def __init__(self, params):
self.num_factors = params.num_factors
self.num_users = params.num_users
self.num_items = params.num_items
self.num_doms = params.num_doms
self.reg_lam = params.reg_lam
self.reg_w = params.reg_w
self.reg_b = params.reg_b
self.initializer = params.initializer
self.params = params
self.num_nodes = params.num_nodes
self.feature_dim = params.feature_dim
self.social_attr_dim = params.social_attr_dim
print('feature dim, social_attr_dim: ', self.feature_dim,
self.social_attr_dim)
self.model = SpGAT()
self.biases = process.preprocess_adj_bias(params.adjacency_matrix)
self.user_item_features = params.user_item_embed_mat #[np.newaxis]
self.social_features = params.social_embed_mat #[np.newaxis]
self.out_size = params.num_factors
self.hid_units = params.hid_units
self.n_heads = params.n_heads
self.attn_keep = params.attn_keep
self.ffd_keep = params.ffd_keep
self.proj_keep = params.proj_keep
self.residual = False
self.nonlinearity = tf.nn.elu
def main(args):
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
dataset = args.dataset
# training params
batch_size = 1
nb_epochs = 100000
patience = 100
lr = args.lr
l2_coef = args.l2
hid_units = [args.units]
n_heads = [1, 1] # layers
drop_out = args.drop
residual = False
nonlinearity = tf.nn.elu
model = SpHGAT
print('Dataset: ' + dataset)
print('----- Opt. hyperparams -----')
print('lr: ' + str(lr))
print('l2_coef: ' + str(l2_coef))
sparse = True
adj, features, y_train, y_val, y_test, train_mask, val_mask, test_mask = process.load_data(dataset)
features, spars = process.preprocess_features(features)
nb_nodes = features.shape[0]
ft_size = features.shape[1]
nb_classes = y_train.shape[1]
features = features[np.newaxis]
y_train = y_train[np.newaxis]
y_val = y_val[np.newaxis]
y_test = y_test[np.newaxis]
train_mask = train_mask[np.newaxis]
val_mask = val_mask[np.newaxis]
test_mask = test_mask[np.newaxis]
if sparse:
biases = process.preprocess_adj_bias(adj)
else:
adj = adj.todense()
adj = adj[np.newaxis]
biases = process.adj_to_bias(adj, [nb_nodes], nhood=1)
with tf.Graph().as_default():
with tf.name_scope('input'):
ftr_in = tf.placeholder(dtype=tf.float32, shape=(batch_size, nb_nodes, ft_size))
if sparse:
bias_in = tf.sparse_placeholder(dtype=tf.float32)
else:
bias_in = tf.placeholder(dtype=tf.float32, shape=(batch_size, nb_nodes, nb_nodes))
lbl_in = tf.placeholder(dtype=tf.int32, shape=(batch_size, nb_nodes, nb_classes))
msk_in = tf.placeholder(dtype=tf.int32, shape=(batch_size, nb_nodes))
attn_drop = tf.placeholder(dtype=tf.float32, shape=())
ffd_drop = tf.placeholder(dtype=tf.float32, shape=())
is_train = tf.placeholder(dtype=tf.bool, shape=())
logits = model.inference(ftr_in, nb_classes, nb_nodes, is_train,
attn_drop, ffd_drop,
bias_mat=bias_in,
hid_units=hid_units, n_heads=n_heads,
activation=nonlinearity)
log_resh = tf.reshape(logits, [-1, nb_classes])
lab_resh = tf.reshape(lbl_in, [-1, nb_classes])
