def gae_for(args):
print("Using {} dataset".format(args.dataset_str))
adj, features = 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.FloatTensor(adj_label.toarray())
pos_weight = torch.Tensor(
[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)
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, 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.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)
def gae_for(args):
print("Using {} dataset".format(args.dataset_str))
adj, features = load_corpus(args.dataset_str)
# n_nodes, feat_dim = features.shape
# print(n_nodes, feat_dim)
print(type(features))
print(adj)
# print(adj[0], adj[1])
features = sp.identity(features.shape[0]) # featureless
# print(adj.shape)
# print(features.shape)
# Some preprocessing
features = preprocess_features(features)
adj_norm = preprocess_adj(adj)
num_supports = 1
# model_func = GCN
adj_norm = torch.FloatTensor(adj_norm.toarray())
features = torch.FloatTensor(features.toarray())
n_nodes, feat_dim = features.shape
print(n_nodes, feat_dim)
print(type(features))
print(type(adj_norm))
print(features.shape)
print(adj_norm.shape)
# n_nodes, feat_dim = features.shape
# print(n_nodes, feat_dim)
# 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()
# modified/added by hollis
# adj_train, train_edges, val_edges, val_edges_false, test_edges, test_edges_false = mask_test_edges(adj)
# Remove diagonal elements
# adj = adj - sp.dia_matrix((adj.diagonal()[np.newaxis, :], [0]), shape=adj.shape)
# adj.eliminate_zeros()
# Check that diag is zero:
# assert np.diag(adj.todense()).sum() == 0
# adj_train = sp.csr_matrix(adj)
# adj_train = adj_train + adj_train.T
# Some preprocessing
# adj_norm = normalize_adj(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())
# adj_label = np.array(adj_label, dtype=float)
# adj_label = torch.FloatTensor(adj_label)
pos_weight = float(adj.shape[0] * adj.shape[0] - adj.sum()) / adj.sum()
# added by hollis
# pos_weight = torch.from_numpy(np.array(pos_weight))
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)
model = GCNModelVAE(feat_dim, args.hidden1, args.dropout)
optimizer = optim.Adam(model.parameters(), lr=args.lr)
hidden_emb = None
for epoch in range(args.epochs):
print("in epoch")
t = time.time()
model.train()
optimizer.zero_grad()
# recovered, mu, logvar = model(features, adj_norm)
print("before model")
recovered, mu, logvar = model(features, adj_norm)
print("before loss")
loss = loss_function(preds=recovered,
labels=adj_norm,
mu=mu,
logvar=logvar,
n_nodes=n_nodes,
norm=norm)
#loss = loss_function(preds=recovered, labels=adj_label,
# mu=mu, logvar=logvar, n_nodes=n_nodes,
# norm=norm, pos_weight=pos_weight)
print("befor backword")
loss.backward()
cur_loss = loss.item()
optimizer.step()
hidden_emb = mu.data.numpy()
hidden_emb = np.array(hidden_emb)
if epoch == 1:
fni = "./result/emb_init.txt"
hidden_emb = np.array(hidden_emb)
np.savetxt(fni, hidden_emb)
if epoch == args.epochs - 1:
fnf = "./result/emb.txt"
hidden_emb = np.array(hidden_emb)
np.savetxt(fnf, hidden_emb)
#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!")
def gae_for(args, position):
print("Using {} dataset".format(args.dataset_str))
#qhashes, chashes = load_hashes()
Q, X = load_data()
prebuild = "/media/chundi/3b6b0f74-0ac7-42c7-b76b-00c65f5b3673/revisitop/cnnimageretrieval-pytorch/data/test/matlab_data/GEM_wDis_prebuild.bin"
Q_features = "/media/chundi/3b6b0f74-0ac7-42c7-b76b-00c65f5b3673/revisitop/cnnimageretrieval-pytorch/data/test/matlab_data/roxford5k_GEM_lw_query_feats.npy" #"/media/jason/cc0aeb62-0bc7-4f3e-99a0-3bba3dd9f8fc/landmarks/oxfordRe/evaluation/roxHD_query_fused.npy"
X_features = "/media/chundi/3b6b0f74-0ac7-42c7-b76b-00c65f5b3673/revisitop/cnnimageretrieval-pytorch/data/test/matlab_data/roxford5k_GEM_index.npy"
D_features = "/media/chundi/3b6b0f74-0ac7-42c7-b76b-00c65f5b3673/revisitop/cnnimageretrieval-pytorch/data/test/matlab_data/roxford5k_GEM_Dis.npy"
adj, features, adj_Q, features_Q = load_from_prebuild(prebuild,
Q_features,
X_features,
D_features,
k=5) # ----> 1M
#cut_size = 800000
#adj = adj[:cut_size, :cut_size]
#adj_Q = adj_Q[:, :cut_size]
#features = features[:cut_size]
#Q = np.load("/media/jason/cc0aeb62-0bc7-4f3e-99a0-3bba3dd9f8fc/landmarks/oxfordRe/evaluation/roxHD_query_fused.npy").T.astype(np.float32)
#X = np.load("/media/jason/cc0aeb62-0bc7-4f3e-99a0-3bba3dd9f8fc/landmarks/oxfordRe/evaluation/roxHD_index_fused.npy").T.astype(np.float32)
#D = np.load("/media/jason/cc0aeb62-0bc7-4f3e-99a0-3bba3dd9f8fc/landmarks/revisitop1m/revisitDistractors_fused_3s_cq.npy").T.astype(np.float32)
#X = np.concatenate((X.T,D.T)).T
# load the distractor too, shape should be (2048, 1M)
#adj, features = gen_graph_index(Q, X, k=5, k_qe=3, do_qe=False) #-----> 5k
#adj_Q, features_Q = gen_graph(Q, X, k=5, k_qe=3, do_qe=False) #generate validation/revop evaluation the same way as training ----> 5k
features_all = np.concatenate([features_Q, features])
features_all = torch.from_numpy(features_all)
#adj_Q = adj_Q.todense()
#adj_all = np.concatenate([adj_Q, adj.todense()])
#adj_all = np.pad(adj_all, [[0,0], [Q.shape[1], 0]], "constant")
adj_all = sp.vstack((adj_Q, adj))
zeros = sp.csr_matrix((adj_all.shape[0], Q.shape[1]))
adj_all = sp.hstack((zeros, adj_all))
adj_all = sp.csr_matrix(adj_all)
rows, columns = adj_all.nonzero()
print("Making Symmetry")
for i in range(rows.shape[0]):
if rows[i] < Q.shape[1]:
adj_all[columns[i], rows[i]] = adj_all[rows[i], columns[i]]
else:
break
#adj_all = sp.csr_matrix(adj_all)
print("preprocessing adj_all")
adj_all_norm = preprocess_graph(adj_all)
#adj = add_neighbours_neighbour(adj)
#adj1, features1 = load_data(args.dataset_str)
features = torch.from_numpy(features)
#features_all = torch.from_numpy(features_all)
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 = adj_orig
#adj_train, train_edges, val_edges, val_edges_false, test_edges, test_edges_false = mask_test_edges(adj)
print("Sampling validation")
adj_train, adj_val, features, features_valid = mask_test_rows(
adj, features)
adj = adj_train
# Some preprocessing
print("preprocessing adj")
adj_norm = preprocess_graph(adj)
#adj_norm_label = preprocess_graph_sp(adj)
adj_label = adj_train + sp.eye(
adj_train.shape[0]
) #adj_norm_label + sp.eye(adj_train.shape[0]) #adj_train + sp.eye(adj_train.shape[0])
#rows, columns = adj_label.nonzero()
#adj_label[columns, rows] = adj_label[rows, columns]
# adj_label = sparse_to_tuple(adj_label)
#adj_label = torch.FloatTensor(adj_label.toarray())
print("adj sum: " + str(adj.sum()))
pos_weight = float(float(adj.shape[0]) * adj.shape[0] -
adj.sum()) / adj.sum()
print("top part: " +
str(float(float(adj.shape[0]) * adj.shape[0] - adj.sum())))
print("pos wieght: " + str(pos_weight))
norm = adj.shape[0] * adj.shape[0] / float(
(adj.shape[0] * adj.shape[0] - adj.sum()) * 2)
# for validation data processing:
zero = sp.csr_matrix((adj_train.shape[0], adj_val.shape[0]))
adj_train_ext = sp.hstack((zero, adj_train))
adj_evaluate = sp.vstack((adj_val, adj_train_ext))
adj_evaluate = sp.csr_matrix(adj_evaluate)
rows, columns = adj_evaluate.nonzero()
val_edges = []
val_edges_false = []
pos = {}
print("getting positive edges")
all_val = [i for i in range(len(rows)) if rows[i] < adj_val.shape[0]]
for i in all_val:
sys.stdout.write("\r sampling edges for validtion: [" + str(i) + "]")
val_edges.append((rows[i], columns[i]))
if rows[i] not in pos:
pos[rows[i]] = []
pos[rows[i]].append(columns[i])
#for i in range(rows.shape[0]):
