def __init__(self):
d_name = "ogbl-ppa"
dataset = LinkPropPredDataset(name=d_name)
splitted_edge = dataset.get_edge_split()
graph = dataset[0]
self.num_nodes = graph["num_nodes"]
self.ogb_evaluator = Evaluator(name="ogbl-ppa")
def __init__(self, path: str):
ogbl_dataset = LinkPropPredDataset("ogbl-citation2", path)
edge_split = ogbl_dataset.get_edge_split()
super(OGBLCitation2Dataset, self).__init__([
_OGBLDatasetUtil.ogbl_data_to_general_static_graph(
ogbl_dataset[0], {
('', '', ''):
torch.from_numpy(ogbl_dataset[0]['edge_index']),
('', 'train_pos_edge', ''):
torch.from_numpy(edge_split['train']['edge']),
('', 'val_pos_edge', ''):
torch.from_numpy(edge_split['valid']['edge']),
('', 'val_neg_edge', ''):
torch.from_numpy(edge_split['valid']['edge_neg']),
('', 'test_pos_edge', ''):
torch.from_numpy(edge_split['test']['edge']),
('', 'test_neg_edge', ''):
torch.from_numpy(edge_split['test']['edge_neg'])
}, ({
'node_feat': 'feat',
'node_year': 'year'
} if _backend.DependentBackend.is_dgl() else {
'node_feat': 'x',
'node_year': 'year'
}))
])
def __init__(self,
graph_wrapper=None,
buf_size=1000,
batch_size=128,
num_workers=1,
shuffle=True,
phase="train"):
super(PPADataGenerator, self).__init__(buf_size=buf_size,
num_workers=num_workers,
batch_size=batch_size,
shuffle=shuffle)
self.d_name = "ogbl-ppa"
self.graph_wrapper = graph_wrapper
dataset = LinkPropPredDataset(name=self.d_name)
splitted_edge = dataset.get_edge_split()
self.phase = phase
graph = dataset[0]
edges = graph["edge_index"].T
#self.graph = pgl.graph.Graph(num_nodes=graph["num_nodes"],
# edges=edges,
# node_feat={"nfeat": graph["node_feat"],
# "node_id": np.arange(0, graph["num_nodes"], dtype="int64").reshape(-1, 1) })
#self.graph.indegree()
self.num_nodes = graph["num_nodes"]
if self.phase == 'train':
edges = splitted_edge["train"]["edge"]
labels = np.ones(len(edges))
elif self.phase == "valid":
# Compute the embedding for all the nodes
pos_edges = splitted_edge["valid"]["edge"]
neg_edges = splitted_edge["valid"]["edge_neg"]
pos_labels = np.ones(len(pos_edges))
neg_labels = np.zeros(len(neg_edges))
edges = np.vstack([pos_edges, neg_edges])
labels = pos_labels.tolist() + neg_labels.tolist()
elif self.phase == "test":
# Compute the embedding for all the nodes
pos_edges = splitted_edge["test"]["edge"]
neg_edges = splitted_edge["test"]["edge_neg"]
pos_labels = np.ones(len(pos_edges))
neg_labels = np.zeros(len(neg_edges))
edges = np.vstack([pos_edges, neg_edges])
labels = pos_labels.tolist() + neg_labels.tolist()
self.line_examples = []
Example = namedtuple('Example', ['src', "dst", "label"])
for edge, label in zip(edges, labels):
self.line_examples.append(
Example(src=edge[0], dst=edge[1], label=label))
print("Phase", self.phase)
print("Len Examples", len(self.line_examples))
def _load(self) -> None:
try:
from ogb.linkproppred import LinkPropPredDataset
except ImportError as e:
raise ModuleNotFoundError(
f'Need to `pip install ogb` to use pykeen.datasets.{self.__class__.__name__}.',
) from e
dataset = LinkPropPredDataset(name=self.name, root=self.cache_root)
edge_split = dataset.get_edge_split()
self._training = self._make_tf(edge_split["train"])
self._testing = self._make_tf(
edge_split["test"],
entity_to_id=self._training.entity_to_id,
relation_to_id=self._training.relation_to_id,
)
self._validation = self._make_tf(
edge_split["valid"],
entity_to_id=self._training.entity_to_id,
relation_to_id=self._training.relation_to_id,
)
def __init__(self, path: str):
ogbl_dataset = LinkPropPredDataset("ogbl-ddi", path)
edge_split = ogbl_dataset.get_edge_split()
super(OGBLDDIDataset, self).__init__([
GeneralStaticGraphGenerator.create_heterogeneous_static_graph(
{'': {
'_NID': torch.arange(ogbl_dataset[0]['num_nodes'])
}}, {
('', '', ''):
torch.from_numpy(ogbl_dataset[0]['edge_index']),
