name == 'Coauthor-CS':
return Coauthor(root=path, name='cs', transform=T.NormalizeFeatures())
if name == 'Coauthor-Phy':
return Coauthor(root=path, name='physics', transform=T.NormalizeFeatures())
if name == 'WikiCS':
return WikiCS(root=path, transform=T.NormalizeFeatures())
if name == 'Amazon-Computers':
return Amazon(root=path, name='computers', transform=T.NormalizeFeatures())
if name == 'Amazon-Photo':
return Amazon(root=path, name='photo', transform=T.NormalizeFeatures())
if name.startswith('ogbn'):
return PygNodePropPredDataset(root=osp.join(root_path, 'OGB'), name=name, transform=T.NormalizeFeatures())
return (CitationFull if name == 'dblp' else Planetoid)(osp.join(root_path, 'Citation'), name, transform=T.NormalizeFeatures())
def __init__(self, path):
dataset = "ogbn-products"
# path = osp.join(osp.dirname(osp.realpath(__file__)), "../..", "data", dataset)
PygNodePropPredDataset(name=dataset, root=path)
super(OGBNproductsDataset, self).__init__(dataset, path)
# Pre-compute GCN normalization.
# adj_t = self.data.adj_t.set_diag()
# deg = adj_t.sum(dim=1).to(torch.float)
# deg_inv_sqrt = deg.pow(-0.5)
# deg_inv_sqrt[deg_inv_sqrt == float('inf')] = 0
# adj_t = deg_inv_sqrt.view(-1, 1) * adj_t * deg_inv_sqrt.view(1, -1)
# self.data.adj_t = adj_t
setattr(OGBNproductsDataset, "metric", "Accuracy")
setattr(OGBNproductsDataset, "loss", "nll_loss")
split_idx = self.get_idx_split()
datalist = []
for d in self:
setattr(d, "train_mask",
index_to_mask(split_idx['train'], d.y.shape[0]))
setattr(d, "val_mask",
index_to_mask(split_idx['valid'], d.y.shape[0]))
setattr(d, "test_mask",
index_to_mask(split_idx['test'], d.y.shape[0]))
datalist.append(d)
self.data, self.slices = self.collate(datalist)
def __init__(self, args=None):
dataset = "ogbn-mag"
path = osp.join(osp.dirname(osp.realpath(__file__)), "../..", "data",
dataset)
if not osp.exists(path):
PygNodePropPredDataset(dataset, path)
super(OGBMAGDataset, self).__init__(path, dataset)
def __init__(self, path):
dataset = "ogbn-mag"
# path = osp.join(osp.dirname(osp.realpath(__file__)), "../..", "data", dataset)
PygNodePropPredDataset(name=dataset, root=path)
super(OGBNmagDataset, self).__init__(dataset, path)
# Preprocess
rel_data = self[0]
# We are only interested in paper <-> paper relations.
self.data = Data(
x=rel_data.x_dict["paper"],
edge_index=rel_data.edge_index_dict[("paper", "cites", "paper")],
y=rel_data.y_dict["paper"],
)
# self.data = T.ToSparseTensor()(data)
# self[0].adj_t = self[0].adj_t.to_symmetric()
setattr(OGBNmagDataset, "metric", "Accuracy")
setattr(OGBNmagDataset, "loss", "nll_loss")
split_idx = self.get_idx_split()
datalist = []
for d in self:
setattr(d, "train_mask", index_to_mask(split_idx["train"], d.y.shape[0]))
setattr(d, "val_mask", index_to_mask(split_idx["valid"], d.y.shape[0]))
setattr(d, "test_mask", index_to_mask(split_idx["test"], d.y.shape[0]))
datalist.append(d)
self.data, self.slices = self.collate(datalist)
def __init__(self):
dataset = "ogbn-papers100M"
path = osp.join(osp.dirname(osp.realpath(__file__)), "../..", "data",
dataset)
if not osp.exists(path):
PygNodePropPredDataset(dataset, path)
super(OGBArxivDataset, self).__init__(path, dataset)
def load_ogb(name, dataset_dir):
if name[:4] == 'ogbn':
dataset = PygNodePropPredDataset(name=name, root=dataset_dir)
splits = dataset.get_idx_split()
split_names = ['train_mask', 'val_mask', 'test_mask']
for i, key in enumerate(splits.keys()):
mask = index2mask(splits[key], size=dataset.data.y.shape[0])
set_dataset_attr(dataset, split_names[i], mask, len(mask))
edge_index = to_undirected(dataset.data.edge_index)
set_dataset_attr(dataset, 'edge_index', edge_index,
edge_index.shape[1])
elif name[:4] == 'ogbg':
dataset = PygGraphPropPredDataset(name=name, root=dataset_dir)
splits = dataset.get_idx_split()
split_names = [
'train_graph_index', 'val_graph_index', 'test_graph_index'
]
for i, key in enumerate(splits.keys()):