msk_resh = tf.reshape(msk_in, [-1])
loss = model.masked_softmax_cross_entropy(log_resh, lab_resh, msk_resh)
accuracy = model.masked_accuracy(log_resh, lab_resh, msk_resh)
pred_all = tf.cast(tf.argmax(log_resh, 1), dtype=tf.int32)
real_all = tf.cast(tf.argmax(lab_resh, 1), dtype=tf.int32)
train_op = model.my_training(loss, lr, l2_coef)
init_op = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer())
vlss_mn = np.inf
vacc_mx = 0.0
tlss_mn = 0.0
tacc_mx = 0.0
curr_step = 0
with tf.Session(config=config) as sess:
sess.run(init_op)
train_loss_avg = 0
train_acc_avg = 0
val_loss_avg = 0
val_acc_avg = 0
for epoch in range(nb_epochs):
tr_step = 0
tr_size = features.shape[0]
while tr_step * batch_size < tr_size:
if sparse:
bbias = biases
else:
bbias = biases[tr_step*batch_size:(tr_step+1)*batch_size]
_, loss_value_tr, acc_tr = sess.run([train_op, loss, accuracy],
feed_dict={
ftr_in: features[tr_step*batch_size:(tr_step+1)*batch_size],
bias_in: bbias,
lbl_in: y_train[tr_step*batch_size:(tr_step+1)*batch_size],
msk_in: train_mask[tr_step*batch_size:(tr_step+1)*batch_size],
is_train: True,
attn_drop: drop_out, ffd_drop: drop_out})
train_loss_avg += loss_value_tr
train_acc_avg += acc_tr
tr_step += 1
vl_step = 0
vl_size = features.shape[0]
while vl_step * batch_size < vl_size:
if sparse:
bbias = biases
else:
bbias = biases[vl_step*batch_size:(vl_step+1)*batch_size]
loss_value_vl, acc_vl = sess.run([loss, accuracy],
feed_dict={
ftr_in: features[vl_step*batch_size:(vl_step+1)*batch_size],
bias_in: bbias,
lbl_in: y_val[vl_step*batch_size:(vl_step+1)*batch_size],
msk_in: val_mask[vl_step*batch_size:(vl_step+1)*batch_size],
is_train: False,
attn_drop: 0.0, ffd_drop: 0.0})
val_loss_avg += loss_value_vl
val_acc_avg += acc_vl
vl_step += 1
ts_size = features.shape[0]
ts_step = 0
ts_loss = 0.0
ts_acc = 0.0
print(epoch, 'Training: loss = %.5f, acc = %.5f | Val: loss = %.5f, acc = %.5f' %
(train_loss_avg/tr_step, train_acc_avg/tr_step,
val_loss_avg/vl_step, val_acc_avg/vl_step))
if val_acc_avg/vl_step >= vacc_mx or val_loss_avg/vl_step <= vlss_mn:
vacc_mx = np.max((val_acc_avg/vl_step, vacc_mx))
vlss_mn = np.min((val_loss_avg/vl_step, vlss_mn))
curr_step = 0
while ts_step * batch_size < ts_size:
if sparse:
bbias = biases
else:
bbias = biases[ts_step * batch_size:(ts_step + 1) * batch_size]
loss_value_ts, acc_ts = sess.run(
[loss, accuracy],
feed_dict={
ftr_in: features[ts_step * batch_size:(ts_step + 1) * batch_size],
bias_in: bbias,
lbl_in: y_test[ts_step * batch_size:(ts_step + 1) * batch_size],
msk_in: test_mask[ts_step * batch_size:(ts_step + 1) * batch_size],
is_train: False,
attn_drop: 0.0, ffd_drop: 0.0})
ts_loss += loss_value_ts
ts_acc += acc_ts
ts_step += 1
tlss_mn = ts_loss / ts_step
tacc_mx = ts_acc / ts_step
else:
curr_step += 1
if curr_step == patience:
print('Early stop! Min validation loss: ', vlss_mn, ', Max accuracy: ', vacc_mx)
print('Test loss:', tlss_mn, ', accuracy {}'.format(tacc_mx))
break