('', 'train_pos_edge', ''):
torch.from_numpy(edge_split['train']['edge']),
('', 'val_pos_edge', ''):
torch.from_numpy(edge_split['valid']['edge']),
('', 'val_neg_edge', ''):
torch.from_numpy(edge_split['valid']['edge_neg']),
('', 'test_pos_edge', ''):
torch.from_numpy(edge_split['test']['edge']),
('', 'test_neg_edge', ''):
torch.from_numpy(edge_split['test']['edge_neg'])
})
])
def main(_):
ds = LinkPropPredDataset(FLAGS.dataset)
split_edge = ds.get_edge_split()
train_edges = split_edge['train']['edge']
train_edges = np.concatenate([train_edges, train_edges[:, ::-1]], axis=0)
spa = scipy.sparse.csr_matrix(
(np.ones([len(train_edges)]), (train_edges[:, 0], train_edges[:, 1])))
mult_f = tf_fsvd.WYSDeepWalkPF(spa,
window=FLAGS.wys_window,
mult_degrees=False,
neg_sample_coef=FLAGS.wys_neg_coef)
tt = tqdm.tqdm(range(FLAGS.num_runs))
test_metrics = []
val_metrics = []
for run in tt:
u, s, v = tf_fsvd.fsvd(mult_f,
FLAGS.k,
n_iter=FLAGS.svd_iters,
n_redundancy=FLAGS.k * 3)
dataset = LinkPropPredDataset(FLAGS.dataset)
evaluator = Evaluator(name=FLAGS.dataset)
evaluator.K = FLAGS.hits
split_edge = dataset.get_edge_split()
metrics = []
for split in ('test', 'valid'):
pos_edges = split_edge[split]['edge']
neg_edges = split_edge[split]['edge_neg']
pos_scores = tf.reduce_sum(tf.gather(u * s, pos_edges[:, 0]) *
tf.gather(v, pos_edges[:, 1]),
axis=1).numpy()
neg_scores = tf.reduce_sum(tf.gather(u * s, neg_edges[:, 0]) *
tf.gather(v, neg_edges[:, 1]),
axis=1).numpy()
metric = evaluator.eval({
'y_pred_pos': pos_scores,
'y_pred_neg': neg_scores
})
metrics.append(metric['hits@%i' % FLAGS.hits])
test_metrics.append(metrics[0])
val_metrics.append(metrics[1])
tt.set_description(
'HITS@%i: validate=%g; test=%g' %
(FLAGS.hits, np.mean(val_metrics), np.mean(test_metrics)))
print('\n\n *** Trained for %i times and average metrics are:')
print('HITS@20 test: mean=%g; std=%g' %
(np.mean(test_metrics), np.std(test_metrics)))
print('HITS@20 validate: mean=%g; std=%g' %
(np.mean(val_metrics), np.std(val_metrics)))
def _add_eig(self, norm='none', number=6):
dataset = LinkPropPredDataset(name='ogbl-collab')
graph = dataset[0]
G = nx.Graph()
G.add_nodes_from([i for i in range(235868)])
for nod1, nod2 in zip(graph['edge_index'][0], graph['edge_index'][1]):
G.add_edge(nod1, nod2)
components = list(nx.connected_components(G))
list_G = []
list_nodes = []
for component in components:
G_new = nx.Graph()
G_new.add_nodes_from(list(component))
list_G.append(G_new)
list_nodes.append(list(component))
for i in range(len(list_G)):
for nod1, nod2 in list(G.edges(list_nodes[i])):
list_G[i].add_edge(nod1, nod2)
EigVec_global = np.ones((235868, number))
for g in list_G:
node_list = list(g.nodes)
A = nx.adjacency_matrix(g, nodelist=node_list).astype(float)
if norm == 'none':
D = sp.diags(list(map(lambda x: x[1], g.degree())))
L = D - A
elif norm == 'sym':
D_norm = sp.diags(list(map(lambda x: x[1]**(-0.5), g.degree())))
D = sp.diags(list(map(lambda x: x[1], g.degree())))
L = D_norm * (D - A) * D_norm
elif norm == 'walk':
D_norm = sp.diags(list(map(lambda x: x[1]**(-1), g.degree())))
D = sp.diags(list(map(lambda x: x[1], g.degree())))
L = D_norm * (D - A)
if len(node_list) > 2:
EigVal, EigVec = sp.linalg.eigs(L, k=min(len(node_list) - 2, number), which='SR', tol=0)
EigVec = EigVec[:, EigVal.argsort()] / np.max(EigVec[:, EigVal.argsort()], 0)
EigVec_global[node_list, : min(len(node_list) - 2, number)] = EigVec[:, :]
elif len(node_list) == 2:
EigVec_global[node_list[0], :number] = np.zeros((1, number))
self.graph.ndata['eig'] = torch.from_numpy(EigVec_global).float()
print(sorted(self.graph.ndata['eig'][1]))
def main(args):
if (not args.do_train) and (not args.do_valid) and (not args.do_test) and (
not args.evaluate_train):
raise ValueError('one of train/val/test mode must be choosed.')
