def gae_for(args):
print("Using {} dataset".format(args.dataset_str))
adj, features = load_data(args.dataset_str)
# print(features)
# exit(0)
n_nodes, feat_dim = features.shape
print("#nodes={}".format(n_nodes))
# Store original adjacency matrix (without diagonal entries) for later
print(
"Store original adjacency matrix (without diagonal entries) for later..."
)
adj_orig = adj
adj_orig = adj_orig - sp.dia_matrix(
(adj_orig.diagonal()[np.newaxis, :], [0]), shape=adj_orig.shape)
adj_orig.eliminate_zeros()
print("Sample the edges for training and testing...")
adj_train, train_edges, val_edges, val_edges_false, test_edges, test_edges_false = mask_test_edges(
adj)
adj = adj_train
# Some preprocessing
print("Some preprocessing...")
adj_norm = preprocess_graph(adj)
adj_label = adj_train + sp.eye(adj_train.shape[0])
# adj_label = sparse_to_tuple(adj_label)
adj_label = torch.FloatTensor(adj_label.toarray())
pos_weight = float(adj.shape[0] * adj.shape[0] - adj.sum()) / adj.sum()
norm = adj.shape[0] * adj.shape[0] / float(
(adj.shape[0] * adj.shape[0] - adj.sum()) * 2)
model = GCNModelVAE(feat_dim, args.hidden1, args.hidden2, args.dropout)
optimizer = optim.Adam(model.parameters(), lr=args.lr)
hidden_emb = None
for epoch in range(args.epochs):
t = time.time()
model.train()
optimizer.zero_grad()
recovered, mu, logvar = model(features, adj_norm)
pos_weight = torch.Tensor([pos_weight])
loss = loss_function(preds=recovered,
labels=adj_label,
mu=mu,
logvar=logvar,
n_nodes=n_nodes,
norm=norm,
pos_weight=pos_weight)
loss.backward()
cur_loss = loss.item()
optimizer.step()
hidden_emb = mu.data.numpy()
roc_curr, ap_curr = get_roc_score(hidden_emb, adj_orig, val_edges,
val_edges_false)
print("Epoch:", '%04d' % (epoch + 1), "train_loss=",
"{:.5f}".format(cur_loss), "val_ap=", "{:.5f}".format(ap_curr),
"time=", "{:.5f}".format(time.time() - t))
print("Optimization Finished!")
roc_score, ap_score = get_roc_score(hidden_emb, adj_orig, test_edges,
test_edges_false)
print('Test ROC score: ' + str(roc_score))
print('Test AP score: ' + str(ap_score))
def gae_for(args):
print("Using {} dataset".format(args.dataset_str))
adj, features = load_data(args.dataset_str)
features = features.to(args.device)
n_nodes, feat_dim = features.shape
# Store original adjacency matrix (without diagonal entries) for later
adj_orig = adj
adj_orig = adj_orig - sp.dia_matrix(
(adj_orig.diagonal()[np.newaxis, :], [0]), shape=adj_orig.shape)
adj_orig.eliminate_zeros()
adj_train, train_edges, val_edges, val_edges_false, test_edges, test_edges_false = mask_test_edges(
adj)
adj = adj_train
# Some preprocessing
adj_norm = preprocess_graph(adj)
adj_norm = adj_norm.to(args.device)
adj_label = adj_train + sp.eye(adj_train.shape[0])
# adj_label = sparse_to_tuple(adj_label)
adj_label = torch.FloatTensor(adj_label.toarray())
adj_orig_tile = adj_label.unsqueeze(2).repeat(1, 1, args.K)
adj_orig_tile = adj_orig_tile.to(args.device)
pos_weight = torch.tensor(
float(adj.shape[0] * adj.shape[0] - adj.sum()) /
adj.sum()).float().to(device=args.device)
norm = adj.shape[0] * adj.shape[0] / float(
(adj.shape[0] * adj.shape[0] - adj.sum()) * 2)
psi_input_dim = args.noise_dim + feat_dim
logv_input_dim = feat_dim
model = GCNModelVAE(psi_input_dim, logv_input_dim, args.hidden1,
args.hidden2, args.dropout, args.K, args.J,