# sys.stdout.write("\r sampling edges for validtion: [" + str(i) + "/" + str(adj_val.shape[0]) + "]")
# sys.stdout.flush()
# if rows[i] < adj_val.shape[0]:
# val_edges.append((rows[i], columns[i]))
# if rows[i] not in pos:
# pos[rows[i]] = []
# pos[rows[i]].append(columns[i])
# adj_evaluate[columns[i], rows[i]] = adj_evaluate[rows[i], columns[i]]
# else:
# break
step = 0
neg_per_pos = 100
#for r in pos:
# p = pos[r]
#neg_edges = Parallel(n_jobs=40)(delayed(neg_sample)(pos[i], adj_val.shape[1], neg_per_pos, i) for i in pos)
#val_edges_false = [(i, item) for i in range(len(neg_edges)) for item in neg_edges[i]]
#a = np.random.permutation(adj_val.shape[1])
#a = [i for i in a if i not in p]
#a = a[:100]
#for i in a:
# val_edges_false.append((r, i))
##count = 0
##i = 0
#sys.stdout.write("\r sampling neg edges for validtion: [" + str(step) + "/" + str(len(pos)) + "]")
#sys.stdout.flush()
#step += 1
#while count < 100:
# if a[i] not in p:
# val_edges_false.append((r, a[i]))
# count += 1
# i += 1
print("preprocessing adj_evaluate")
adj_evaluate_norm = preprocess_graph(adj_evaluate)
#adj_evaluate_norm_label = preprocess_graph_sp(adj_evaluate)
adj_label_evaluate = adj_evaluate + sp.eye(
adj_evaluate.shape[0]
) #adj_evaluate_norm_label+ sp.eye(adj_evaluate.shape[0]) #adj_evaluate + sp.eye(adj_evaluate.shape[0])
#adj_label_evaluate = torch.FloatTensor(adj_label_evaluate.toarray()) #sparse_mx_to_torch_sparse_tensor(adj_label_evaluate)
features_evaluate = np.concatenate([features, features_valid])
features_evaluate = torch.from_numpy(features_evaluate)
# validation done
if mode == "VAE":
model = GCNModelVAE(feat_dim, args.hidden1, args.hidden2, args.dropout)
adj_label = torch.FloatTensor(adj_label.toarray())
adj_label_evaluate = torch.FloatTensor(adj_label_evaluate.toarray())
elif mode == "AE":
model = GCNModelAE(feat_dim, args.hidden1, args.hidden2, args.dropout)
#adj_label = torch.FloatTensor(adj_label.toarray())
#adj_label_evaluate = torch.FloatTensor(adj_label_evaluate.toarray())
elif mode == "VAE_batch":
model = GCNModelVAE_batch(feat_dim, args.hidden1, args.hidden2,
args.dropout)
elif mode == "AE_batch":
model = GCNModelAE_batch(feat_dim, args.hidden1, args.hidden2,
args.dropout).cuda()
#model = torch.nn.DataParallel(model)
#model = model.cuda()
# train_dataset = GAEDataset(adj_norm, adj_label, features)
# train_loader = DataLoader(dataset=train_dataset, batch_size=args.batch_size,
# shuffle=True, num_workers=8, pin_memory=True)
train_ids = torch.tensor(range(features.shape[0]), dtype=torch.long)
train_dataset = TensorDataset(train_ids)
train_loader = DataLoader(dataset=train_dataset,
batch_size=args.batch_size,
shuffle=True,
num_workers=8,
pin_memory=True)
optimizer = optim.Adam(model.parameters(), lr=args.lr)
#optimizer = pSGLD(model.parameters(), lr=args.lr)
#optimizer = optim.RMSprop(model.parameters(), lr=args.lr)
hidden_emb = None
pos_weight = torch.from_numpy(np.array(0.0, dtype=np.float32))
#ipdb.set_trace()
t = time.time()
best = 0
best_epoch = 0
best_val_cost = 99999
best_val_epoch = 0
best_val_epoch_revop = 0
prev_loss = 0
prev_val_loss = 99999
best_val_roc = 0
best_val_ap = 0
best_val_roc_revop = 0
best_val_ap_revop = 0
torch.set_num_threads(20)
print("NUM THREADS USED")
print(torch.get_num_threads())
for epoch in range(args.epochs):
#t = time.time()
model.train()
lossVal = 0
lossValNorm = 0
backtime = time.time()
for batchID, (inds) in enumerate(train_loader):
z = model(features, adj_norm)
inds = inds[0]
adj = F.relu(torch.mm(z[inds], z[inds].t()))
preds = adj
label_batch = torch.FloatTensor(adj_label[inds, :][:,
inds].toarray())
cost = norm * F.binary_cross_entropy_with_logits(
preds, label_batch, pos_weight=pos_weight)
lossVal += cost.item()
lossValNorm += 1
optimizer.zero_grad()
cost.backward(retain_graph=True)
# if batchID == 0:
# cost.backward(retain_graph=True)
# else:
# cost.backward()
optimizer.step()
if batchID >= 10:
break
backtime_done = time.time() - backtime
sys.stdout.write("\r time taken to do epoch: " + str(backtime_done) +
" opt: " + str(time.time() - backtime) + "\n")
sys.stdout.flush()
#optimizer.step()
# sample rows only: non-square
#for i in range(0, d.shape[0], sample_size):
# selection = random_perm[i:i+sample_size]
# to_keep = selection
# sample_adj_norm = sparse_mx_to_torch_sparse_tensor(sp.coo_matrix(d[to_keep, :]))
# sample_adj = adj[to_keep, :]
# sample_features = features
# recovered, mu, logvar = model(sample_features, sample_adj_norm)
# loss = loss_function(preds=recovered, labels=sample_adj_label,
# mu=mu, logvar=logvar, n_nodes=n_nodes,
# norm=norm, pos_weight=pos_weight)
# loss.backward()
# cur_loss = loss.item()
# optimizer.step()
# sys.stdout.write("\r ")
# sys.stdout.write("\r" + "sampling [" + str(i) + "/" + str(d.shape[0]))
# sys.stdout.flush()
# sample rows + take their postiives and add to rows (make it square)
#for i in range(0, d.shape[0], sample_size):
# selection = random_perm[i:i+sample_size]
# to_keep = np.nonzero(d[selection, :])
# # (array([0, 1, 2, 2]), array([0, 1, 0, 1]))
# the_set = set(list(to_keep[0]) + list(to_keep[1]))
# temp = set(list(to_keep[0]))
# to_keep = list(the_set - column_exclude)
# # column_exclude.union(temp)
# # these ar ethe rows and columns that we need ne select
# sample_adj_norm = sparse_mx_to_torch_sparse_tensor(sp.coo_matrix(d[to_keep, :][:,to_keep]))
# sample_features = features[to_keep, :]
# sample_adj_label = adj_label[to_keep, :][:,to_keep]
# #print(samplei_adj_norm.shape)
# #print(sample_features.shape)
# #print(sample_adj_label.shape)
# #print(sample.shape)
# sample_adj = adj[to_keep, :][:,to_keep]
# pos_weight = float(sample_adj.shape[0] * sample_adj.shape[0] - sample_adj.sum()) / sample_adj.sum()
# pos_weight = torch.from_numpy(np.array(pos_weight))
# norm = sample_adj.shape[0] * sample_adj.shape[0] / float((sample_adj.shape[0] * sample_adj.shape[0] - sample_adj.sum()) * 2)
# n_nodes, feat_dim = sample_features.shape
# if mode == "VAE":
# recovered, mu, logvar = model(sample_features, sample_adj_norm)
# #recovered = recovered[i:i+500]
# #sample_adj_label = sample_adj_label[i:i+500]
# loss = loss_function(preds=recovered, labels=sample_adj_label,
# mu=mu, logvar=logvar, n_nodes=n_nodes,
# norm=norm, pos_weight=pos_weight)
# elif mode == "AE":
# recovered = model(sample_features, sample_adj_norm)
# loss = loss_function_ae(preds=recovered, labels=sample_adj_label,
# norm=norm, pos_weight=pos_weight)
# loss.backward()
# cur_loss = loss.item()
# optimizer.step()
# sys.stdout.write("\r ")
# sys.stdout.write("\r" + "sampling [" + str(i) + "/" + str(d.shape[0]) + "]....size of sample=" + str(len(sample_features)))
# sys.stdout.flush()
sys.stdout.write(
"\r \r"
)
if (epoch + 1) % 1 == 0:
model.eval()
#adj_dense = adj_train.todense()
#adj_val_dense = adj_val.todense()
#adj_train_ext = np.pad(adj_dense, [[0,0], [adj_val_dense.shape[0], 0]], "constant")
#adj_evaluate = np.concatenate([adj_val_dense, adj_train_ext])
#zero = sp.csr_matrix((adj_train.shape[0], adj_val.shape[0]))
#adj_train_ext = sp.hstack((zero, adj_train))
#adj_evaluate = sp.vstack((adj_val, adj_train_ext))
##zeros = sp.csr_matrix((adj_evaluate.shape[0], adj_val.shape[1]))
##adj_evaluate = sp.hstack((zeros, adj_evaluate))
#adj_evaluate = sp.csr_matrix(adj_evaluate)
#rows, columns = adj_evaluate.nonzero()
#for i in range(rows.shape[0]):
# if rows[i] < adj_val.shape[1]:
# adj_evaluate[columns[i], rows[i]] = adj_evaluate[rows[i], columns[i]]
# else:
# break
#adj_evaluate_norm = preprocess_graph(adj_evaluate)
#adj_label_evaluate = adj_evaluate + sp.eye(adj_evaluate.shape[0])
#adj_label_evaluate = torch.FloatTensor(adj_label_evaluate.toarray())
##adj_label_evaluate = sparse_to_tuple(adj_label_evaluate)