if args.init_checkpoint:
override_config(args)
args.save_path = 'log/%s/%s/%s-%s/%s' % (
args.dataset, args.model, args.hidden_dim, args.gamma,
time.time()) if args.save_path == None else args.save_path
writer = SummaryWriter(args.save_path)
# Write logs to checkpoint and console
set_logger(args)
dataset = LinkPropPredDataset(name='ogbl-biokg')
split_edge = dataset.get_edge_split()
train_triples, valid_triples, test_triples = split_edge[
"train"], split_edge["valid"], split_edge["test"]
nrelation = int(max(train_triples['relation'])) + 1
entity_dict = dict()
cur_idx = 0
for key in dataset[0]['num_nodes_dict']:
entity_dict[key] = (cur_idx,
cur_idx + dataset[0]['num_nodes_dict'][key])
cur_idx += dataset[0]['num_nodes_dict'][key]
nentity = sum(dataset[0]['num_nodes_dict'].values())
evaluator = Evaluator(name=args.dataset)
args.nentity = nentity
args.nrelation = nrelation
logging.info('Model: %s' % args.model)
logging.info('Dataset: %s' % args.dataset)
logging.info('#entity: %d' % nentity)
logging.info('#relation: %d' % nrelation)
# train_triples = split_dict['train']
logging.info('#train: %d' % len(train_triples['head']))
# valid_triples = split_dict['valid']
logging.info('#valid: %d' % len(valid_triples['head']))
# test_triples = split_dict['test']
logging.info('#test: %d' % len(test_triples['head']))
train_count, train_true_head, train_true_tail = defaultdict(
lambda: 4), defaultdict(list), defaultdict(list)
for i in tqdm(range(len(train_triples['head']))):
head, relation, tail = train_triples['head'][i], train_triples[
'relation'][i], train_triples['tail'][i]
head_type, tail_type = train_triples['head_type'][i], train_triples[
'tail_type'][i]
train_count[(head, relation, head_type)] += 1
train_count[(tail, -relation - 1, tail_type)] += 1
train_true_head[(relation, tail)].append(head)
train_true_tail[(head, relation)].append(tail)
kge_model = KGEModel(
model_name=args.model,
nentity=nentity,
nrelation=nrelation,
hidden_dim=args.hidden_dim,
gamma=args.gamma,
double_entity_embedding=args.double_entity_embedding,
double_relation_embedding=args.double_relation_embedding,
evaluator=evaluator)
logging.info('Model Parameter Configuration:')
for name, param in kge_model.named_parameters():
logging.info('Parameter %s: %s, require_grad = %s' %
(name, str(param.size()), str(param.requires_grad)))
if args.cuda:
kge_model = kge_model.cuda()
if args.init_checkpoint:
# Restore model from checkpoint directory
logging.info('Loading checkpoint %s...' % args.init_checkpoint)
checkpoint = torch.load(
os.path.join(args.init_checkpoint, 'checkpoint'))
entity_dict = checkpoint['entity_dict']
if args.do_train:
# Set training dataloader iterator
train_dataloader_head = DataLoader(
TrainDataset(train_triples, nentity, nrelation,
args.negative_sample_size, 'head-batch', train_count,
train_true_head, train_true_tail, entity_dict),
batch_size=args.batch_size,
shuffle=True,
num_workers=max(1, args.cpu_num // 2),
collate_fn=TrainDataset.collate_fn)
train_dataloader_tail = DataLoader(
TrainDataset(train_triples, nentity, nrelation,
args.negative_sample_size, 'tail-batch', train_count,
train_true_head, train_true_tail, entity_dict),
batch_size=args.batch_size,
shuffle=True,
num_workers=max(1, args.cpu_num // 2),
collate_fn=TrainDataset.collate_fn)
train_iterator = BidirectionalOneShotIterator(train_dataloader_head,
train_dataloader_tail)
# Set training configuration
current_learning_rate = args.learning_rate
optimizer = torch.optim.Adam(filter(lambda p: p.requires_grad,
kge_model.parameters()),
lr=current_learning_rate)
if args.warm_up_steps:
warm_up_steps = args.warm_up_steps
else:
warm_up_steps = args.max_steps // 2
if args.init_checkpoint:
# Restore model from checkpoint directory
# logging.info('Loading checkpoint %s...' % args.init_checkpoint)
# checkpoint = torch.load(os.path.join(args.init_checkpoint, 'checkpoint'))
init_step = checkpoint['step']
kge_model.load_state_dict(checkpoint['model_state_dict'])
# entity_dict = checkpoint['entity_dict']
if args.do_train:
current_learning_rate = checkpoint['current_learning_rate']
warm_up_steps = checkpoint['warm_up_steps']
optimizer.load_state_dict(checkpoint['optimizer_state_dict'])
else:
logging.info('Ramdomly Initializing %s Model...' % args.model)
init_step = 0
step = init_step
logging.info('Start Training...')
logging.info('init_step = %d' % init_step)
logging.info('batch_size = %d' % args.batch_size)
logging.info('negative_adversarial_sampling = %d' %
args.negative_adversarial_sampling)
logging.info('hidden_dim = %d' % args.hidden_dim)
logging.info('gamma = %f' % args.gamma)
logging.info('negative_adversarial_sampling = %s' %
str(args.negative_adversarial_sampling))
if args.negative_adversarial_sampling:
logging.info('adversarial_temperature = %f' %
args.adversarial_temperature)
# Set valid dataloader as it would be evaluated during training
if args.do_train:
logging.info('learning_rate = %d' % current_learning_rate)
training_logs = []
#Training Loop
for step in range(init_step, args.max_steps):
log = kge_model.train_step(kge_model, optimizer, train_iterator,
args)
training_logs.append(log)
if step >= warm_up_steps:
current_learning_rate = current_learning_rate / 10
logging.info('Change learning_rate to %f at step %d' %
(current_learning_rate, step))
optimizer = torch.optim.Adam(filter(lambda p: p.requires_grad,
kge_model.parameters()),
lr=current_learning_rate)
warm_up_steps = warm_up_steps * 3
if step % args.save_checkpoint_steps == 0 and step > 0: # ~ 41 seconds/saving
save_variable_list = {
'step': step,
'current_learning_rate': current_learning_rate,
'warm_up_steps': warm_up_steps,
'entity_dict': entity_dict
}
save_model(kge_model, optimizer, save_variable_list, args)
if step % args.log_steps == 0:
metrics = {}
for metric in training_logs[0].keys():
metrics[metric] = sum(
[log[metric]
for log in training_logs]) / len(training_logs)
log_metrics('Train', step, metrics, writer)
training_logs = []
if args.do_valid and step % args.valid_steps == 0 and step > 0:
logging.info('Evaluating on Valid Dataset...')
metrics = kge_model.test_step(kge_model, valid_triples, args,
entity_dict)
log_metrics('Valid', step, metrics, writer)
save_variable_list = {
'step': step,
'current_learning_rate': current_learning_rate,
'warm_up_steps': warm_up_steps
}
save_model(kge_model, optimizer, save_variable_list, args)
if args.do_valid:
logging.info('Evaluating on Valid Dataset...')