train_loss_avg = 0
train_acc_avg = 0
val_loss_avg = 0
val_acc_avg = 0
sess.close()
nb_nodes = features.shape[0]
ft_size = features.shape[1]
nb_classes = y_train.shape[1]
features = features[np.newaxis]
y_train = y_train[np.newaxis]
y_val = y_val[np.newaxis]
y_test_real = y_test
test_mask_real = test_mask
y_test = y_test[np.newaxis]
train_mask = train_mask[np.newaxis]
val_mask = val_mask[np.newaxis]
test_mask = test_mask[np.newaxis]
if sparse:
biases = process.preprocess_adj_bias(adj)
else:
adj = adj.todense()
adj = adj[np.newaxis]
biases = process.adj_to_bias(adj, [nb_nodes], nhood=1)
with tf.Graph().as_default():
with tf.name_scope('input'):
ftr_in = tf.placeholder(dtype=tf.float32,
shape=(batch_size, nb_nodes, ft_size))
if sparse:
#bias_idx = tf.placeholder(tf.int64)
#bias_val = tf.placeholder(tf.float32)
#bias_shape = tf.placeholder(tf.int64)
bias_in = tf.sparse_placeholder(dtype=tf.float32)
else:
adj = sp.csr_matrix(adj)
###
nb_nodes = features.shape[0]
ft_size = features.shape[1]
nb_classes = y_train.shape[1]
features = features[np.newaxis]
y_train = y_train[np.newaxis]
y_val = y_val[np.newaxis]
y_test = y_test[np.newaxis]
train_mask = train_mask[np.newaxis]
val_mask = val_mask[np.newaxis]
test_mask = test_mask[np.newaxis]
biases = process.preprocess_adj_bias(
adj) if args.model == 'gat' else process.preprocess_adj(adj)
nnz = len(biases[1])
def run_once(run_id):
with tf.Graph().as_default():
with tf.name_scope('input'):
ftr_in = tf.placeholder(dtype=tf.float32,
shape=(batch_size, nb_nodes, ft_size))
bias_in = tf.sparse_placeholder(dtype=tf.float32)
lbl_in = tf.placeholder(dtype=tf.int32,
shape=(batch_size, nb_nodes, nb_classes))
msk_in = tf.placeholder(dtype=tf.int32,
shape=(batch_size, nb_nodes))
attn_drop = tf.placeholder(dtype=tf.float32, shape=())
ffd_drop = tf.placeholder(dtype=tf.float32, shape=())
def train(sparse, epochs, lr, patience, l2_coef, hid_units, n_heads, residual,
attention_drop, edge_attr_directory, node_features_path, label_path,
log_path, train_ratio):
# flags = tf.app.flags
# FLAGS = flags.FLAGS
nb_epochs = epochs
# flags.DEFINE_string('summaries_dir', log_path, 'Summaries directory')
if tf.gfile.Exists(log_path):
tf.gfile.DeleteRecursively(log_path)
tf.gfile.MakeDirs(log_path)
checkpt_file = 'pre_trained/mod_test.ckpt'
dataset = 'know'
# training params
batch_size = 1
nonlinearity = tf.nn.elu
if sparse:
model = SpGAT
else:
model = GAT
nhood = 1
in_drop = attention_drop
print('Dataset: ' + dataset)
print('----- Opt. hyperparams -----')
print('lr: ' + str(lr))
print('l2_coef: ' + str(l2_coef))
print('----- Archi. hyperparams -----')
print('nb. layers: ' + str(len(hid_units)))
print('nb. units per layer: ' + str(hid_units))
print('nb. attention heads: ' + str(n_heads))
print('residual: ' + str(residual))
print('nonlinearity: ' + str(nonlinearity))
print('model: ' + str(model))
adjs, features, y_train, y_val, y_test, train_mask, val_mask, test_mask, edge_attr_name = process.load_data(