#features_evaluate = np.concatenate([features, features_valid])
#features_evaluate = torch.from_numpy(features_evaluate)
just_adj_evaluate = sparse_mx_to_torch_sparse_tensor(adj_evaluate)
#recovered, mu, logvar = model(features_evaluate, just_adj_evaluate.coalesce().indices(), just_adj_evaluate.coalesce().values())
#recovered, mu, logvar = model(features_evaluate, adj_evaluate_norm)
#val_loss = loss_function(preds=recovered, labels=adj_label_evaluate,
# mu=mu, logvar=logvar, n_nodes=n_nodes,
# norm=norm, pos_weight=pos_weight)
# if mode == "VAE":
# recovered, mu, logvar = model(features_evaluate, adj_evaluate_norm)
# val_loss = loss_function(preds=recovered, labels=adj_label_evaluate,
# mu=mu, logvar=logvar, n_nodes=n_nodes,
# norm=norm, pos_weight=pos_weight)
# elif mode == "AE":
# mu = model(features_evaluate, adj_evaluate_norm)
# val_loss = loss_function_ae(preds=recovered, labels=adj_label_evaluate,
# norm=norm, pos_weight=pos_weight)
# elif mode == "VAE_batch":
# recovered, mu, logvar, val_loss = model(features_evaluate, adj_evaluate_norm, labels=adj_label_evaluate, n_nodes=n_nodes, norm=norm, pos_weight=pos_weight, opt=None, training=False)
# elif mode == "AE_batch":
# recovered, mu, val_loss = model(features_evaluate, adj_evaluate_norm, labels=adj_label_evaluate, n_nodes=n_nodes, norm=norm, pos_weight=pos_weight, opt=None, training=False)
# val_emb = mu.data.numpy()
#roc_curr, ap_curr = get_roc_score(val_emb, val_edges, val_edges_false)
# do one q at a time
#revop_map = eval_each_q(model, adj_all, features_all, Q.shape[1])
# hack by appending stuff on top of adj
if mode == "VAE":
_, mu, _ = model(features_all, adj_all_norm)
elif mode == "AE":
mu = model(features_all, adj_all_norm)
elif mode == "VAE_batch":
mu = model(features_all,
adj_all_norm,
None,
None,
None,
None,
None,
just_mu=True,
training=False)
elif mode == "AE_batch":
mu = model(features_all,
adj_all_norm,
None,
None,
None,
None,
None,
just_mu=True,
training=False)
hidden_emb = mu.data.numpy()
## get validation loss
#recovered, mu, logvar = model(features, adj_norm)
#val_loss = loss_function(preds=recovered, labels=adj_label,
# mu=mu, logvar=logvar, n_nodes=n_nodes,
# norm=norm, pos_weight=pos_weight)
revop_map = get_roc_score_matrix(hidden_emb, Q.shape[1])
if best <= revop_map:
emb = hidden_emb
Q_end = Q.shape[1]
best = revop_map
best_epoch = epoch + 1
# write it into a file and do egt on that
#embQ = emb[:Q_end,:].T
#embX = emb[Q_end:,:].T
#np.save("/media/jason/28c9eee1-312e-47d0-88ce-572813ebd6f1/graph/gae-pytorch/best_embedding2.npy",hidden_emb)
#concat = np.concatenate((embQ.T,embX.T))
#revop_inner_prod = np.matmul(concat, concat.T)
#revop_preds = np.argsort(-revop_inner_prod,axis=0)
#if revop_map > 54:
# f = open("best_result.txt", "w")
# for i in range(revop_preds.shape[1]):
# if i < Q_end:
# f.write(qhashes[i] + ",")
# else:
# f.write(chashes[i - Q_end] + ",")
# for j in revop_preds[:,i]:
# if j < Q_end:
# f.write(qhashes[j] + " " + str(int(revop_inner_prod[j,i] * 1000)) + " ")
# else:
# f.write(chashes[j - Q_end] + " " + str(int(revop_inner_prod[j,i] * 1000)) + " ")
# f.write("\n")
# f.flush()
# #for j in range()
# f.close()
if best_val_cost > -99.0: #prev_val_loss - val_loss > 0 and prev_val_loss - val_loss > prev_loss - cur_loss and best_val_cost > val_loss:
best_val_cost = -99.0
best_val_epoch = epoch + 1
best_val_epoch_revop = revop_map
#if best_val_roc < roc_curr:
# best_val_roc = roc_curr
# best_val_roc_revop = revop_map
#if best_val_ap < ap_curr:
# best_val_ap = ap_curr
# best_val_ap_revop = revop_map
print(
"Epoch:",
'%04d' % (epoch + 1),
"train_loss=",
"{:.5f}".format(lossVal / lossValNorm),
"val_loss=",
"{:.5f}".format(-99.0),
#"val_roc_curr=", "{:.5f}".format(roc_curr),
#"val_ap_curr=", "{:.5f}".format(ap_curr),
"revop=",
"{:.5f}".format(revop_map),
"best_revop=",
"{:.5f}".format(best),
"revop_at_best_val=",
"{:.5f}".format(best_val_epoch_revop),
#"revop_at_best_val_roc=", "{:.5f}".format(best_val_roc_revop),
#"revop_at_best_ap_roc=", "{:.5f}".format(best_val_ap_revop),
"time=",
"{:.5f}".format(time.time() - t))
prev_val_loss = -99.0
prev_loss = -99.0
t = time.time()
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))
return best, best_val_epoch_revop, best_val_roc_revop, best_val_ap_revop
def __init__(self, graph_edgelist, num_actions, dimension, learning_rate=0.01, epochs=300, hidden1=32, hidden2=16,
dropout=0., model_str='gcn_vae', use_features=0):
"""Initialize ExactBasis."""
if graph_edgelist is None:
raise ValueError('graph cannot be None')
if dimension < 1:
raise ValueError('dimension must be >= 1')
self.__num_actions = BasisFunction._validate_num_actions(num_actions)
self._dimension = dimension
adj, features = self.read_graph(graph_edgelist)
# 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
if use_features == 0:
features = sp.identity(features.shape[0]) # featureless
# Some preprocessing
adj_norm = preprocess_graph(adj)
# Define placeholders
placeholders = {
'features': tf.sparse_placeholder(tf.float32),
'adj': tf.sparse_placeholder(tf.float32),
'adj_orig': tf.sparse_placeholder(tf.float32),
'dropout': tf.placeholder_with_default(0., shape=())
}
num_nodes = adj.shape[0]
features = sparse_to_tuple(features.tocoo())
num_features = features[2][1]
features_nonzero = features[1].shape[0]
# Create model
model = None
if model_str == 'gcn_ae':
model = GCNModelAE(placeholders, num_features, features_nonzero, hidden1, hidden2, dimension)
elif model_str == 'gcn_vae':
model = GCNModelVAE(placeholders, num_features, num_nodes, features_nonzero, hidden1, dimension)
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)
# Optimizer
with tf.name_scope('optimizer'):
if model_str == 'gcn_ae':
opt = OptimizerAE(preds=model.reconstructions,
labels=tf.reshape(tf.sparse_tensor_to_dense(placeholders['adj_orig'],
validate_indices=False), [-1]),
pos_weight=pos_weight,
norm=norm, learning_rate=learning_rate)
elif model_str == 'gcn_vae':
opt = OptimizerVAE(preds=model.reconstructions,
labels=tf.reshape(tf.sparse_tensor_to_dense(placeholders['adj_orig'],
validate_indices=False), [-1]),
model=model, num_nodes=num_nodes,
pos_weight=pos_weight,
norm=norm, learning_rate=learning_rate)
# Initialize session
sess = tf.Session()
sess.run(tf.global_variables_initializer())
adj_label = adj_train + sp.eye(adj_train.shape[0])
adj_label = sparse_to_tuple(adj_label)
# Train model
for epoch in range(epochs):
t = time.time()
# Construct feed dictionary
feed_dict = construct_feed_dict(adj_norm, adj_label, features, placeholders)
feed_dict.update({placeholders['dropout']: dropout})
# Run single weight update
outs = sess.run([opt.opt_op, opt.cost, opt.accuracy], feed_dict=feed_dict)
print("GCN Optimization Finished!")
feed_dict.update({placeholders['dropout']: 0})
self.embeddings = sess.run(model.z_mean, feed_dict=feed_dict)
def gae(filename, output_dir):
# Settings
flags = tf.app.flags
FLAGS = flags.FLAGS
flags.DEFINE_float('learning_rate', 0.01, 'Initial learning rate.')
flags.DEFINE_integer('epochs', 200, 'Number of epochs to train.')
flags.DEFINE_integer('hidden1', 32, 'Number of units in hidden layer 1.')
flags.DEFINE_integer('hidden2', 16, 'Number of units in hidden layer 2.')
flags.DEFINE_float('weight_decay', 0.,
'Weight for L2 loss on embedding matrix.')
flags.DEFINE_float('dropout', 0., 'Dropout rate (1 - keep probability).')
flags.DEFINE_string('filename', 'email-Eu-core.mat', 'dataset')
flags.DEFINE_string('model', 'gcn_vae', 'Model string.')
flags.DEFINE_string('dataset', 'cora', 'Dataset string.')
flags.DEFINE_integer('features', 0,
'Whether to use features (1) or not (0).')