args.noise_dim, args.device).to(args.device)
optimizer = optim.Adam(model.parameters(), lr=args.lr)
for epoch in range(args.epochs):
warm_up = torch.min(torch.FloatTensor([epoch / 300,
1])).to(args.device)
t = time.time()
model.train()
optimizer.zero_grad()
reconstruct_iw, log_prior_iw, log_H_iw, psi_iw_vec = model(
features, adj_norm)
hidden_emb = psi_iw_vec.data.contiguous().cpu().numpy()
loss = loss_function(reconstructed_iw=reconstruct_iw,
log_prior_iw=log_prior_iw,
log_H_iw=log_H_iw,
adj_orig_tile=adj_orig_tile,
nodes=n_nodes,
K=args.K,
pos_weight=pos_weight,
norm=norm,
warm_up=warm_up,
device=args.device)
loss.backward()
cur_loss = loss.item()
optimizer.step()
roc_score_val, ap_score_val = get_roc_score(hidden_emb, adj_orig,
val_edges, val_edges_false)
roc_score_test, ap_score_test = get_roc_score(hidden_emb, adj_orig,
test_edges,
test_edges_false)
print('Epoch:', '%04d ---> ' % (epoch + 1),
'training_loss = {:.5f} '.format(cur_loss),
'val_AP = {:.5f} '.format(ap_score_val),
'val_ROC = {:.5f} '.format(roc_score_val),
'test_AP = {:.5f} '.format(ap_score_test),
'test_ROC = {:.5f} '.format(roc_score_test),
'time = {:.5f} '.format(time.time() - t))
writer.add_scalar('Loss/train_loss', cur_loss, epoch)
writer.add_scalar('Average Precision/test', ap_score_test, epoch)
writer.add_scalar('Average Precision/val', ap_score_val, epoch)
writer.add_scalar('Area under Roc(AUC)/test', roc_score_test, epoch)
writer.add_scalar('Area under Roc(AUC)/val', roc_score_val, epoch)
print("Optimization Finished!")
def gae_for(args):
print("Using {} dataset".format(args.dataset_str))
adj, features, y_test, tx, ty, test_maks, true_labels = load_data(
args.dataset_str)
n_nodes, feat_dim = features.shape
# Store original adjacency matrix (without diagonal entries) for later
adj_orig = adj
adj_orig = adj_orig - sp.dia_matrix(
(adj_orig.diagonal()[np.newaxis, :], [0]), shape=adj_orig.shape)
adj_orig.eliminate_zeros()
adj_train, train_edges, val_edges, val_edges_false, test_edges, test_edges_false = mask_test_edges(
adj)
adj = adj_train
# Before proceeding further, make the structure for doing deepWalk
if args.dw == 1:
print('Using deepWalk regularization...')
G = load_edgelist_from_csr_matrix(adj_orig, undirected=True)
print("Number of nodes: {}".format(len(G.nodes())))
num_walks = len(G.nodes()) * args.number_walks
print("Number of walks: {}".format(num_walks))
data_size = num_walks * args.walk_length
print("Data size (walks*length): {}".format(data_size))
# Some preprocessing
adj_norm = preprocess_graph(adj)
adj_label = adj_train + sp.eye(adj_train.shape[0])
# adj_label = sparse_to_tuple(adj_label)
# adj_label = torch.DoubleTensor(adj_label.toarray())
adj_label = torch.FloatTensor(adj_label.toarray())
pos_weight = float(adj.shape[0] * adj.shape[0] - adj.sum()) / adj.sum()
norm = adj.shape[0] * adj.shape[0] / float(
(adj.shape[0] * adj.shape[0] - adj.sum()) * 2)
if args.model == 'gcn_vae':
model = GCNModelVAE(feat_dim, args.hidden1, args.hidden2, args.dropout)
else:
model = GCNModelAE(feat_dim, args.hidden1, args.hidden2, args.dropout)
optimizer = optim.Adam(model.parameters(), lr=args.lr)
if args.dw == 1:
sg = SkipGram(args.hidden2, adj.shape[0])
optimizer_dw = optim.Adam(sg.parameters(), lr=args.lr_dw)