metrics = kge_model.test_step(kge_model, valid_triples, args,
entity_dict)
log_metrics('Valid', step, metrics, writer)
if args.do_test:
logging.info('Evaluating on Test Dataset...')
metrics = kge_model.test_step(kge_model, test_triples, args,
entity_dict)
log_metrics('Test', step, metrics, writer)
if args.evaluate_train:
logging.info('Evaluating on Training Dataset...')
small_train_triples = {}
indices = np.random.choice(len(train_triples['head']),
args.ntriples_eval_train,
replace=False)
for i in train_triples:
if 'type' in i:
small_train_triples[i] = [train_triples[i][x] for x in indices]
else:
small_train_triples[i] = train_triples[i][indices]
metrics = kge_model.test_step(kge_model,
small_train_triples,
args,
entity_dict,
random_sampling=True)
log_metrics('Train', step, metrics, writer)
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# =============================================================================
"""ogbl_collab dataset.
"""
import os
import numpy as np
from ogb.linkproppred import LinkPropPredDataset
# load data
dataset = LinkPropPredDataset(name='ogbl-collab')
split_edge = dataset.get_edge_split()
train_edge, valid_edge, test_edge = split_edge['train'], split_edge[
'valid'], split_edge['test']
# train_edge['edge'], (1179052, 2)
# train_edge['weight'], (1179052,)
# train_edge['year'], (1179052,)
# valid_edge, 60084
# test_edge, 46329
graph = dataset[0]
num_nodes = graph['num_nodes'] # 235868
node_feat = graph['node_feat'] # shape(235868, 128)
# dump to disk
root = 'ogbl_collab/'
from collections import defaultdict
import time
import pdb
import datetime
def now():
d = datetime.datetime.now()
x = d - datetime.timedelta(microseconds=d.microsecond)
return x
d_name = "ogbl-biokg"
dataset = LinkPropPredDataset(name=d_name)
split_edge = dataset.get_edge_split()
train_triples, valid_triples, test_triples = split_edge["train"], split_edge[
"valid"], split_edge["test"]
nrelation = int(max(train_triples['relation'])) + 1 #4
nentity = sum(dataset[0]['num_nodes_dict'].values())
entity_dict = dict()
cur_idx = 0
for key in dataset[0][
'num_nodes_dict']: #['drug', 'sideeffect', 'protein', 'disease', 'function']:
entity_dict[key] = (cur_idx, cur_idx + dataset[0]['num_nodes_dict'][key])
cur_idx += dataset[0]['num_nodes_dict'][key]
nentity = sum(
def main(args):
if (
(not args.do_train)
and (not args.do_valid)
and (not args.do_test)
and (not args.evaluate_train)
):
raise ValueError("one of train/val/test mode must be choosed.")
if args.init_checkpoint:
override_config(args)
args.save_path = (
"log/%s/%s/%s-%s/%s"
% (args.dataset, args.model, args.hidden_dim, args.gamma, time.time())
if args.save_path == None
else args.save_path
)
writer = SummaryWriter(args.save_path)
# Write logs to checkpoint and console
set_logger(args)
dataset = LinkPropPredDataset(name=args.dataset)
split_dict = dataset.get_edge_split()
nentity = dataset.graph["num_nodes"]
nrelation = int(max(dataset.graph["edge_reltype"])[0]) + 1
evaluator = Evaluator(name=args.dataset)
args.nentity = nentity
args.nrelation = nrelation
logging.info("Model: %s" % args.model)
logging.info("Dataset: %s" % args.dataset)
logging.info("#entity: %d" % nentity)
logging.info("#relation: %d" % nrelation)
train_triples = split_dict["train"]
logging.info("#train: %d" % len(train_triples["head"]))
valid_triples = split_dict["valid"]
logging.info("#valid: %d" % len(valid_triples["head"]))
test_triples = split_dict["test"]
logging.info("#test: %d" % len(test_triples["head"]))
train_count, train_true_head, train_true_tail = (
defaultdict(lambda: 4),
defaultdict(list),
defaultdict(list),
)
for i in tqdm(range(len(train_triples["head"]))):
head, relation, tail = (
train_triples["head"][i],
train_triples["relation"][i],
train_triples["tail"][i],
)
train_count[(head, relation)] += 1
train_count[(tail, -relation - 1)] += 1
train_true_head[(relation, tail)].append(head)
train_true_tail[(head, relation)].append(tail)
kge_model = KGEModel(
model_name=args.model,
nentity=nentity,
nrelation=nrelation,
hidden_dim=args.hidden_dim,
gamma=args.gamma,
double_entity_embedding=args.double_entity_embedding,
double_relation_embedding=args.double_relation_embedding,
evaluator=evaluator,
)
logging.info("Model Parameter Configuration:")
for name, param in kge_model.named_parameters():
logging.info(
"Parameter %s: %s, require_grad = %s"
% (name, str(param.size()), str(param.requires_grad))
)
if args.cuda:
kge_model = kge_model.cuda()
if args.do_train:
# Set training dataloader iterator
train_dataloader_head = DataLoader(
TrainDataset(
train_triples,
nentity,
nrelation,
args.negative_sample_size,
"head-batch",
train_count,
train_true_head,
train_true_tail,
),
batch_size=args.batch_size,
shuffle=True,
num_workers=max(1, args.cpu_num // 2),
collate_fn=TrainDataset.collate_fn,
)
train_dataloader_tail = DataLoader(
TrainDataset(
train_triples,
nentity,
nrelation,
args.negative_sample_size,
"tail-batch",
train_count,
train_true_head,
train_true_tail,
),
batch_size=args.batch_size,
shuffle=True,
num_workers=max(1, args.cpu_num // 2),
collate_fn=TrainDataset.collate_fn,
)
train_iterator = BidirectionalOneShotIterator(
train_dataloader_head, train_dataloader_tail
)
# Set training configuration
current_learning_rate = args.learning_rate
optimizer = torch.optim.Adam(
filter(lambda p: p.requires_grad, kge_model.parameters()),
lr=current_learning_rate,
)
if args.warm_up_steps:
warm_up_steps = args.warm_up_steps
else:
warm_up_steps = args.max_steps // 2
if args.init_checkpoint:
# Restore model from checkpoint directory
logging.info("Loading checkpoint %s..." % args.init_checkpoint)
checkpoint = torch.load(os.path.join(args.init_checkpoint, "checkpoint"))
init_step = checkpoint["step"]
kge_model.load_state_dict(checkpoint["model_state_dict"])
if args.do_train:
current_learning_rate = checkpoint["current_learning_rate"]
warm_up_steps = checkpoint["warm_up_steps"]
optimizer.load_state_dict(checkpoint["optimizer_state_dict"])
else:
logging.info("Ramdomly Initializing %s Model..." % args.model)
init_step = 0
step = init_step
logging.info("Start Training...")