id = splits[key]
set_dataset_attr(dataset, split_names[i], id, len(id))
elif name[:4] == "ogbl":
dataset = PygLinkPropPredDataset(name=name, root=dataset_dir)
splits = dataset.get_edge_split()
id = splits['train']['edge'].T
if cfg.dataset.resample_negative:
set_dataset_attr(dataset, 'train_pos_edge_index', id, id.shape[1])
# todo: applying transform for negative sampling is very slow
dataset.transform = neg_sampling_transform
else:
id_neg = negative_sampling(edge_index=id,
num_nodes=dataset.data.num_nodes[0],
num_neg_samples=id.shape[1])
id_all = torch.cat([id, id_neg], dim=-1)
label = get_link_label(id, id_neg)
set_dataset_attr(dataset, 'train_edge_index', id_all,
id_all.shape[1])
set_dataset_attr(dataset, 'train_edge_label', label, len(label))
id, id_neg = splits['valid']['edge'].T, splits['valid']['edge_neg'].T
id_all = torch.cat([id, id_neg], dim=-1)
label = get_link_label(id, id_neg)
set_dataset_attr(dataset, 'val_edge_index', id_all, id_all.shape[1])
set_dataset_attr(dataset, 'val_edge_label', label, len(label))
id, id_neg = splits['test']['edge'].T, splits['test']['edge_neg'].T
id_all = torch.cat([id, id_neg], dim=-1)
label = get_link_label(id, id_neg)
set_dataset_attr(dataset, 'test_edge_index', id_all, id_all.shape[1])
set_dataset_attr(dataset, 'test_edge_label', label, len(label))
else:
raise ValueError('OGB dataset: {} non-exist')
return dataset
def load_data(args, datapath):
if args.dataset in ['arxiv'] and args.task == 'lp':
data = {}
dataset = PygNodePropPredDataset(name='ogbn-{}'.format(args.dataset),
root='/pasteur/u/jeffgu/hgcn/data')
split_idx = dataset.get_idx_split()
train_idx, valid_idx, test_idx = split_idx["train"], split_idx[
"valid"], split_idx["test"]
induced_edges_train, _ = subgraph(train_idx, dataset[0].edge_index)
induced_edges_valid, _ = subgraph(valid_idx, dataset[0].edge_index)
induced_edges_test, _ = subgraph(test_idx, dataset[0].edge_index)
neg_edges_train = negative_sampling(induced_edges_train)
neg_edges_valid = negative_sampling(induced_edges_valid)
neg_edges_test = negative_sampling(induced_edges_test)
data['adj_train'] = to_scipy_sparse_matrix(
dataset[0].edge_index).tocsr()
data['features'] = dataset[0].x
data['train_edges'], data[
'train_edges_false'] = induced_edges_train, neg_edges_train
data['val_edges'], data[
'val_edges_false'] = induced_edges_valid, neg_edges_valid
data['test_edges'], data[
'test_edges_false'] = induced_edges_test, neg_edges_test
elif args.task == 'nc':
data = load_data_nc(args.dataset, args.use_feats, datapath,
args.split_seed)
else:
data = load_data_lp(args.dataset, args.use_feats, datapath)
adj = data['adj_train']
if args.task == 'lp':
adj_train, train_edges, train_edges_false, val_edges, val_edges_false, test_edges, test_edges_false = mask_edges(
adj, args.val_prop, args.test_prop, args.split_seed)
data['adj_train'] = adj_train
data['train_edges'], data[
'train_edges_false'] = train_edges, train_edges_false
data['val_edges'], data[
'val_edges_false'] = val_edges, val_edges_false
data['test_edges'], data[
'test_edges_false'] = test_edges, test_edges_false
data['adj_train_norm'], data['features'] = process(data['adj_train'],
data['features'],
args.normalize_adj,
args.normalize_feats)
if args.dataset == 'airport':
data['features'] = augment(data['adj_train'], data['features'])
return data
def create_dataset(name):
if name.startswith("ogbn"):
dataset = name[5:]
if dataset in ["arxiv", "products", "papers100M", "proteins"]:
return PygNodePropPredDataset(name)
elif name.startswith("saint"):
dataset = name[6:]
return SAINTDataset(dataset)
def main():
args = ArgsInit().args
if args.use_gpu:
device = torch.device("cuda:" +
str(args.device)) if torch.cuda.is_available(
) else torch.device("cpu")
else:
device = torch.device('cpu')
dataset = PygNodePropPredDataset(name=args.dataset)
data = dataset[0]
split_idx = dataset.get_idx_split()
evaluator = Evaluator(args.dataset)