model_str = FLAGS.model
# dataset_str = FLAGS.dataset
# Load data
# adj, features = load_data(dataset_str)
adj, R, edges = load_network_data(filename)
num_edges = np.sum(adj)
length = adj.shape[0]
A = np.array(adj, copy=True)
adj = sp.csr_matrix(adj)
# 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 = mask_test_edges(adj)
adj = adj_train
if FLAGS.features == 0:
features = sp.identity(adj.shape[0]) # featureless
# Some preprocessing
adj_norm = preprocess_graph(adj)
# Define placeholders
placeholders = {
'features': tf.sparse_placeholder(tf.float32),
'adj': tf.sparse_placeholder(tf.float32),
'adj_orig': tf.sparse_placeholder(tf.float32),
'dropout': tf.placeholder_with_default(0., shape=())
}
num_nodes = adj.shape[0]
features = sparse_to_tuple(features.tocoo())
num_features = features[2][1]
features_nonzero = features[1].shape[0]
# Create model
model = None
if model_str == 'gcn_ae':
model = GCNModelAE(placeholders, num_features, features_nonzero)
elif model_str == 'gcn_vae':
model = GCNModelVAE(placeholders, num_features, num_nodes,
features_nonzero)
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)
# Optimizer
with tf.name_scope('optimizer'):
if model_str == 'gcn_ae':
opt = OptimizerAE(preds=model.reconstructions,
labels=tf.reshape(
tf.sparse_tensor_to_dense(
placeholders['adj_orig'],
validate_indices=False), [-1]),
pos_weight=pos_weight,
norm=norm)
elif model_str == 'gcn_vae':
opt = OptimizerVAE(preds=model.reconstructions,
labels=tf.reshape(
tf.sparse_tensor_to_dense(
placeholders['adj_orig'],
validate_indices=False), [-1]),
model=model,
num_nodes=num_nodes,
pos_weight=pos_weight,
norm=norm)
# Initialize session
sess = tf.Session()
sess.run(tf.global_variables_initializer())
adj_label = adj_train + sp.eye(adj_train.shape[0])
adj_label = sparse_to_tuple(adj_label)
# Train model
for epoch in range(FLAGS.epochs):
t = time.time()
# Construct feed dictionary
feed_dict = construct_feed_dict(adj_norm, adj_label, features,
placeholders)
feed_dict.update({placeholders['dropout']: FLAGS.dropout})
# Run single weight update
outs = sess.run([opt.opt_op, opt.cost, opt.accuracy],
feed_dict=feed_dict)
# Compute average loss
# avg_cost = outs[1]
# avg_accuracy = outs[2]
#
# if (epoch + 1) % 10 == 0:
# print("Epoch:", '%04d' % (epoch + 1), "train_loss=", "{:.5f}".format(avg_cost),
# "train_acc=", "{:.5f}".format(avg_accuracy), "time=", "{:.5f}".format(time.time() - t))
print("GAE Optimization Finished!")
feed_dict.update({placeholders['dropout']: 0})
emb = sess.run(model.z_mean, feed_dict=feed_dict)
def sigmoid(x):
return 1 / (1 + np.exp(-x))
# Predict on test set of edges
adj_rec = np.dot(emb, emb.T)
adj_rec = np.array(adj_rec)
# adj_rec = adj_rec[1:length, :][:, 1:length]
DD = np.sort(adj_rec.flatten())
threshold = DD[int(-1 * num_edges)]
network_C = np.array([[
0 if adj_rec[i, j] < threshold else 1 for i in range(adj_rec.shape[0])
] for j in range(adj_rec.shape[1])],
dtype=np.int8)
# np.save('../data/GAE_network.npy', network_C[1:length, :][:, 1:length])
os.chdir('../')
np.save('{}/GAE_network.npy'.format(output_dir, filename),
network_C[1:length, :][:, 1:length])
A_copy = adj_rec
final_network = [A_copy]
# orinal_network = [A]
for i in range(1, 5):
adjacent_matrix = tf.placeholder(tf.float32, shape=A_copy.shape)
R_matrix = tf.placeholder(tf.float32, shape=R[i - 1, 0].shape)
A_copy = sess.run(tf.matmul(tf.matmul(R_matrix, adjacent_matrix),
tf.transpose(R_matrix)),
feed_dict={
R_matrix: R[i - 1, 0].todense(),
adjacent_matrix: A_copy
})
final_network.append(np.array(A_copy))
# adjacent_matrix = tf.placeholder(tf.float32, shape=A.shape)
# R_matrix = tf.placeholder(tf.float32, shape=R[i - 1, 0].shape)
# A = sess.run(tf.matmul(tf.matmul(R_matrix, adjacent_matrix), tf.transpose(R_matrix)),
# feed_dict={R_matrix: R[i - 1, 0].todense(), adjacent_matrix: A})
# orinal_network.append(A)
# draw_graph(final_network, edges, output_dir)
network_B = final_network[0]
print('Generating graph by GAE algorithm.')
DD = np.sort(network_B.flatten())[::-1]
threshold = DD[edges[0, 0]]
network_C = np.array([[
0 if network_B[i, j] < threshold else 1
for i in range(network_B.shape[0])
] for j in range(network_B.shape[1])])
_A_obs = network_C + network_C.T
_A_obs[_A_obs > 1] = 1
_A_obs = np.array(_A_obs)
print('Computing metrics for graph generated by GAE')
c = compute_graph_statistics(_A_obs)
with open('{}/gae_network_statistics.pickle'.format(output_dir),
'wb') as handle:
pickle.dump(c, handle, protocol=pickle.HIGHEST_PROTOCOL)
print(c)
'adj_orig': tf.sparse_placeholder(tf.float32),
'dropout': tf.placeholder_with_default(0., shape=())
# 'features_nonzero': tf.placeholder_with_default(features_nonzero, shape=()),
# 'num_nodes': tf.placeholder_with_default(num_nodes, shape=())
}
# How much to weigh positive examples (true edges) in cost print_function
# Want to weigh less-frequent classes higher, so as to prevent model output bias
# pos_weight = (num. negative samples / (num. positive samples)
pos_weight = float(adj.shape[0] * adj.shape[0] - adj.sum()) / adj.sum()
# normalize (scale) average weighted cost
norm = adj.shape[0] * adj.shape[0] / float((adj.shape[0] * adj.shape[0] - adj.sum()) * 2)
# Create VAE model
model = GCNModelVAE(placeholders, num_features, num_nodes, features_nonzero,
HIDDEN1_DIM, HIDDEN2_DIM)
opt = OptimizerVAE(preds=model.reconstructions,
labels=tf.reshape(tf.sparse_tensor_to_dense(placeholders['adj_orig'],
validate_indices=False), [-1]),
model=model, num_nodes=num_nodes,
pos_weight=pos_weight,
norm=norm,
learning_rate=LEARNING_RATE)
cost_val = []
acc_val = []
val_roc_score = []
# Initialize session
sess = tf.Session()
def gae_scores(
adj_sparse,
train_test_split,
features_matrix=None,
LEARNING_RATE = 0.01,
EPOCHS = 250,
HIDDEN1_DIM = 32,
HIDDEN2_DIM = 16,
DROPOUT = 0,
edge_score_mode="dot-product",
verbose=1,
dtype=tf.float32
):
adj_train, train_edges, train_edges_false, val_edges, val_edges_false, \
test_edges, test_edges_false = train_test_split # Unpack train-test split
if verbose >= 1:
print('GAE preprocessing...')
# start_time = time.time()
# 由于内存限制，使用CPU (隐藏 GPU)训练
os.environ['CUDA_VISIBLE_DEVICES'] = ""
# 特征转换 正常矩阵 --> 稀疏矩阵 --> 元组
# 特征元组包含： (矩阵坐标列表, 矩阵值列表, 矩阵维度)
if features_matrix is None:
x = sp.lil_matrix(np.identity(adj_sparse.shape[0]))
else:
x = sp.lil_matrix(features_matrix)
features_tuple = sparse_to_tuple(x)
features_shape = features_tuple[2]
# 获取图属性 (用于输入模型)
num_nodes = adj_sparse.shape[0] # 邻接矩阵的节点数量
num_features = features_shape[1] # 特征数量 (特征矩阵的列数)
features_nonzero = features_tuple[1].shape[0] # 特征矩阵中的非零条目数(或者矩阵值列表长度)
# 保存原始邻接矩阵 (没有对角线条目) 到后面使用
adj_orig = deepcopy(adj_sparse)
adj_orig = adj_orig - sp.dia_matrix((adj_orig.diagonal()[np.newaxis, :], [0]), shape=adj_orig.shape)
adj_orig.eliminate_zeros()
# 归一化邻接矩阵
adj_norm = preprocess_graph(adj_train)
# 添加对角线
adj_label = adj_train + sp.eye(adj_train.shape[0])
adj_label = sparse_to_tuple(adj_label)
# 定义占位符
placeholders = {
'features': tf.sparse_placeholder(tf.float32),
'adj': tf.sparse_placeholder(tf.float32),
'adj_orig': tf.sparse_placeholder(tf.float32),
'dropout': tf.placeholder_with_default(0., shape=())
}
# How much to weigh positive examples (true edges) in cost print_function
# Want to weigh less-frequent classes higher, so as to prevent model output bias
# pos_weight = (num. negative samples / (num. positive samples)
pos_weight = float(adj_sparse.shape[0] * adj_sparse.shape[0] - adj_sparse.sum()) / adj_sparse.sum()
# normalize (scale) average weighted cost
norm = adj_sparse.shape[0] * adj_sparse.shape[0] / float((adj_sparse.shape[0] * adj_sparse.shape[0] - adj_sparse.sum()) * 2)
if verbose >= 1:
print('Initializing GAE model...')