edge_attr_directory, node_features_path, label_path, train_ratio)
features, spars = process.preprocess_features(features)
nb_nodes = features.shape[0]
ft_size = features.shape[1]
nb_classes = y_train.shape[1]
features = features[np.newaxis]
# adj = adj[np.newaxis]
# adjs = [adj[np.newaxis] for adj in adjs]
y_train = y_train[np.newaxis]
y_val = y_val[np.newaxis]
y_test = y_test[np.newaxis]
train_mask = train_mask[np.newaxis]
val_mask = val_mask[np.newaxis]
test_mask = test_mask[np.newaxis]
if sparse:
biases = process.preprocess_adj_bias(
adjs[0], to_unweighted=True
) # sparse (indices, values, dense_shape), the graph topologies (unweighted)
adjs = [
tf.SparseTensor(
*process.preprocess_adj_bias(adj, to_unweighted=False))
for adj in adjs
]
else:
biases = process.adj_to_bias(adjs[0], [nb_nodes], nhood=nhood)
# biases = process.get_bias_mat(adjs[0], [nb_nodes], nhood=nhood)
print(biases)
# with tf.Graph().as_default():
with tf.name_scope('input'):
ftr_in = tf.placeholder(dtype=tf.float32,
shape=(batch_size, nb_nodes, ft_size))
if sparse:
# bias_in = tf.sparse_placeholder(dtype=tf.float32)
bias_in = tf.SparseTensor(*biases)
else:
bias_in = tf.placeholder(dtype=tf.float32,
shape=(batch_size, nb_nodes, nb_nodes))
lbl_in = tf.placeholder(dtype=tf.int32,
shape=(batch_size, nb_nodes, nb_classes))
msk_in = tf.placeholder(dtype=tf.int32, shape=(batch_size, nb_nodes))
attn_drop = tf.placeholder(dtype=tf.float32, shape=())
ffd_drop = tf.placeholder(dtype=tf.float32, shape=())
is_train = tf.placeholder(dtype=tf.bool, shape=())
logits = model.inference(inputs=ftr_in,
edge_adjs=adjs,
nb_classes=nb_classes,
nb_nodes=nb_nodes,
training=is_train,
attn_drop=attn_drop,
ffd_drop=ffd_drop,
bias_mat=bias_in,
hid_units=hid_units,
n_heads=n_heads,
residual=residual,
activation=nonlinearity,
edge_attr_name=edge_attr_name)
log_resh = tf.reshape(logits, [-1, nb_classes])
lab_resh = tf.reshape(lbl_in, [-1, nb_classes])
msk_resh = tf.reshape(msk_in, [-1])
loss = model.masked_softmax_cross_entropy(log_resh, lab_resh, msk_resh)
micro_f1 = model.micro_f1(log_resh, lab_resh, msk_resh)
accuracy = model.masked_accuracy(log_resh, lab_resh, msk_resh)
train_op = model.training(loss, lr, l2_coef)
saver = tf.train.Saver()
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
vlss_mn = np.inf
vacc_mx = 0.0
vmf1_mx = 0.0
curr_step = 0
with tf.Session() as sess:
merged = tf.summary.merge_all()
train_summary_writer = tf.summary.FileWriter(log_path + '/train')
test_summary_writer = tf.summary.FileWriter(log_path + '/test')
sess.run(init_op)
train_loss_avg = 0
train_acc_avg = 0
train_microf1_avg = 0
val_loss_avg = 0
val_acc_avg = 0
val_microf1_avg = 0
for epoch in range(nb_epochs):
tr_step = 0
tr_size = features.shape[0]
while tr_step * batch_size < tr_size:
if sparse:
bbias = biases
else:
bbias = biases[tr_step * batch_size:(tr_step + 1) *
batch_size]
_, summary, loss_value_tr, acc_tr, micro_f1_tr = sess.run(