x = data.x.to(device)
y_true = data.y.to(device)
edge_index = data.edge_index.to(device)
edge_index = to_undirected(edge_index, data.num_nodes)
if args.self_loop:
edge_index = add_self_loops(edge_index, num_nodes=data.num_nodes)[0]
args.in_channels = data.x.size(-1)
args.num_tasks = dataset.num_classes
print(args)
model = DeeperGCN(args)
model.load_state_dict(torch.load(args.model_load_path)['model_state_dict'])
model.to(device)
result = test(model, x, edge_index, y_true, split_idx, evaluator)
train_accuracy, valid_accuracy, test_accuracy = result
print({
'Train': train_accuracy,
'Validation': valid_accuracy,
'Test': test_accuracy
})
model.print_params(final=True)
def load_ogb_graph(dataset_name):
if not os.path.isfile('torch_geometric_data/dgl_' + dataset_name):
dataset = PygNodePropPredDataset(name="ogbn-" + dataset_name,
root='torch_geometric_data/')
split_idx = dataset.get_idx_split()
train_idx, valid_idx, test_idx = split_idx["train"], split_idx[
"valid"], split_idx["test"]
edge = dataset[0].edge_index
num_classes = len(np.unique(dataset[0].y))
print("Nodes: %d, edges: %d, features: %d, classes: %d. \n" %
(dataset[0].y.shape[0], len(edge[0]) / 2, len(
dataset[0].x[0]), num_classes))
graph = dgl.DGLGraph((edge[0], edge[1]))
graph.ndata['features'] = dataset[0].x
graph.ndata['labels'] = dataset[0].y
dgl.data.utils.save_graphs('torch_geometric_data/dgl_' + dataset_name,
graph)
torch.save(
train_idx, 'torch_geometric_data/ogbn_' + dataset_name +
'/train_' + dataset_name + '.pt')
torch.save(
valid_idx, 'torch_geometric_data/ogbn_' + dataset_name +
'/valid_' + dataset_name + '.pt')
torch.save(
test_idx, 'torch_geometric_data/ogbn_' + dataset_name + '/test_' +
dataset_name + '.pt')
labels = graph.ndata.pop('labels')
features = graph.ndata.pop('features')
features = torch.hstack([features, torch.ones([features.shape[0], 1])])
#print(features)
elif os.path.isfile('torch_geometric_data/dgl_' + dataset_name):
graph = dgl.data.utils.load_graphs('torch_geometric_data/dgl_' +
dataset_name)[0][0]
labels = graph.ndata.pop('labels')
features = graph.ndata.pop('features')
features = torch.hstack([features, torch.ones([features.shape[0], 1])])
train_idx = torch.load('torch_geometric_data/ogbn_' + dataset_name +
'/train_' + dataset_name + '.pt')
valid_idx = torch.load('torch_geometric_data/ogbn_' + dataset_name +
'/valid_' + dataset_name + '.pt')
test_idx = torch.load('torch_geometric_data/ogbn_' + dataset_name +
'/test_' + dataset_name + '.pt')
num_classes = len(torch.unique(labels))
return graph, features, labels, num_classes, train_idx, valid_idx, test_idx
def __init__(self, path):
dataset = "ogbn-papers100M"
# path = osp.join(osp.dirname(osp.realpath(__file__)), "../..", "data", dataset)
PygNodePropPredDataset(name=dataset,
root=path,
transform=T.ToSparseTensor())
super(OGBNpapers100MDataset,
self).__init__(dataset, path, transform=T.ToSparseTensor())
setattr(OGBNpapers100MDataset, "metric", "Accuracy")
setattr(OGBNpapers100MDataset, "loss", "nll_loss")
def __init__(self, path):
dataset = "ogbn-proteins"
# path = osp.join(osp.dirname(osp.realpath(__file__)), "../..", "data", dataset)
PygNodePropPredDataset(name=dataset,
root=path,
transform=T.ToSparseTensor())
super(OGBNproteinsDataset, self).__init__(dataset,
path,
transform=T.ToSparseTensor())
setattr(OGBNproteinsDataset, "metric", "ROC-AUC")
setattr(OGBNproteinsDataset, "loss", "BCEWithLogitsLoss")
def __init__(self):
dataset = "ogbn-arxiv"
path = osp.join(osp.dirname(osp.realpath(__file__)), "../..", "data")
if not osp.exists(path):
PygNodePropPredDataset(dataset, path)
super(OGBArxivDataset, self).__init__(path, dataset)
#to_symmetric
rev_edge_index = self.data.edge_index[[1, 0]]
edge_index = torch.cat([self.data.edge_index, rev_edge_index], dim = 1).to(dtype=torch.int64)
self.data.edge_index, self.data.edge_attr = coalesce(edge_index, None, self.data.num_nodes, self.data.num_nodes)