# 创建 VAE 模型
model = GCNModelVAE(placeholders, num_features, num_nodes, features_nonzero,
HIDDEN1_DIM, HIDDEN2_DIM, dtype=dtype, flatten_output=False)
opt = OptimizerVAE(preds=model.reconstructions,
labels=tf.sparse_tensor_to_dense(placeholders['adj_orig'], validate_indices=False),
# labels=placeholders['adj_orig'],
model=model, num_nodes=num_nodes,
pos_weight=pos_weight,
norm=norm,
learning_rate=LEARNING_RATE,
dtype=tf.float32)
cost_val = []
acc_val = []
val_roc_score = []
prev_embs = []
# 初始化 session
sess = tf.Session()
if verbose >= 1:
# 打印所有可训练的变量
total_parameters = 0
for variable in tf.trainable_variables():
# shape 是tf.Dimension的一个数组
shape = variable.get_shape()
print("Variable shape: ", shape)
variable_parameters = 1
for dim in shape:
print("Current dimension: ", dim)
variable_parameters *= dim.value
print("Variable params: ", variable_parameters)
total_parameters += variable_parameters
print('')
print("TOTAL TRAINABLE PARAMS: ", total_parameters)
print('Initializing TF variables...')
sess.run(tf.global_variables_initializer())
if verbose >= 1:
print('Starting GAE training!')
start_time = time.time()
# 训练模型
train_loss = []
train_acc = []
val_roc = []
val_ap = []
for epoch in range(EPOCHS):
t = time.time()
# 构造 feed dictionary
feed_dict = construct_feed_dict(adj_norm, adj_label, features_tuple, placeholders)
feed_dict.update({placeholders['dropout']: DROPOUT})
# 单一权重更新
outs = sess.run([opt.opt_op, opt.cost, opt.accuracy], feed_dict=feed_dict)
# 计算平均损失
avg_cost = outs[1]
avg_accuracy = outs[2]
# 评估预测
feed_dict.update({placeholders['dropout']: 0})
gae_emb = sess.run(model.z_mean, feed_dict=feed_dict)
prev_embs.append(gae_emb)
gae_score_matrix = np.dot(gae_emb, gae_emb.T)
roc_curr, ap_curr = get_roc_score(val_edges, val_edges_false, gae_score_matrix, apply_sigmoid=True)
val_roc_score.append(roc_curr)
# 每次迭代打印结果
# if verbose == 2:
# print(("Epoch:", '%04d' % (epoch + 1), "train_loss=", "{:.5f}".format(avg_cost),
# "train_acc=", "{:.5f}".format(avg_accuracy), "val_roc=", "{:.5f}".format(val_roc_score[-1]),
# "val_ap=", "{:.5f}".format(ap_curr),
# "time=", "{:.5f}".format(time.time() - t)))
train_loss.append(avg_cost)
train_acc.append(avg_accuracy)
val_roc.append(val_roc_score[-1])
val_ap.append(ap_curr)
# 画出训练过程损失和准确度以及验证AUC和AP
#draw_gae_training('hamster', EPOCHS, train_loss, train_acc, val_roc, val_ap)
runtime = time.time() - start_time
if verbose == 2:
print("Optimization Finished!")
# 打印最终结果
feed_dict.update({placeholders['dropout']: 0})
gae_emb = sess.run(model.z_mean, feed_dict=feed_dict)
# 点积边得分
if edge_score_mode == "dot-product":
gae_score_matrix = np.dot(gae_emb, gae_emb.T)
# runtime = time.time() - start_time
# 计算最终得分
gae_val_roc, gae_val_ap = get_roc_score(val_edges, val_edges_false, gae_score_matrix)
gae_test_roc, gae_test_ap = get_roc_score(test_edges, test_edges_false, gae_score_matrix)
# 采取自举边嵌入 (通过哈达玛积)
elif edge_score_mode == "edge-emb":
def get_edge_embeddings(edge_list):
embs = []
for edge in edge_list:
node1 = edge[0]
node2 = edge[1]
emb1 = gae_emb[node1]
emb2 = gae_emb[node2]
edge_emb = np.multiply(emb1, emb2)
embs.append(edge_emb)
embs = np.array(embs)
return embs
# 训练集 边嵌入
pos_train_edge_embs = get_edge_embeddings(train_edges)
neg_train_edge_embs = get_edge_embeddings(train_edges_false)
train_edge_embs = np.concatenate([pos_train_edge_embs, neg_train_edge_embs])
# 创建训练集 边标签： 1 = real edge, 0 = false edge
train_edge_labels = np.concatenate([np.ones(len(train_edges)), np.zeros(len(train_edges_false))])
# 验证集 边嵌入，标签
if len(val_edges) > 0 and len(val_edges_false) > 0:
pos_val_edge_embs = get_edge_embeddings(val_edges)
neg_val_edge_embs = get_edge_embeddings(val_edges_false)
val_edge_embs = np.concatenate([pos_val_edge_embs, neg_val_edge_embs])
val_edge_labels = np.concatenate([np.ones(len(val_edges)), np.zeros(len(val_edges_false))])
# 测试集 边嵌入，标签
pos_test_edge_embs = get_edge_embeddings(test_edges)
neg_test_edge_embs = get_edge_embeddings(test_edges_false)
test_edge_embs = np.concatenate([pos_test_edge_embs, neg_test_edge_embs])
# 创建验证集 边标签： 1 = real edge, 0 = false edge
test_edge_labels = np.concatenate([np.ones(len(test_edges)), np.zeros(len(test_edges_false))])
# 在训练集边嵌入上训练逻辑回归分类器
edge_classifier = LogisticRegression(random_state=0, solver='liblinear')
edge_classifier.fit(train_edge_embs, train_edge_labels)
#预测边得分: 分为1类（真实边）的概率
if len(val_edges) > 0 and len(val_edges_false) > 0:
val_preds = edge_classifier.predict_proba(val_edge_embs)[:, 1]
test_preds = edge_classifier.predict_proba(test_edge_embs)[:, 1]
#runtime = time.time() - start_time
# 计算得分
if len(val_edges) > 0 and len(val_edges_false) > 0:
gae_val_roc = roc_auc_score(val_edge_labels, val_preds)
gae_val_roc_curve = roc_curve(val_edge_labels, val_preds)
gae_val_ap = average_precision_score(val_edge_labels, val_preds)
else:
gae_val_roc = None
gae_val_roc_curve = None
gae_val_ap = None
gae_test_roc = roc_auc_score(test_edge_labels, test_preds)
gae_test_roc_curve = roc_curve(test_edge_labels, test_preds)
gae_test_pr_curve = precision_recall_curve(test_edge_labels, test_preds)
gae_test_ap = average_precision_score(test_edge_labels, test_preds)
# 记录得分
gae_scores = {}
gae_scores['test_roc'] = gae_test_roc
gae_scores['test_ap'] = gae_test_ap
gae_scores['val_roc'] = gae_val_roc
gae_scores['val_ap'] = gae_val_ap
if(edge_score_mode=="edge-emb"):
gae_scores['test_roc_curve'] = gae_test_roc_curve
gae_scores['val_roc_curve'] = gae_val_roc_curve
gae_scores['test_pr_curve'] = gae_test_pr_curve
gae_scores['val_roc_per_epoch'] = val_roc_score
gae_scores['runtime'] = runtime
return gae_scores
def gae_for(args):
print("Using {} dataset".format(args.dataset_str))
adj, features = 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.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)
lst_result = []
for i in range(10):
model = GCNModelVAE(feat_dim, args.hidden1, args.hidden2, args.dropout)
optimizer = optim.Adam(model.parameters(), lr=args.lr)
hidden_emb = None
max_roc_ap = 0
for epoch in range(args.epochs):
t = time.time()
model.train()
optimizer.zero_grad()
recovered, mu, logvar = model(features, adj_norm)
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)
roc_ap = roc_curr + ap_curr
if max_roc_ap < roc_ap:
max_roc_ap = roc_ap
h_emb_best_model = hidden_emb
print("Epoch:", '%04d' % (epoch + 1), "train_loss=",
"{:.5f}".format(cur_loss), "val_ap=",
"{:.5f}".format(ap_curr), "time=",
"{:.5f}".format(time.time() - t))
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))
print("---------------------------------------")
print("Optimization Finished!: ", i)
roc_score, ap_score = get_roc_score(h_emb_best_model, adj_orig,
test_edges, test_edges_false)
# roc_score, ap_score = get_roc_score(hidden_emb, adj_orig, test_edges, test_edges_false)
lst_result.append([i, roc_score, ap_score])
print('Test ROC score: ' + str(roc_score))
print('Test AP score: ' + str(ap_score))
lst_result = np.array(lst_result)
csv_info = np.append(
lst_result,
[["mean", np.mean(lst_result[:, 1]),
np.mean(lst_result[:, 2])]],
axis=0)
csv_info = np.append(
csv_info,
[["std", np.std(lst_result[:, 1]),
np.std(lst_result[:, 2])]],
axis=0)
t = int(time.time())
folder = Path(os.path.join(os.getcwd(), "csv"))
csv_name = "{}_{}_{}_{}_{}.csv".format(args.dataset_str, args.epochs,
args.hidden1, args.hidden2, t)
df = pd.DataFrame(csv_info, columns=['run', 'ROC', "AP"])
df.to_csv(os.path.join(folder, csv_name))
def gcn_multilayer(self):
"""Neural embedding of a multilayer network"""
all_nodes = self.get_all_nodes()
tmp_fname = pjoin(self.out_dir, 'tmp.emb')
for net_name, net in self.nets.items():
self.log.info('Run GCN For Net: %s' % net_name)
# =============================================================
adjacency_matrix = nx.adjacency_matrix(net)