logging.info("init_step = %d" % init_step)
logging.info("batch_size = %d" % args.batch_size)
logging.info(
"negative_adversarial_sampling = %d" % args.negative_adversarial_sampling
)
logging.info("hidden_dim = %d" % args.hidden_dim)
logging.info("gamma = %f" % args.gamma)
logging.info(
"negative_adversarial_sampling = %s" % str(args.negative_adversarial_sampling)
)
if args.negative_adversarial_sampling:
logging.info("adversarial_temperature = %f" % args.adversarial_temperature)
# Set valid dataloader as it would be evaluated during training
if args.do_train:
logging.info("learning_rate = %d" % current_learning_rate)
training_logs = []
# Training Loop
for step in range(init_step, args.max_steps):
log = kge_model.train_step(kge_model, optimizer, train_iterator, args)
training_logs.append(log)
if step >= warm_up_steps:
current_learning_rate = current_learning_rate / 10
logging.info(
"Change learning_rate to %f at step %d"
% (current_learning_rate, step)
)
optimizer = torch.optim.Adam(
filter(lambda p: p.requires_grad, kge_model.parameters()),
lr=current_learning_rate,
)
warm_up_steps = warm_up_steps * 3
if (
step % args.save_checkpoint_steps == 0 and step > 0
): # ~ 41 seconds/saving
save_variable_list = {
"step": step,
"current_learning_rate": current_learning_rate,
"warm_up_steps": warm_up_steps,
}
save_model(kge_model, optimizer, save_variable_list, args)
if step % args.log_steps == 0:
metrics = {}
for metric in training_logs[0].keys():
metrics[metric] = sum([log[metric] for log in training_logs]) / len(
training_logs
)
log_metrics("Train", step, metrics, writer)
training_logs = []
if args.do_valid and step % args.valid_steps == 0 and step > 0:
logging.info("Evaluating on Valid Dataset...")
metrics = kge_model.test_step(kge_model, valid_triples, args)
log_metrics("Valid", step, metrics, writer)
save_variable_list = {
"step": step,
"current_learning_rate": current_learning_rate,
"warm_up_steps": warm_up_steps,
}
save_model(kge_model, optimizer, save_variable_list, args)
if args.do_valid:
logging.info("Evaluating on Valid Dataset...")
metrics = kge_model.test_step(kge_model, valid_triples, args)
log_metrics("Valid", step, metrics, writer)
if args.do_test:
logging.info("Evaluating on Test Dataset...")
metrics = kge_model.test_step(kge_model, test_triples, args)
log_metrics("Test", step, metrics, writer)
if args.evaluate_train:
logging.info("Evaluating on Training Dataset...")