[train_op, merged, loss, accuracy, micro_f1],
feed_dict={
ftr_in:
features[tr_step * batch_size:(tr_step + 1) *
batch_size],
# bias_in: bbias,
lbl_in:
y_train[tr_step * batch_size:(tr_step + 1) *
batch_size],
msk_in:
train_mask[tr_step * batch_size:(tr_step + 1) *
batch_size],
is_train:
True,
attn_drop:
attention_drop,
ffd_drop:
in_drop
})
print(loss_value_tr)
train_microf1_avg += micro_f1_tr
train_loss_avg += loss_value_tr
train_acc_avg += acc_tr
tr_step += 1
train_summary_writer.add_summary(summary, epoch)
vl_step = 0
vl_size = features.shape[0]
while vl_step * batch_size < vl_size:
if sparse:
bbias = biases
else:
bbias = biases[vl_step * batch_size:(vl_step + 1) *
batch_size]
summary, loss_value_vl, acc_vl, micro_f1_vl = sess.run(
[merged, loss, accuracy, micro_f1],
feed_dict={
ftr_in:
features[vl_step * batch_size:(vl_step + 1) *
batch_size],
# bias_in: bbias,
lbl_in:
y_val[vl_step * batch_size:(vl_step + 1) * batch_size],
msk_in:
val_mask[vl_step * batch_size:(vl_step + 1) *
batch_size],
is_train:
False,
attn_drop:
0.0,
ffd_drop:
0.0
})
val_microf1_avg += micro_f1_vl
val_loss_avg += loss_value_vl
val_acc_avg += acc_vl
vl_step += 1
test_summary_writer.add_summary(summary, epoch)
print(
'Training: loss = %.5f, acc = %.5f, micro_f1 = %.5f | Val: loss = %.5f, acc = %.5f, micro_f1 = %.5f'
% (train_loss_avg / tr_step, train_acc_avg / tr_step,
train_microf1_avg / tr_step, val_loss_avg / vl_step,
val_acc_avg / vl_step, val_microf1_avg / vl_step))
if val_acc_avg / vl_step >= vacc_mx or val_loss_avg / vl_step <= vlss_mn:
if val_acc_avg / vl_step >= vacc_mx and val_loss_avg / vl_step <= vlss_mn:
vacc_early_model = val_acc_avg / vl_step
vlss_early_model = val_loss_avg / vl_step
saver.save(sess, checkpt_file)
vmf1_mx = np.max((val_microf1_avg / vl_step, vmf1_mx))
vacc_mx = np.max((val_acc_avg / vl_step, vacc_mx))
vlss_mn = np.min((val_loss_avg / vl_step, vlss_mn))
curr_step = 0
else:
curr_step += 1
if curr_step == patience:
print('Early stop! Min loss: ', vlss_mn,
', Max accuracy: ', vacc_mx, ', Max Micro-f1',
vmf1_mx)
print('Early stop model validation loss: ',
vlss_early_model, ', accuracy: ', vacc_early_model)
break
train_loss_avg = 0
train_acc_avg = 0
train_microf1_avg = 0
val_loss_avg = 0
val_acc_avg = 0
val_microf1_avg = 0
saver.restore(sess, checkpt_file)
ts_size = features.shape[0]
ts_step = 0
ts_loss = 0.0
ts_acc = 0.0
while ts_step * batch_size < ts_size:
if sparse:
bbias = biases
else:
bbias = biases[ts_step * batch_size:(ts_step + 1) * batch_size]
loss_value_ts, acc_ts = sess.run(
[loss, accuracy],
feed_dict={
ftr_in:
features[ts_step * batch_size:(ts_step + 1) * batch_size],
# bias_in: bbias,
lbl_in:
y_test[ts_step * batch_size:(ts_step + 1) * batch_size],
msk_in:
test_mask[ts_step * batch_size:(ts_step + 1) * batch_size],
is_train:
False,
attn_drop:
0.0,
ffd_drop:
0.0
})
ts_loss += loss_value_ts
ts_acc += acc_ts
ts_step += 1