# Construct the nodes for doing random walk. Doing it before since the seed is fixed
nodes_in_G = list(G.nodes())
chunks = len(nodes_in_G) // args.number_walks
random.Random().shuffle(nodes_in_G)
hidden_emb = None
for epoch in tqdm(range(args.epochs)):
t = time.time()
model.train()
optimizer.zero_grad()
z, mu, logvar = model(features, adj_norm)
# After back-propagating gae loss, now do the deepWalk regularization
if args.dw == 1:
sg.train()
if args.full_number_walks > 0:
walks = build_deepwalk_corpus(G,
num_paths=args.full_number_walks,
path_length=args.walk_length,
alpha=0,
rand=random.Random(SEED))
else:
walks = build_deepwalk_corpus_iter(
G,
num_paths=args.number_walks,
path_length=args.walk_length,
alpha=0,
rand=random.Random(SEED),
chunk=epoch % chunks,
nodes=nodes_in_G)
for walk in walks:
if args.context == 1:
# Construct the pairs for predicting context node
# for each node, treated as center word
curr_pair = (int(walk[center_node_pos]), [])
for center_node_pos in range(len(walk)):
# for each window position
for w in range(-args.window_size,
args.window_size + 1):
context_node_pos = center_node_pos + w
# make soure not jump out sentence
if context_node_pos < 0 or context_node_pos >= len(
walk
) or center_node_pos == context_node_pos:
continue
context_node_idx = walk[context_node_pos]
curr_pair[1].append(int(context_node_idx))
else:
# first item in the walk is the starting node
curr_pair = (int(walk[0]), [
int(context_node_idx) for context_node_idx in walk[1:]
])
if args.ns == 1:
neg_nodes = []
pos_nodes = set(walk)
while len(neg_nodes) < args.walk_length - 1:
rand_node = random.randint(0, n_nodes - 1)
if rand_node not in pos_nodes:
neg_nodes.append(rand_node)
neg_nodes = torch.from_numpy(np.array(neg_nodes)).long()
# Do actual prediction
src_node = torch.from_numpy(np.array([curr_pair[0]])).long()
tgt_nodes = torch.from_numpy(np.array(curr_pair[1])).long()
optimizer_dw.zero_grad()
log_pos = sg(src_node, tgt_nodes, neg_sample=False)
if args.ns == 1:
loss_neg = sg(src_node, neg_nodes, neg_sample=True)
loss_dw = log_pos + loss_neg
else:
loss_dw = log_pos
loss_dw.backward(retain_graph=True)
cur_dw_loss = loss_dw.item()
optimizer_dw.step()
loss = loss_function(preds=model.dc(z),
labels=adj_label,
mu=mu,
logvar=logvar,
n_nodes=n_nodes,
norm=norm,
pos_weight=pos_weight)
loss.backward()
cur_loss = loss.item()
optimizer.step()
hidden_emb = mu.data.numpy()
roc_curr, ap_curr = get_roc_score(hidden_emb, adj_orig, val_edges,
val_edges_false)
if args.dw == 1:
tqdm.write(
"Epoch: {}, train_loss_gae={:.5f}, train_loss_dw={:.5f}, val_ap={:.5f}, time={:.5f}"
.format(epoch + 1, cur_loss, cur_dw_loss, ap_curr,
time.time() - t))
else:
tqdm.write(
"Epoch: {}, train_loss_gae={:.5f}, val_ap={:.5f}, time={:.5f}".
format(epoch + 1, cur_loss, ap_curr,
time.time() - t))
if (epoch + 1) % 10 == 0:
tqdm.write("Evaluating intermediate results...")
kmeans = KMeans(n_clusters=args.n_clusters,
random_state=0).fit(hidden_emb)
predict_labels = kmeans.predict(hidden_emb)
cm = clustering_metrics(true_labels, predict_labels)
cm.evaluationClusterModelFromLabel(tqdm)
roc_score, ap_score = get_roc_score(hidden_emb, adj_orig,
test_edges, test_edges_false)
tqdm.write('ROC: {}, AP: {}'.format(roc_score, ap_score))
np.save('logs/emb_epoch_{}.npy'.format(epoch + 1), hidden_emb)
tqdm.write("Optimization Finished!")