small_train_triples = {}
indices = np.random.choice(
len(train_triples["head"]), args.ntriples_eval_train, replace=False
)
for i in train_triples:
small_train_triples[i] = train_triples[i][indices]
metrics = kge_model.test_step(
kge_model, small_train_triples, args, random_sampling=True
)
log_metrics("Train", step, metrics, writer)
def main():
parser = argparse.ArgumentParser(description='OGBL-DDI (MADGraph)')
parser.add_argument('--lr', type=float, default=0.005)
parser.add_argument('--epochs', type=int, default=200)
parser.add_argument('--eval_steps', type=int, default=5)
parser.add_argument('--runs', type=int, default=10)
parser.add_argument('--batch_size', type=int, default=4 * 1024)
parser.add_argument('--dim', type=int, default=12)
parser.add_argument('--heads', type=int, default=12)
parser.add_argument('--samples', type=int, default=8)
parser.add_argument('--nearest', type=int, default=8)
parser.add_argument('--seed', type=int, default=0)
parser.add_argument('--sentinels', type=int, default=8)
parser.add_argument('--memory', type=str, default='all')
parser.add_argument('--softmin', type=bool, default=True)
parser.add_argument('--output_csv', type=str, default='')
args = parser.parse_args()
print(args)
DNAME = 'ogbl-ddi'
dataset = LinkPropPredDataset(name=DNAME)
graph = dataset[0]
n_nodes = graph['num_nodes']
data = dataset.get_edge_split()
for group in 'train valid test'.split():
if group in data:
sets = data[group]
for key in ('edge', 'edge_neg'):
if key in sets:
sets[key] = gpu(torch.from_numpy(sets[key]))
data['eval_train'] = {
'edge':
data['train']['edge'][torch.randperm(
data['train']['edge'].shape[0])[:data['valid']['edge'].shape[0]]]
}
model = MADGraph(
n_nodes=n_nodes,
node_feats=args.dim,
src=data['train']['edge'][:, 0],
dst=data['train']['edge'][:, 1],
n_samples=args.samples,
n_heads=args.heads,
n_sentinels=args.sentinels,
memory=['none', 'stat', 'all'].index(args.memory),
softmin=args.softmin,
n_nearest=args.nearest,
)
params = [p for net in [model] for p in net.parameters()]
print('params:', sum(p.numel() for p in params))
evaluator = Evaluator(name=DNAME)
loggers = {
'Hits@10': Logger(args.runs, args),
'Hits@20': Logger(args.runs, args),
'Hits@30': Logger(args.runs, args),
}
for run in range(args.runs):
torch.manual_seed(args.seed + run)
opt = optim.Adam(params, lr=args.lr)
torch.nn.init.xavier_uniform_(model.pos.data)
torch.nn.init.xavier_uniform_(model.field.data)
model.uncertainty.data = model.uncertainty.data * 0 + 1
for epoch in range(1, args.epochs + 1):
model.train()
for chunk in sample(data['train']['edge'], args.batch_size):
opt.zero_grad()
p_edge = torch.sigmoid(model(chunk))
edge_neg_chunk = gpu(torch.randint(0, n_nodes, chunk.shape))
p_edge_neg = torch.sigmoid(model(edge_neg_chunk))
loss = (-torch.log(1e-5 + 1 - p_edge_neg).mean() -
torch.log(1e-5 + p_edge).mean())
loss.backward()
opt.step()
if epoch % args.eval_steps:
continue
with torch.no_grad():
model.eval()
p_train = torch.cat([
model(chunk) for chunk in sample(
data['eval_train']['edge'], args.batch_size)
])
n_train = torch.cat([
model(chunk) for chunk in sample(data['valid']['edge_neg'],
args.batch_size)
])
p_valid = torch.cat([
model(chunk)
for chunk in sample(data['valid']['edge'], args.batch_size)
])
n_valid = n_train
p_test = torch.cat([
model(chunk)
for chunk in sample(data['test']['edge'], args.batch_size)
])
n_test = torch.cat([
model(chunk) for chunk in sample(data['test']['edge_neg'],
args.batch_size)
])
for K in [10, 20, 30]:
evaluator.K = K
key = f'Hits@{K}'
h_train = evaluator.eval({
'y_pred_pos': p_train,
'y_pred_neg': n_train,
})[f'hits@{K}']
h_valid = evaluator.eval({
'y_pred_pos': p_valid,
'y_pred_neg': n_valid,
})[f'hits@{K}']
h_test = evaluator.eval({
'y_pred_pos': p_test,
'y_pred_neg': n_test,
})[f'hits@{K}']
loggers[key].add_result(run, (h_train, h_valid, h_test))
print(key)
print(f'Run: {run + 1:02d}, '
f'Epoch: {epoch:02d}, '
f'Loss: {loss:.4f}, '
f'Train: {100 * h_train:.2f}%, '
f'Valid: {100 * h_valid:.2f}%, '
f'Test: {100 * h_test:.2f}%')
print('---')
for key in loggers.keys():
print(key)
loggers[key].print_statistics(run)
for key in loggers.keys():
print(key)
loggers[key].print_statistics()
def test_datasetsaver():
# test on graph classification
# ogbg-molhiv
test_task = 'link'
# testing all the dataset objects are working.
if test_task == 'graph':
from ogb.graphproppred import PygGraphPropPredDataset, DglGraphPropPredDataset, GraphPropPredDataset
dataset_name = 'ogbg-molhiv'
dataset = PygGraphPropPredDataset(dataset_name)
dataset.get_idx_split()
dataset = DglGraphPropPredDataset(dataset_name)
dataset.get_idx_split()
dataset = GraphPropPredDataset(dataset_name)
dataset.get_idx_split()
elif test_task == 'node':
from ogb.nodeproppred import NodePropPredDataset, PygNodePropPredDataset, DglNodePropPredDataset
dataset_name = 'ogbn-arxiv' # test ogbn-proteins
dataset = PygNodePropPredDataset(dataset_name)
dataset.get_idx_split()
dataset = DglNodePropPredDataset(dataset_name)
dataset.get_idx_split()
dataset = NodePropPredDataset(dataset_name)
dataset.get_idx_split()
elif test_task == 'link':
from ogb.linkproppred import LinkPropPredDataset, PygLinkPropPredDataset, DglLinkPropPredDataset
dataset_name = 'ogbl-collab'
dataset = PygLinkPropPredDataset(dataset_name)
dataset.get_edge_split()
dataset = DglLinkPropPredDataset(dataset_name)
dataset.get_edge_split()
dataset = LinkPropPredDataset(dataset_name)
dataset.get_edge_split()
elif test_task == 'heteronode':
from ogb.nodeproppred import NodePropPredDataset, PygNodePropPredDataset, DglNodePropPredDataset
dataset_name = 'ogbn-mag'
dataset = PygNodePropPredDataset(dataset_name)
dataset.get_idx_split()
dataset = DglNodePropPredDataset(dataset_name)
dataset.get_idx_split()
dataset = NodePropPredDataset(dataset_name)
dataset.get_idx_split()
elif test_task == 'heterolink':
from ogb.linkproppred import LinkPropPredDataset, PygLinkPropPredDataset, DglLinkPropPredDataset
dataset_name = 'ogbl-biokg'
dataset = PygLinkPropPredDataset(dataset_name)
dataset.get_edge_split()
dataset = DglLinkPropPredDataset(dataset_name)
dataset.get_edge_split()
dataset = LinkPropPredDataset(dataset_name)
dataset.get_edge_split()
else:
raise ValueError('Invalid task category')
print(dataset[0])
if 'link' in test_task:
print(dataset.get_edge_split())
else:
print(dataset.get_idx_split())
if 'graph' in test_task:
graph_list = dataset.graphs
else:
graph_list = [dataset.graph]
if 'link' not in test_task:
labels = dataset.labels
is_hetero = 'hetero' in test_task
version = 2 if dataset_name == 'ogbn-mag' else 1
saver = DatasetSaver(dataset_name, is_hetero, version=version)
# saving graph objects
saver.save_graph_list(graph_list)
# saving target labels
if 'link' not in test_task:
saver.save_target_labels(labels)
# saving split
if 'link' in test_task:
split_idx = dataset.get_edge_split()
else:
split_idx = dataset.get_idx_split()
# second argument must be the name of the split
saver.save_split(split_idx, dataset.meta_info['split'])
# copying mapping dir
# saver.copy_mapping_dir(f"dataset/{'_'.join(dataset_name.split('-'))}/mapping/")
saver.copy_mapping_dir("dataset/{}/mapping/".format('_'.join(
dataset_name.split('-'))))
saver.save_task_info(
dataset.task_type, dataset.eval_metric,
dataset.num_classes if hasattr(dataset, 'num_classes') else None)
meta_dict = saver.get_meta_dict()
print(meta_dict)
print('Now testing.')