print('Test loss:', ts_loss / ts_step, '; Test accuracy:',
ts_acc / ts_step)
sess.close()
#some preprocess
adj, features, y_train, y_val, y_test, train_mask, val_mask, test_mask = process.load_data(
FLAGS.dataset)
features, spars = process.preprocess_features(features)
nb_nodes = features.shape[0]
ft_size = features.shape[1]
nb_classes = y_train.shape[1]
features = features[np.newaxis]
y_train = y_train[np.newaxis]
y_val = y_val[np.newaxis]
y_test = y_test[np.newaxis]
train_mask = train_mask[np.newaxis]
val_mask = val_mask[np.newaxis]
test_mask = test_mask[np.newaxis]
#biases = process.preprocess_adj_gat(adj)####process adj to find the 1hop and 2hop neighbors
biases = process.preprocess_adj_bias(adj) ####just 1-hop adj matrix
adj_hop1_all, adj_hop2_all, adj_hop1_neig, adj_hop2_neig, N_hop1_target, N_hop2_target = process.preprocess_bilinear(
adj)
t_rep_s = time.time()
ftr_in = tf.placeholder(dtype=tf.float32, shape=(1, nb_nodes, ft_size))
bias_in = tf.sparse_placeholder(dtype=tf.float32)
adj_hop1_all_in = tf.sparse_placeholder(dtype=tf.float32)
adj_hop2_all_in = tf.sparse_placeholder(dtype=tf.float32)
adj_hop1_neig_in = tf.sparse_placeholder(dtype=tf.float32)
adj_hop2_neig_in = tf.sparse_placeholder(dtype=tf.float32)
N_hop1_target_in = tf.sparse_placeholder(dtype=tf.float32)
N_hop2_target_in = tf.sparse_placeholder(dtype=tf.float32)
lbl_in = tf.placeholder(dtype=tf.int32, shape=(1, nb_nodes, nb_classes))
msk_in = tf.placeholder(dtype=tf.int32, shape=(1, nb_nodes))
def run_gat(dataset,
batch_size,
nb_epochs,
patience,
lr,
l2_coef,
hid_units,
n_heads,
residual,
nonlinearity,
model,
checkpt_file,
nhood,
param_attn_drop=0.6,
param_ffd_drop=0.6,
sparse=False):
'''
Function that runs all the experiments.
:param dataset: The string name of the dataset.
:param batch_size: Number of samples per batch. Has to be one for spartial execution.
:param nb_epochs: Number of epochs that the method runs
:param patience: The number of epochs with no improvement in validation accuracy that stops the training.
:param lr: Learning rate.
:param l2_coef: The L2 regularization strength.
:param hid_units: List. Number of features the respecting layer produces from the input features.
:param n_heads: List. Number of entries is the number of layers. The elements value is the number of attention heads.
:param residual: Whether or not to use residual connections in the hidden layers.
:param nonlinearity: tensorflow function for non-linearity
:param model: Model that inherits from BasGAttn and implements the inference method
:param checkpt_file: Location where the logs, output and model checkpoints are saved
:param nhood: The neighborhood to consider. One for direct neighborhood and two for neighbors of neighbors.
:param param_attn_drop: Drops a percent of attention coefficients.
:param param_ffd_drop: Drops a percent of inputs from the previous layer.
:param sparse: If True, the model has to be SpGAT
:return: Prints and logs results.