adjacency_matrix = adjacency_matrix.todense()
nodes_count = adjacency_matrix.shape[0]
adj = adjacency_matrix
features = sp.identity(nodes_count)
adj = sp.csr_matrix(adj)
# ----------------myCode-----------------------------------
# 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()
# tst_actual_matrix = adj.toarray()
adj_train, train_edges, val_edges, val_edges_false, test_edges, test_edges_false = mask_test_edges(adj)
adj = adj_train
# -----------------------------myCode-------------------------
# if FLAGS.features == 0:
# features = sp.identity(features.shape[0]) # featureless
# -----------------------------myCode-------------------------
# Some pre processing
adj_norm = preprocess_graph(adj)
# Define placeholders
placeholders = {
'features': tf.sparse_placeholder(tf.float32),
'adj': tf.sparse_placeholder(tf.float32),
'adj_orig': tf.sparse_placeholder(tf.float32),
'dropout': tf.placeholder_with_default(0., shape=())
}
num_nodes = adj.shape[0]
features = sparse_to_tuple(features.tocoo())
num_features = features[2][1]
features_nonzero = features[1].shape[0]
# Create model
model = None
if self.model_str == 'gcn_ae':
model = GCNModelAE(placeholders, num_features, features_nonzero, self.hidden1, self.hidden2)
elif self.model_str == 'gcn_vae':
model = GCNModelVAE(placeholders, num_features, num_nodes, features_nonzero, self.hidden1, self.hidden2)
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)
# Optimizer
with tf.name_scope('optimizer'):
if self.model_str == 'gcn_ae':
opt = OptimizerAE(preds=model.reconstructions,
labels=tf.reshape(tf.sparse_tensor_to_dense(placeholders['adj_orig'],
validate_indices=False), [-1]),
pos_weight=pos_weight,
norm=norm)
elif self.model_str == 'gcn_vae':
opt = OptimizerVAE(preds=model.reconstructions,
labels=tf.reshape(tf.sparse_tensor_to_dense(placeholders['adj_orig'],
validate_indices=False), [-1]),
model=model, num_nodes=num_nodes,
pos_weight=pos_weight,
norm=norm)
# Initialize session
sess = tf.Session()
sess.run(tf.global_variables_initializer())
cost_val = []
acc_val = []
def get_roc_score(edges_pos, edges_neg, emb=None):
if emb is None:
feed_dict.update({placeholders['dropout']: 0})
emb = sess.run(model.z_mean, feed_dict=feed_dict)
def sigmoid(x):
return 1 / (1 + np.exp(-x))
# Predict on test set of edges
adj_rec = np.dot(emb, emb.T)
preds = []
pos = []
for e in edges_pos:
preds.append(sigmoid(adj_rec[e[0], e[1]]))
pos.append(adj_orig[e[0], e[1]])
preds_neg = []
neg = []
for e in edges_neg:
preds_neg.append(sigmoid(adj_rec[e[0], e[1]]))
neg.append(adj_orig[e[0], e[1]])
preds_all = np.hstack([preds, preds_neg])
labels_all = np.hstack([np.ones(len(preds)), np.zeros(len(preds_neg))])
roc_score = roc_auc_score(labels_all, preds_all)
ap_score = average_precision_score(labels_all, preds_all)
return roc_score, ap_score
cost_val = []
acc_val = []
val_roc_score = []
adj_label = adj_train + sp.eye(adj_train.shape[0])
adj_label = sparse_to_tuple(adj_label)
# Train model
# for epoch in range(FLAGS.epochs):
# epochs = 10
dropout = 0
for epoch in range(self.n_iter):
self.log.info('Iteration: %d' % epoch)
t = time.time()
# Construct feed dictionary
feed_dict = construct_feed_dict(adj_norm, adj_label, features, placeholders)
# feed_dict.update({placeholders['dropout']: FLAGS.dropout})
# -----------myCode------------
feed_dict.update({placeholders['dropout']: dropout})
# -----------myCode------------
# Run single weight update
outs = sess.run([opt.opt_op, opt.cost, opt.accuracy], feed_dict=feed_dict)
# Compute average loss
avg_cost = outs[1]
avg_accuracy = outs[2]
roc_curr, ap_curr = get_roc_score(val_edges, val_edges_false)
val_roc_score.append(roc_curr)
print("Epoch:", '%04d' % (epoch + 1), "train_loss=", "{:.5f}".format(avg_cost),
"train_acc=", "{:.5f}".format(avg_accuracy), "val_roc=", "{:.5f}".format(val_roc_score[-1]),
"val_ap=", "{:.5f}".format(ap_curr),
"time=", "{:.5f}".format(time.time() - t))
print("Optimization Finished!")
roc_score, ap_score = get_roc_score(test_edges, test_edges_false)
print('Test ROC score: ' + str(roc_score))
print('Test AP score: ' + str(ap_score))
# ------vector generation -----------------------------
vectors = sess.run(model.embeddings, feed_dict=feed_dict)
fname = self.out_dir + net_name +'vectors.txt'
# with open(fname, 'a+') as fout:
# for line in np.array(vectors):
# fout.write(line + "\n")
np.savetxt(fname, np.array(vectors), fmt="%s", delimiter=' ')
self.log.info('Saving vectors: %s' % fname)
# ==============================================================
self.log.info('after exec gcn : %s' % net_name)
self.log.info('Done!')
def run(self):
if self.file_expr == '':
# text-image-code combination
n_by_n, x_train, y_train, train_mask, val_mask, test_mask, idx_supernodes, label_encoder = graph_generator.load_combo(
self.labels_dict)
else:
n_by_n, x_train, y_train, train_mask, val_mask, test_mask, idx_supernodes, label_encoder = graph_generator.load_data(
self.labels_dict,
self.file_expr,
min_valid_triples=self.min_valid_triples,
sep=self.file_sep,
select_rels=self.select_rels)
self.idx_supernodes = idx_supernodes
adj = nx.adjacency_matrix(nx.from_scipy_sparse_matrix(
n_by_n)) #nx.adjacency_matrix(nx.from_numpy_array(n_by_n))
features = scipy.sparse.csr.csr_matrix(x_train)
# 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()
self.adj_orig = adj_orig
adj_train, train_edges, val_edges, val_edges_false, test_edges, test_edges_false = mask_test_edges2(
adj)
adj = adj_train
# Some preprocessing
adj_norm = preprocess_graph(adj)
num_nodes = adj.shape[0]
if not self.use_features:
features = sp.identity(features.shape[0]) # featureless
features = sparse_to_tuple(features.tocoo())
num_features = features[2][1]
features_nonzero = features[1].shape[0]
# Create model
if model_str == 'gcn_ae':
self.model = GCNModelAE(self.placeholders, num_features,
features_nonzero)
elif model_str == 'gcn_vae':
self.model = GCNModelVAE(self.placeholders, num_features,
num_nodes, features_nonzero)
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)
# Optimizer
with tf.name_scope('optimizer'):
if model_str == 'gcn_ae':
opt = OptimizerAE(preds=self.model.reconstructions,
labels=tf.reshape(
tf.sparse_tensor_to_dense(
self.placeholders['adj_orig'],
validate_indices=False), [-1]),
pos_weight=pos_weight,
norm=norm)
elif model_str == 'gcn_vae':
opt = OptimizerVAE(preds=self.model.reconstructions,
labels=tf.reshape(
tf.sparse_tensor_to_dense(
self.placeholders['adj_orig'],
validate_indices=False), [-1]),
model=self.model,
num_nodes=num_nodes,
pos_weight=pos_weight,
norm=norm)
# Initialize session
self.sess = tf.Session()
self.sess.run(tf.global_variables_initializer())
val_roc_score = []
adj_label = adj_train + sp.eye(adj_train.shape[0])
adj_label = sparse_to_tuple(adj_label)
#import datetime
#log_dir="logs/gae/" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
# Train model
for epoch in range(self.epochs): #FLAGS.epochs):
t = time.time()
# Construct feed dictionary
self.feed_dict = construct_feed_dict(adj_norm, adj_label, features,
self.placeholders)
self.feed_dict.update(
{self.placeholders['dropout']:
self.dropout_rate}) # FLAGS.dropout})
# Run single weight update
outs = self.sess.run([opt.opt_op, opt.cost, opt.accuracy],
feed_dict=self.feed_dict)
# Compute average loss
avg_cost = outs[1]
avg_accuracy = outs[2]
roc_curr, ap_curr = self.get_roc_score(val_edges, val_edges_false)
val_roc_score.append(roc_curr)
# tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir, histogram_freq=1)
print("Epoch:", '%04d' % (epoch + 1), "train_loss=",
"{:.5f}".format(avg_cost), "train_acc=",
"{:.5f}".format(avg_accuracy), "val_roc=",
"{:.5f}".format(val_roc_score[-1]), "val_ap=",
"{:.5f}".format(ap_curr), "time=",
"{:.5f}".format(time.time() - t))
print("Optimization Finished!")