if 'graph' in test_task:
print('library agnostic')
dataset = GraphPropPredDataset(dataset_name, meta_dict=meta_dict)
dataset = GraphPropPredDataset(dataset_name, meta_dict=meta_dict)
print(dataset[0])
print(dataset.get_idx_split())
print('Pytorch Geometric')
dataset = PygGraphPropPredDataset(dataset_name, meta_dict=meta_dict)
dataset = PygGraphPropPredDataset(dataset_name, meta_dict=meta_dict)
print(dataset[0])
print(dataset.get_idx_split())
print('DGL')
dataset = DglGraphPropPredDataset(dataset_name, meta_dict=meta_dict)
dataset = DglGraphPropPredDataset(dataset_name, meta_dict=meta_dict)
print(dataset[0])
print(dataset.get_idx_split())
elif 'node' in test_task:
print('library agnostic')
dataset = NodePropPredDataset(dataset_name, meta_dict=meta_dict)
dataset = NodePropPredDataset(dataset_name, meta_dict=meta_dict)
print(dataset[0])
print(dataset.get_idx_split())
print('Pytorch Geometric')
dataset = PygNodePropPredDataset(dataset_name, meta_dict=meta_dict)
dataset = PygNodePropPredDataset(dataset_name, meta_dict=meta_dict)
print(dataset[0])
print(dataset.get_idx_split())
print('DGL')
dataset = DglNodePropPredDataset(dataset_name, meta_dict=meta_dict)
dataset = DglNodePropPredDataset(dataset_name, meta_dict=meta_dict)
print(dataset[0])
print(dataset.get_idx_split())
elif 'link' in test_task:
print('library agnostic')
dataset = LinkPropPredDataset(dataset_name, meta_dict=meta_dict)
dataset = LinkPropPredDataset(dataset_name, meta_dict=meta_dict)
print(dataset[0])
# print(dataset.get_edge_split())
print('Pytorch Geometric')
dataset = PygLinkPropPredDataset(dataset_name, meta_dict=meta_dict)
dataset = PygLinkPropPredDataset(dataset_name, meta_dict=meta_dict)
print(dataset[0])
# print(dataset.get_edge_split())
print('DGL')
dataset = DglLinkPropPredDataset(dataset_name, meta_dict=meta_dict)
dataset = DglLinkPropPredDataset(dataset_name, meta_dict=meta_dict)
print(dataset[0])
# print(dataset.get_edge_split())
else:
raise ValueError('Invalid task category')
# zip
saver.zip()
print('Finished zipping!')