roc_score, ap_score = get_roc_score(hidden_emb, adj_orig, test_edges,
test_edges_false)
tqdm.write('Test ROC score: ' + str(roc_score))
tqdm.write('Test AP score: ' + str(ap_score))
kmeans = KMeans(n_clusters=args.n_clusters, random_state=0).fit(hidden_emb)
predict_labels = kmeans.predict(hidden_emb)
cm = clustering_metrics(true_labels, predict_labels)
cm.evaluationClusterModelFromLabel(tqdm)
if args.plot == 1:
cm.plotClusters(tqdm, hidden_emb, true_labels)
# mu=mu,
# logvar=logvar,
# n_nodes=n_nodes,
# norm=norm,
# pos_weight=pos_weight)
#
# cpu_loss = loss.cpu()
# cur_loss_list.append(cpu_loss.data.numpy().tolist())
# loss.backward()
# optimizer.step()
###################################################################
optimizer = optim.Adam(model.parameters(), lr=args.lr)
hidden_emb = None
t = time.time()
model.train()
optimizer.zero_grad()
features_bs = features_bs.cuda()
adj_norm = adj_norm.cuda()
# print('features_bs :')
# print(features_bs)
# print('adj_norm :')
# print(adj_norm)
recovered, mu, logvar = model(features_bs, adj_norm)
loss = loss_function(preds=recovered,
labels=adj_label,
mu=mu,
logvar=logvar,
n_nodes=n_nodes,
norm=norm,
def gae_for(args):
print("Using {} dataset".format(args.dataset_str))
adj, features, y_test, tx, ty, test_maks, true_labels = load_data(args.dataset_str)
n_nodes, feat_dim = features.shape
# Store original adjacency matrix (without diagonal entries) for later
adj_orig = adj
adj_orig = adj_orig - sp.dia_matrix((adj_orig.diagonal()[np.newaxis, :], [0]), shape=adj_orig.shape)
adj_orig.eliminate_zeros()
adj_train, train_edges, val_edges, val_edges_false, test_edges, test_edges_false = mask_test_edges(adj)
adj = adj_train
# Some preprocessing
adj_norm = preprocess_graph(adj)
adj_label = adj_train + sp.eye(adj_train.shape[0])
# adj_label = sparse_to_tuple(adj_label)
# adj_label = torch.DoubleTensor(adj_label.toarray())
adj_label = torch.FloatTensor(adj_label.toarray())
pos_weight = float(adj.shape[0] * adj.shape[0] - adj.sum()) / adj.sum()
norm = adj.shape[0] * adj.shape[0] / float((adj.shape[0] * adj.shape[0] - adj.sum()) * 2)
if args.model == 'gcn_vae':
model = GCNModelVAE(feat_dim, args.hidden1, args.hidden2, args.dropout)
else:
model = GCNModelAE(feat_dim, args.hidden1, args.hidden2, args.dropout)
optimizer = optim.Adam(model.parameters(), lr=args.lr)
hidden_emb = None
for epoch in tqdm(range(args.epochs)):
t = time.time()
model.train()
optimizer.zero_grad()
z, mu, logvar = model(features, adj_norm)
loss = loss_function(preds=model.dc(z), labels=adj_label,
mu=mu, logvar=logvar, n_nodes=n_nodes,
norm=norm, pos_weight=pos_weight)
loss.backward()
cur_loss = loss.item()
optimizer.step()
hidden_emb = mu.data.numpy()
roc_curr, ap_curr = get_roc_score(hidden_emb, adj_orig, val_edges, val_edges_false)
tqdm.write("Epoch: {}, train_loss_gae={:.5f}, val_ap={:.5f}, time={:.5f}".format(
epoch + 1, cur_loss,
ap_curr, time.time() - t))
if (epoch + 1) % 10 == 0:
tqdm.write("Evaluating intermediate results...")
kmeans = KMeans(n_clusters=args.n_clusters, random_state=0).fit(hidden_emb)
predict_labels = kmeans.predict(hidden_emb)
cm = clustering_metrics(true_labels, predict_labels)
cm.evaluationClusterModelFromLabel(tqdm)
roc_score, ap_score = get_roc_score(hidden_emb, adj_orig, test_edges, test_edges_false)
tqdm.write('ROC: {}, AP: {}'.format(roc_score, ap_score))
np.save('logs/emb_epoch_{}.npy'.format(epoch + 1), hidden_emb)
tqdm.write("Optimization Finished!")
roc_score, ap_score = get_roc_score(hidden_emb, adj_orig, test_edges, test_edges_false)
tqdm.write('Test ROC score: ' + str(roc_score))
tqdm.write('Test AP score: ' + str(ap_score))
kmeans = KMeans(n_clusters=args.n_clusters, random_state=0).fit(hidden_emb)
predict_labels = kmeans.predict(hidden_emb)
cm = clustering_metrics(true_labels, predict_labels)
cm.evaluationClusterModelFromLabel(tqdm)
if args.plot == 1:
cm.plotClusters(tqdm, hidden_emb, true_labels)