roc_score, ap_score = self.get_roc_score(test_edges, test_edges_false)
print('Test ROC score: ' + str(roc_score))
print('Test AP score: ' + str(ap_score))
[supernodes, supernodes_embeddings,
supernodes_labels] = self.get_embeddings(y_train, label_encoder)
self.supernodes = [
supernodes, supernodes_embeddings, supernodes_labels
]
def main(args):
""" Compute embeddings using GAE/VGAE. """
# Load edgelist
oneIndx = False
E = np.loadtxt(args.inputgraph, delimiter=args.delimiter, dtype=int)
if np.min(E) == 1:
oneIndx = True
E -= 1
# Create an unweighted graph
G = nx.Graph()
G.add_edges_from(E[:, :2])
# Get adj matrix of the graph
tr_A = nx.adjacency_matrix(G, weight=None)
num_nodes = tr_A.shape[0]
# Set main diag to 1s and normalize (algorithm requirement)
adj_norm = preprocess_graph(tr_A)
# Define placeholders
placeholders = {
'features': tf.sparse_placeholder(tf.float32),
'adj': tf.sparse_placeholder(tf.float32),
'adj_orig': tf.sparse_placeholder(tf.float32),
'dropout': tf.placeholder_with_default(0., shape=())
}
# Create empty feature matrix
features = sp.identity(num_nodes) # featureless
features = sparse_to_tuple(features.tocoo())
num_features = features[2][1]
features_nonzero = features[1].shape[0]
# Create model
model = None
if args.model == 'gcn_ae':
model = GCNModelAE(placeholders, num_features, features_nonzero)
elif args.model == 'gcn_vae':
model = GCNModelVAE(placeholders, num_features, num_nodes,
features_nonzero)
pos_weight = float(tr_A.shape[0] * tr_A.shape[0] - tr_A.sum()) / tr_A.sum()
norm = tr_A.shape[0] * tr_A.shape[0] / float(
(tr_A.shape[0] * tr_A.shape[0] - tr_A.sum()) * 2)
# Optimizer
with tf.name_scope('optimizer'):
if args.model == 'gcn_ae':
opt = OptimizerAE(preds=model.reconstructions,
labels=tf.reshape(
tf.sparse_tensor_to_dense(
placeholders['adj_orig'],
validate_indices=False), [-1]),
pos_weight=pos_weight,
norm=norm)
elif args.model == 'gcn_vae':
opt = OptimizerVAE(preds=model.reconstructions,
labels=tf.reshape(
tf.sparse_tensor_to_dense(
placeholders['adj_orig'],
validate_indices=False), [-1]),
model=model,
num_nodes=num_nodes,
pos_weight=pos_weight,
norm=norm)
# Initialize session
sess = tf.Session()
sess.run(tf.global_variables_initializer())
adj_label = tr_A + sp.eye(tr_A.shape[0])
adj_label = sparse_to_tuple(adj_label)
# Train model
for epoch in range(FLAGS.epochs):
# Construct feed dictionary
feed_dict = construct_feed_dict(adj_norm, adj_label, features,
placeholders)
feed_dict.update({placeholders['dropout']: FLAGS.dropout})
# Run single weight update
outs = sess.run([opt.opt_op, opt.cost, opt.accuracy],
feed_dict=feed_dict)
print("Epoch:", '%04d' % (epoch + 1), "train_loss=",
"{:.5f}".format(outs[1]), "train_acc=", "{:.5f}".format(outs[2]))
# Compute predictions
feed_dict.update({placeholders['dropout']: 0})
emb = sess.run(model.z_mean, feed_dict=feed_dict)
def sigmoid(x):
return 1 / (1 + np.exp(-x))
# Node similarities
adj_rec = np.dot(emb, emb.T)
start = time.time()
# Read the train edges and compute similarity
if args.tr_e is not None:
train_edges = np.loadtxt(args.tr_e,
delimiter=args.delimiter,
dtype=int)
if oneIndx:
train_edges -= 1
scores = list()
for src, dst in train_edges:
scores.append(sigmoid(adj_rec[src, dst]))
np.savetxt(args.tr_pred, scores, delimiter=args.delimiter)
# Read the test edges and run predictions
if args.te_e is not None:
test_edges = np.loadtxt(args.te_e,
delimiter=args.delimiter,
dtype=int)
if oneIndx:
test_edges -= 1
scores = list()
for src, dst in test_edges:
scores.append(sigmoid(adj_rec[src, dst]))
np.savetxt(args.te_pred, scores, delimiter=args.delimiter)
# If no edge lists provided to predict links, then just store the embeddings
else:
np.savetxt(args.output, emb, delimiter=args.delimiter)
print('Prediction time: {}'.format(time.time() - start))
def fit(self, adj, features, labels):
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 = gen_train_edges(adj)
adj = adj_train
# Some preprocessing
adj_norm = preprocess_graph(adj)
num_nodes = adj.shape[0]
input_feature_dim = features.shape[1]
features = normalize_vectors(features)
# Define placeholders
self.placeholders = {
'features':
tf.compat.v1.placeholder(tf.float32,
shape=(None, input_feature_dim)),
# 'features': tf.compat.v1.sparse_placeholder(tf.float32),
'adj':
tf.compat.v1.sparse_placeholder(tf.float32),
'adj_orig':
tf.compat.v1.sparse_placeholder(tf.float32),
'dropout':
tf.compat.v1.placeholder_with_default(0., shape=())
}
if self.model_type == 'gcn_ae':
self.model = GCNModelAE(self.placeholders, input_feature_dim)
elif self.model_type == 'gcn_vae':
self.model = GCNModelVAE(self.placeholders, input_feature_dim,
num_nodes)
pos_weight = float(adj.shape[0] * adj.shape[0] -
adj.sum()) / adj.sum() # negative edges/pos edges
# print('positive edge weight', pos_weight)
norm = adj.shape[0] * adj.shape[0] / float(
(adj.shape[0] * adj.shape[0] - adj.nnz) * 2)
# Optimizer
with tf.compat.v1.name_scope('optimizer'):
if self.model_type == 'gcn_ae':
opt = OptimizerAE(preds=self.model.reconstructions,
labels=tf.reshape(
tf.sparse.to_dense(
self.placeholders['adj_orig'],
validate_indices=False), [-1]),
pos_weight=pos_weight,
norm=norm)
elif self.model_type == 'gcn_vae':
opt = OptimizerVAE(preds=self.model.reconstructions,
labels=tf.reshape(
tf.sparse.to_dense(
self.placeholders['adj_orig'],
validate_indices=False), [-1]),
model=self.model,
num_nodes=num_nodes,
pos_weight=pos_weight,
norm=norm)
# Initialize session
self.sess = tf.compat.v1.Session()
self.sess.run(tf.compat.v1.global_variables_initializer())
adj_label = adj_train + sp.eye(adj_train.shape[0])
adj_label = sparse_to_tuple(adj_label)
# Train model
for epoch in range(FLAGS.epochs):
t = time.time()
# Construct feed dictionary
self.feed_dict = construct_feed_dict(adj_norm, adj_label, features,
self.placeholders)
self.feed_dict.update(
{self.placeholders['dropout']: FLAGS.dropout})
# Run single weight update
outs = self.sess.run([opt.opt_op, opt.cost, opt.accuracy],
feed_dict=self.feed_dict)
# Compute average loss
avg_cost = outs[1]
avg_accuracy = outs[2]
def gae_scores(
adj_sparse,
train_test_split,
features_matrix=None,
LEARNING_RATE = 0.01,
EPOCHS = 200,
HIDDEN1_DIM = 32,
HIDDEN2_DIM = 16,
DROPOUT = 0,
edge_score_mode="dot-product",
verbose=1,
dtype=tf.float32
):
adj_train, train_edges, train_edges_false, val_edges, val_edges_false, \
test_edges, test_edges_false = train_test_split # Unpack train-test split
if verbose >= 1:
print 'GAE preprocessing...'
start_time = time.time()
# Train on CPU (hide GPU) due to memory constraints
os.environ['CUDA_VISIBLE_DEVICES'] = ""
# Convert features from normal matrix --> sparse matrix --> tuple
# features_tuple contains: (list of matrix coordinates, list of values, matrix dimensions)
if features_matrix is None:
x = sp.lil_matrix(np.identity(adj_sparse.shape[0]))
else:
x = sp.lil_matrix(features_matrix)
features_tuple = sparse_to_tuple(x)
features_shape = features_tuple[2]
# Get graph attributes (to feed into model)
num_nodes = adj_sparse.shape[0] # number of nodes in adjacency matrix
num_features = features_shape[1] # number of features (columsn of features matrix)
features_nonzero = features_tuple[1].shape[0] # number of non-zero entries in features matrix (or length of values list)
# Store original adjacency matrix (without diagonal entries) for later
adj_orig = deepcopy(adj_sparse)
adj_orig = adj_orig - sp.dia_matrix((adj_orig.diagonal()[np.newaxis, :], [0]), shape=adj_orig.shape)
adj_orig.eliminate_zeros()
# Normalize adjacency matrix
adj_norm = preprocess_graph(adj_train)
# Add in diagonals
adj_label = adj_train + sp.eye(adj_train.shape[0])
adj_label = sparse_to_tuple(adj_label)
# Define placeholders
placeholders = { # TODO: try making these dense from the get-go
'features': tf.sparse_placeholder(tf.float16),
'adj': tf.sparse_placeholder(tf.float16),
'adj_orig': tf.sparse_placeholder(tf.float16),
'dropout': tf.placeholder_with_default(0., shape=())
}
# How much to weigh positive examples (true edges) in cost print_function
# Want to weigh less-frequent classes higher, so as to prevent model output bias
# pos_weight = (num. negative samples / (num. positive samples)
pos_weight = float(adj_sparse.shape[0] * adj_sparse.shape[0] - adj_sparse.sum()) / adj_sparse.sum()
# normalize (scale) average weighted cost
norm = adj_sparse.shape[0] * adj_sparse.shape[0] / float((adj_sparse.shape[0] * adj_sparse.shape[0] - adj_sparse.sum()) * 2)
if verbose >= 1:
print 'Initializing GAE model...'
# Create VAE model
model = GCNModelVAE(placeholders, num_features, num_nodes, features_nonzero,
HIDDEN1_DIM, HIDDEN2_DIM, dtype=dtype, flatten_output=False)
opt = OptimizerVAE(preds=model.reconstructions,
labels=tf.sparse_tensor_to_dense(placeholders['adj_orig'], validate_indices=False),
# labels=placeholders['adj_orig'],
model=model, num_nodes=num_nodes,
pos_weight=pos_weight,
norm=norm,
learning_rate=LEARNING_RATE,
dtype=tf.float16)
cost_val = []
acc_val = []
val_roc_score = []
prev_embs = []
# Initialize session
sess = tf.Session()
if verbose >= 1:
# Print total # trainable variables
total_parameters = 0
for variable in tf.trainable_variables():
# shape is an array of tf.Dimension
shape = variable.get_shape()
print "Variable shape: ", shape
variable_parameters = 1
for dim in shape:
print "Current dimension: ", dim
variable_parameters *= dim.value
print "Variable params: ", variable_parameters
total_parameters += variable_parameters
print ''
print "TOTAL TRAINABLE PARAMS: ", total_parameters
print 'Initializing TF variables...'
sess.run(tf.global_variables_initializer())
if verbose >= 1:
print 'Starting GAE training!'