saver.cleanup()
def main():
parser = ArgumentParser(description="ne")
parser.add_argument("-d", "--dataset", type=str, default="cora", \
help="input dataset")
parser.add_argument("-o", "--coarse", type=str, default="simple", \
help="choose either simple_coarse or lamg_coarse, [simple, lamg]")
parser.add_argument("-c", "--mcr_dir", type=str, default="/opt/matlab/R2018A/", \
help="directory of matlab compiler runtime (only required by lamg_coarsen)")
parser.add_argument("-s", "--search_ratio", type=int, default=12, \
help="control the search space in graph fusion process (only required by lamg_coarsen)")
parser.add_argument("-r", "--reduce_ratio", type=int, default=2, \
help="control graph coarsening levels (only required by lamg_coarsen)")
parser.add_argument("-v", "--level", type=int, default=1, \
help="number of coarsening levels (only required by simple_coarsen)")
parser.add_argument("-n", "--num_neighs", type=int, default=2, \
help="control k-nearest neighbors in graph fusion process")
parser.add_argument("-l", "--lda", type=float, default=0.1, \
help="control self loop in adjacency matrix")
parser.add_argument("-e", "--embed_path", type=str, default="embed_results/embeddings_palone_deepwalk.npy", \
help="path of embedding result")
parser.add_argument("-m", "--embed_method", type=str, default="deepwalk", \
help="[deepwalk, node2vec, graphsage]")
parser.add_argument("-f", "--fusion", default=True, action="store_false", \
help="whether use graph fusion")
parser.add_argument("-p", "--power", default=False, action="store_true", \
help="Strong power of graph filter, set True to enhance filter power")
parser.add_argument("-g", "--sage_model", type=str, default="mean", \
help="aggregation function in graphsage")
parser.add_argument("-w", "--sage_weighted", default=True, action="store_false", \
help="whether consider weighted reduced graph")
args = parser.parse_args()
dataset = args.dataset
feature_path = "dataset/{}/{}-feats.npy".format(dataset, dataset)
fusion_input_path = "dataset/{}/{}.mtx".format(dataset, dataset)
reduce_results = "reduction_results/"
mapping_path = "{}Mapping.mtx".format(reduce_results)
if args.fusion:
coarsen_input_path = "dataset/{}/fused_{}.mtx".format(dataset, dataset)
else:
coarsen_input_path = "dataset/{}/{}.mtx".format(dataset, dataset)
######Load Data######
print("%%%%%% Loading Graph Data %%%%%%")
if args.dataset == "ogb":
d_name = "ogbl-ppa"
from ogb.linkproppred import LinkPropPredDataset
dataset = LinkPropPredDataset(name=d_name)
print(dataset)
print(dataset[0])
split_edge = dataset.get_edge_split()
print(split_edge)
# train_edge, valid_edge, test_edge = split_edge["train"], split_edge["valid"], split_edge["test"]
graph = dataset[0] # graph: library-agnostic graph object
print(graph['edge_index'].shape)
print(graph['edge_feat'])
print(graph['node_feat'])
# print((np.array(graph['node_feat']) == 0.0).all())
graph['directed'] = False
print(graph)
graph_nodes = [i for i in range(0, graph['num_nodes'])]
G = nx.Graph()
G.add_nodes_from(graph_nodes)
G.add_edges_from(graph['edge_index'].T)
# nx.draw(G, with_labels=True)
print(G.nodes)
# plt.show()
laplacian = laplacian_matrix(G)
print(laplacian)
else:
path = "dataset/ppi/ppi.mtx"
G = mtx2graph(path)
laplacian, edges = json2mtx(dataset)
## whether node features are required
if args.fusion or args.embed_method == "graphsage":
if args.dataset == 'ogb':
feature = graph['node_feat']
else:
feature = np.load(feature_path)
# print(feature[1][0])
######Embed Reduced Graph######
print("%%%%%% Starting Graph Embedding %%%%%%")
if args.embed_method == "deepwalk":
embed_start = time.process_time()
embeddings = deepwalk(G)
elif args.embed_method == "node2vec":
embed_start = time.process_time()
embeddings = node2vec(G)
elif args.embed_method == "graphsage":
from embed_methods.graphsage.graphsage import graphsage
nx.set_node_attributes(G, False, "test")
nx.set_node_attributes(G, False, "val")
## obtain mapping operator
if args.coarse == "lamg":
mapping = normalize(mtx2matrix(mapping_path), norm='l1', axis=1)
else:
mapping = identity(feature.shape[0])
for p in projections:
mapping = mapping @ p
mapping = normalize(mapping, norm='l1', axis=1).transpose()
## control iterations for training
coarse_ratio = mapping.shape[1] / mapping.shape[0]
## map node feats to the coarse graph
feats = mapping @ feature
embed_start = time.process_time()
embeddings = graphsage(G, feats, args.sage_model, args.sage_weighted,
int(1000 / coarse_ratio))
embed_time = time.process_time() - embed_start
######Save Embeddings######
np.save(args.embed_path, embeddings)
######Evaluation######
print("%%%%%% Starting Evaluation %%%%%%")
# link prediction
embeds = np.load(args.embed_path)
'''
if args.dataset == "ogb":
acc, pre, sen, mcc, auc = linkprediction_ogb(split_edge, embeds)
else:
acc, pre, sen, mcc, auc = linkprediction(edges, embeds, dataset)'''
print("Running regression..")
# node prediction
# run_regression(np.array(train_embeds), np.array(train_labels), np.array(test_embeds), np.array(test_labels))
# lr("dataset/{}/".format(dataset), args.embed_path, dataset)
######Report timing information######å
print("%%%%%% CPU time %%%%%%")
if args.fusion:
total_time = embed_time
print(f"Graph Fusion Time:")
else:
total_time = embed_time
print("Graph Fusion Time: 0")
print(f"Graph Embedding Time: {embed_time:.3f}")
print(f"Total Time = Embedding_time = {total_time:.3f}")
return None
map = dict()
with open(file, newline='') as csvfile:
csvfile.readline()
for (idx, name) in csv.reader(csvfile, delimiter=',', quotechar='|'):
map[name] = int(idx)
return map
args = parse_args()
dataset_name = args.dataset
if args.do_test:
meta = 'dataset_' + re.sub('-', '_', args.dataset) + '/meta_dict.pt'
meta_dict = load(meta)
dataset = LinkPropPredDataset(dataset_name, meta_dict=meta_dict)
dsplit = dataset.get_edge_split()
if args.print_relations:
np.set_printoptions(threshold=np.inf)
print('test.relations <- c(')
print(
re.sub('[\[\]]', '',
np.array2string(dsplit['test']['relation'],
separator=', ')))
print(')')
elif args.select_head >= 0 or args.select_tail >= 0:
for k in dsplit.keys():
for i in range(len(dsplit[k]['head'])):
(h, t, r) = (dsplit[k]['head'][i], dsplit[k]['tail'][i],
dsplit[k]['relation'][i])
if args.select_head < 0 or args.select_head == h: