opt1 = torch.optim.Adam(log.parameters(), lr=0.01, weight_decay=0.0)
log.cuda()
log.train()
for _ in range(100):
opt1.zero_grad()
logits = log(train_embs)
loss1 = xent(logits, train_lbls)
#print('logreg loss ', loss1)
loss1.backward()
opt1.step()
log.eval()
with torch.no_grad():
logits = log(test_embs)
preds = torch.argmax(logits, dim=1)
acc = torch.sum(preds == test_lbls).float() / test_lbls.shape[0]
accs.append(acc * 100)
print(acc)
tot += acc
print('Average accuracy:', tot / 50)
accs = torch.stack(accs)
print(accs.mean())
print(accs.std())
def process_inductive(dataset, gnn_type="GCNConv", K=None, random_init=False, runs=10):
hyperparameters = get_hyperparameters()
nb_epochs = hyperparameters["nb_epochs"]
patience = hyperparameters["patience"]
lr = hyperparameters["lr"]
l2_coef = hyperparameters["l2_coef"]
drop_prob = hyperparameters["drop_prob"]
hid_units = hyperparameters["hid_units"]
nonlinearity = hyperparameters["nonlinearity"]
batch_size = hyperparameters["batch_size"]
norm_features = torch_geometric.transforms.NormalizeFeatures()
dataset_train = PPI(
"./geometric_datasets/"+dataset,
split="train",
transform=norm_features,
)
print(dataset_train)
dataset_val = PPI(
"./geometric_datasets/"+dataset,
split="val",
transform=norm_features,
)
print(dataset_val)
dataset_test = PPI(
"./geometric_datasets/"+dataset,
split="test",
transform=norm_features,
)
data = []
for d in dataset_train:
data.append(d)
for d in dataset_val:
data.append(d)
ft_size = dataset_train[0].x.shape[1]
nb_classes = dataset_train[0].y.shape[1] # multilabel
b_xent = nn.BCEWithLogitsLoss()
loader_train = DataLoader(
data,
batch_size=hyperparameters["batch_size"],
shuffle=True,
)
loader_test = DataLoader(
dataset_test,
batch_size=hyperparameters["batch_size"],
shuffle=False
)
all_accs = []
for _ in range(runs):
model = DGI(ft_size, hid_units, nonlinearity, update_rule=gnn_type, batch_size=1, K=K)
model_name = get_model_name(dataset, gnn_type, K, random_init=random_init)
print(model)
optimiser = torch.optim.Adam(model.parameters(), lr=lr, weight_decay=l2_coef)
if torch.cuda.is_available():
print('Using CUDA')
model = model.cuda()
model.train()
torch.cuda.empty_cache()
for epoch in range(20):
if random_init:
break
total_loss = 0
batch_id = 0
model.train()
loaded = list(loader_train)
for batch in loaded:
optimiser.zero_grad()
if torch.cuda.is_available:
batch = batch.to('cuda')
nb_nodes = batch.x.shape[0]
features = batch.x
labels = batch.y
edge_index = batch.edge_index
idx = np.random.randint(0, len(data))
while idx == batch_id:
idx = np.random.randint(0, len(data))
shuf_fts = torch.nn.functional.dropout(loaded[idx].x, drop_prob)
edge_index2 = loaded[idx].edge_index
lbl_1 = torch.ones(nb_nodes)
lbl_2 = torch.zeros(shuf_fts.shape[0])
lbl = torch.cat((lbl_1, lbl_2), 0)
if torch.cuda.is_available():
shuf_fts = shuf_fts.cuda()
if edge_index2 is not None:
edge_index2 = edge_index2.cuda()
lbl = lbl.cuda()
logits = model(features, shuf_fts, edge_index, batch=batch.batch, edge_index_alt=edge_index2)
loss = b_xent(logits, lbl)
loss.backward()
optimiser.step()
batch_id += 1
total_loss += loss.item()
print(epoch, 'Train Loss:', total_loss/(len(dataset_train)))
torch.save(model.state_dict(), './trained_models/'+model_name)
torch.cuda.empty_cache()
print('Loading last epoch')
if not random_init:
model.load_state_dict(torch.load('./trained_models/'+model_name))
model.eval()
b_xent_reg = nn.BCEWithLogitsLoss(pos_weight=torch.tensor(2.25))
train_embs, whole_train_data = preprocess_embeddings(model, dataset_train)
val_embs, whole_val_data = preprocess_embeddings(model, dataset_val)
test_embs, whole_test_data = preprocess_embeddings(model, dataset_test)
for _ in range(50):
log = LogReg(hid_units, nb_classes)
opt = torch.optim.Adam(log.parameters(), lr=0.01, weight_decay=0.0)
log.cuda()
pat_steps = 0
best = 1e9
log.train()
for _ in range(250):
opt.zero_grad()
logits = log(train_embs)
loss = b_xent_reg(logits, whole_train_data.y)
loss.backward()
opt.step()
log.eval()
val_logits = log(val_embs)
loss = b_xent_reg(val_logits, whole_val_data.y)
if loss.item() < best:
best = loss.item()
pat_steps = 0
if pat_steps >= 5:
break
pat_steps += 1
log.eval()
logits = log(test_embs)
preds = torch.sigmoid(logits) > 0.5
f1 = sklearn.metrics.f1_score(whole_test_data.y.cpu(), preds.long().cpu(), average='micro')
all_accs.append(float(f1))
print()
print('Micro-averaged f1:', f1)
all_accs = torch.tensor(all_accs)
with open("./results/"+model_name[:-4]+"_results.txt", "w") as f:
f.writelines([str(all_accs.mean().item())+'\n', str(all_accs.std().item())])
print(all_accs.mean())
print(all_accs.std())