# Train model
for epoch in range(EPOCHS):
t = time.time()
# Construct feed dictionary
feed_dict = construct_feed_dict(adj_norm, adj_label, features_tuple, placeholders)
feed_dict.update({placeholders['dropout']: DROPOUT})
# Run single weight update
outs = sess.run([opt.opt_op, opt.cost, opt.accuracy], feed_dict=feed_dict)
# Compute average loss
avg_cost = outs[1]
avg_accuracy = outs[2]
# Evaluate predictions
feed_dict.update({placeholders['dropout']: 0})
gae_emb = sess.run(model.z_mean, feed_dict=feed_dict)
prev_embs.append(gae_emb)
gae_score_matrix = np.dot(gae_emb, gae_emb.T)
# # TODO: remove this (debugging)
# if not np.isfinite(gae_score_matrix).all():
# print 'Found non-finite value in GAE score matrix! Epoch: {}'.format(epoch)
# with open('numpy-nan-debugging.pkl', 'wb') as f:
# dump_info = {}
# dump_info['gae_emb'] = gae_emb
# dump_info['epoch'] = epoch
# dump_info['gae_score_matrix'] = gae_score_matrix
# dump_info['adj_norm'] = adj_norm
# dump_info['adj_label'] = adj_label
# dump_info['features_tuple'] = features_tuple
# # dump_info['feed_dict'] = feed_dict
# dump_info['prev_embs'] = prev_embs
# pickle.dump(dump_info, f, protocol=2)
# # END TODO
roc_curr, ap_curr = get_roc_score(val_edges, val_edges_false, gae_score_matrix, apply_sigmoid=True)
val_roc_score.append(roc_curr)
# Print results for this epoch
if verbose == 2:
print("Epoch:", '%04d' % (epoch + 1), "train_loss=", "{:.5f}".format(avg_cost),
"train_acc=", "{:.5f}".format(avg_accuracy), "val_roc=", "{:.5f}".format(val_roc_score[-1]),
"val_ap=", "{:.5f}".format(ap_curr),
"time=", "{:.5f}".format(time.time() - t))
if verbose == 2:
print("Optimization Finished!")
# Print final results
feed_dict.update({placeholders['dropout']: 0})
gae_emb = sess.run(model.z_mean, feed_dict=feed_dict)
# Dot product edge scores (default)
if edge_score_mode == "dot-product":
gae_score_matrix = np.dot(gae_emb, gae_emb.T)
runtime = time.time() - start_time
# Calculate final scores
gae_val_roc, gae_val_ap = get_roc_score(val_edges, val_edges_false, gae_score_matrix)
gae_test_roc, gae_test_ap = get_roc_score(test_edges, test_edges_false, gae_score_matrix)
# Take bootstrapped edge embeddings (via hadamard product)
elif edge_score_mode == "edge-emb":
def get_edge_embeddings(edge_list):
embs = []
for edge in edge_list:
node1 = edge[0]
node2 = edge[1]
emb1 = gae_emb[node1]
emb2 = gae_emb[node2]
edge_emb = np.multiply(emb1, emb2)
embs.append(edge_emb)
embs = np.array(embs)
return embs
# Train-set edge embeddings
pos_train_edge_embs = get_edge_embeddings(train_edges)
neg_train_edge_embs = get_edge_embeddings(train_edges_false)
train_edge_embs = np.concatenate([pos_train_edge_embs, neg_train_edge_embs])
# Create train-set edge labels: 1 = real edge, 0 = false edge
train_edge_labels = np.concatenate([np.ones(len(train_edges)), np.zeros(len(train_edges_false))])
# Val-set edge embeddings, labels
if len(val_edges) > 0 and len(val_edges_false) > 0:
pos_val_edge_embs = get_edge_embeddings(val_edges)
neg_val_edge_embs = get_edge_embeddings(val_edges_false)
val_edge_embs = np.concatenate([pos_val_edge_embs, neg_val_edge_embs])
val_edge_labels = np.concatenate([np.ones(len(val_edges)), np.zeros(len(val_edges_false))])
# Test-set edge embeddings, labels
pos_test_edge_embs = get_edge_embeddings(test_edges)
neg_test_edge_embs = get_edge_embeddings(test_edges_false)
test_edge_embs = np.concatenate([pos_test_edge_embs, neg_test_edge_embs])
# Create val-set edge labels: 1 = real edge, 0 = false edge
test_edge_labels = np.concatenate([np.ones(len(test_edges)), np.zeros(len(test_edges_false))])
# Train logistic regression classifier on train-set edge embeddings
edge_classifier = LogisticRegression(random_state=0)
edge_classifier.fit(train_edge_embs, train_edge_labels)
# Predicted edge scores: probability of being of class "1" (real edge)
if len(val_edges) > 0 and len(val_edges_false) > 0:
val_preds = edge_classifier.predict_proba(val_edge_embs)[:, 1]
test_preds = edge_classifier.predict_proba(test_edge_embs)[:, 1]
runtime = time.time() - start_time
# Calculate scores
if len(val_edges) > 0 and len(val_edges_false) > 0:
gae_val_roc = roc_auc_score(val_edge_labels, val_preds)
# gae_val_roc_curve = roc_curve(val_edge_labels, val_preds)
gae_val_ap = average_precision_score(val_edge_labels, val_preds)
else:
gae_val_roc = None
gae_val_roc_curve = None
gae_val_ap = None
gae_test_roc = roc_auc_score(test_edge_labels, test_preds)
# gae_test_roc_curve = roc_curve(test_edge_labels, test_preds)
gae_test_ap = average_precision_score(test_edge_labels, test_preds)
# Record scores
gae_scores = {}
gae_scores['test_roc'] = gae_test_roc
# gae_scores['test_roc_curve'] = gae_test_roc_curve
gae_scores['test_ap'] = gae_test_ap
gae_scores['val_roc'] = gae_val_roc
# gae_scores['val_roc_curve'] = gae_val_roc_curve
gae_scores['val_ap'] = gae_val_ap
gae_scores['val_roc_per_epoch'] = val_roc_score
gae_scores['runtime'] = runtime
return gae_scores
def GAEembedding(z, adj, args):
'''
GAE embedding for clustering
Param:
z,adj
Return:
Embedding from graph
'''
# true_labels = np.asarray(true_labels)
# args.model = 'gcn_vae'
# args.dw = 0
# args.epochs = 200
# args.hidden1 = 32
# args.hidden2 = 16
# args.lr = 0.01
# args.dropout = 0.
# args.dataset_sr = 'cora'
# args.walk_length = 5
# args.window_size = 3
# args.number_walks = 5
# args.full_number_walks =0
# args.lr_dw = 0.001
# args.context = 0
# args.ns = 1
# args.n_clusters = 11
# args.plot = 0
# featrues from z
# Louvain
features = z
# features = torch.DoubleTensor(features)
features = torch.FloatTensor(features)
# Old implementation
# 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.GAEmodel == 'gcn_vae':
model = GCNModelVAE(feat_dim, args.GAEhidden1, args.GAEhidden2,
args.GAEdropout)
else:
model = GCNModelAE(feat_dim, args.GAEhidden1, args.GAEhidden2,
args.GAEdropout)
if args.precisionModel == 'Double':
model = model.double()
optimizer = optim.Adam(model.parameters(), lr=args.GAElr)
# 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.GAEepochs)):
t = time.time()
# mem=resource.getrusage(resource.RUSAGE_SELF).ru_maxrss
# print('Mem consumption before training: '+str(mem))
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()
# TODO, this is prediction
# roc_curr, ap_curr = get_roc_score(hidden_emb, adj_orig, val_edges, val_edges_false)
ap_curr = 0
# 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.GAEplot == 1:
# cm.plotClusters(tqdm, hidden_emb, true_labels)
return hidden_emb
'features': tf.sparse_placeholder(tf.float32),
'adj': tf.sparse_placeholder(tf.float32),
'adj_orig': tf.sparse_placeholder(tf.float32),
'dropout': tf.placeholder_with_default(0., shape=())
}
num_nodes = adj.shape[0] #网络中结点的个数
features = sparse_to_tuple(features.tocoo(
)) #特征转化为稀疏矩阵存储,存成tuple的形式，第一行存一对对关系，第二行存每对关系的值，第三行存行列数
num_features = features[2][1] #特征的维度
features_nonzero = features[1].shape[0] #有特征的节点个数
# Create model
model = None
model = GCNModelVAE(placeholders, num_features, num_nodes,
features_nonzero)
pos_weight = float(adj.shape[0] * adj.shape[0] -
adj.sum()) / adj.sum() #负样本与正样本的比例
print('adj.shape', adj.shape[0], adj.sum())
norm = adj.shape[0] * adj.shape[0] / float(
(adj.shape[0] * adj.shape[0] - adj.sum()) *
2) # shape[0] = 913, adj.sum() = 10734
# Optimizer
opt = OptimizerVAE(preds=model.reconstructions,
labels=tf.reshape(
tf.sparse_tensor_to_dense(
placeholders['adj_orig'],
validate_indices=False), [-1]),
model=model,
def GAEembedding(z, adj, args):
'''
GAE embedding for clustering
Param:
z,adj
Return:
Embedding from graph
'''
# featrues from z
# Louvain
features = z
# features = torch.DoubleTensor(features)
features = torch.FloatTensor(features)
# Old implementation
# 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.GAEmodel == 'gcn_vae':
model = GCNModelVAE(feat_dim, args.GAEhidden1, args.GAEhidden2,
args.GAEdropout)
else:
model = GCNModelAE(feat_dim, args.GAEhidden1, args.GAEhidden2,
args.GAEdropout)
if args.precisionModel == 'Double':
model = model.double()
optimizer = optim.Adam(model.parameters(), lr=args.GAElr)
hidden_emb = None
for epoch in tqdm(range(args.GAEepochs)):
t = time.time()
# mem=resource.getrusage(resource.RUSAGE_SELF).ru_maxrss
# print('Mem consumption before training: '+str(mem))
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()
# TODO, this is prediction
# roc_curr, ap_curr = get_roc_score(hidden_emb, adj_orig, val_edges, val_edges_false)
ap_curr = 0
tqdm.write(
"Epoch: {}, train_loss_gae={:.5f}, val_ap={:.5f}, time={:.5f}".
format(epoch + 1, cur_loss, ap_curr,
time.time() - t))
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))
return hidden_emb