'''
# necessary work around to run on GPU
'''
from tensorflow.compat.v1 import ConfigProto
from tensorflow.compat.v1 import InteractiveSession
config = ConfigProto()
config.gpu_options.allow_growth = True
session = InteractiveSession(config=config)
'''
# redirect output to file
import sys
orig_stdout = sys.stdout
if os.path.isfile(os.path.dirname(checkpt_file) + 'out.txt'):
f = open(os.path.dirname(checkpt_file) + 'out.txt', 'a')
sys.stdout = f
print('\n\n\n\n')
else:
f = open(os.path.dirname(checkpt_file) + 'out.txt', 'w')
sys.stdout = f
print('Dataset: ' + dataset)
print('batch_size: ' + str(batch_size))
print('----- Opt. hyperparams -----')
print('lr: ' + str(lr))
print('l2_coef: ' + str(l2_coef))
print('----- Archi. hyperparams -----')
print('nb. layers: ' + str(len(hid_units)))
print('nb. units per layer: ' + str(hid_units))
print('nb. attention heads: ' + str(n_heads))
print('residual: ' + str(residual))
print('nonlinearity: ' + str(nonlinearity))
print('model: ' + str(model))
print('nhood: ' + str(nhood))
print('attn_drop: ' + str(param_attn_drop))
print('ffd_drop: ' + str(param_ffd_drop))
# load any of the three transductive datasets
# adj has information about the connections
# features is a node node x features matrix with the features for each node
# y_... has the label for each class in a node x class matrix
# mask has 0 or 1 as value in a node vector, this is used to mask train, val and test set
# so for all nodes all information is calculated, but only nodes masked with 1 are evaluated
adj, features, y_train, y_val, y_test, train_mask, val_mask, test_mask = process.load_data(
dataset)
# preprocessing steps
features, spars = process.preprocess_features(features)
nb_nodes = features.shape[0]
ft_size = features.shape[1]
nb_classes = y_train.shape[1]
features = features[np.newaxis]
# adj = adj[np.newaxis]
y_train = y_train[np.newaxis]
y_val = y_val[np.newaxis]
y_test = y_test[np.newaxis]
train_mask = train_mask[np.newaxis]
val_mask = val_mask[np.newaxis]
test_mask = test_mask[np.newaxis]
# the adjacency matrix is transformed into a bias that is added.
# when no connection between nodes exist in the specified neighborhood, the value of the attention between
# both nodes is set to a big negative value, pratically canceling out the effect.
if sparse:
biases = process.preprocess_adj_bias(adj)
else:
adj = adj.todense()
adj = adj[np.newaxis]
biases = process.adj_to_bias(adj, [nb_nodes], nhood=1)
with tf.Graph().as_default():
with tf.name_scope('input'):
# initialization
ftr_in = tf.placeholder(dtype=tf.float32,
shape=(batch_size, nb_nodes, ft_size))
if sparse:
bias_in = tf.sparse_placeholder(dtype=tf.float32)
else:
bias_in = tf.placeholder(dtype=tf.float32,
shape=(batch_size, nb_nodes,
nb_nodes))
# bias_in = tf.placeholder(dtype=tf.float32, shape=(batch_size, nb_nodes, nb_nodes))
lbl_in = tf.placeholder(dtype=tf.int32,
shape=(batch_size, nb_nodes, nb_classes))
msk_in = tf.placeholder(dtype=tf.int32,
shape=(batch_size, nb_nodes))
attn_drop = tf.placeholder(dtype=tf.float32, shape=())
ffd_drop = tf.placeholder(dtype=tf.float32, shape=())
is_train = tf.placeholder(dtype=tf.bool, shape=())
logits = model.inference(ftr_in,
nb_classes,
nb_nodes,
is_train,
attn_drop,
ffd_drop,
bias_mat=bias_in,
hid_units=hid_units,
n_heads=n_heads,
residual=residual,
activation=nonlinearity)
log_resh = tf.reshape(logits, [-1, nb_classes])
lab_resh = tf.reshape(lbl_in, [-1, nb_classes])
msk_resh = tf.reshape(msk_in, [-1])
loss = model.masked_softmax_cross_entropy(log_resh, lab_resh, msk_resh)
accuracy = model.masked_accuracy(log_resh, lab_resh, msk_resh)
train_op = model.training(loss, lr, l2_coef)
saver = tf.train.Saver()
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
vlss_mn = np.inf
vacc_mx = 0.0
curr_step = 0
start = time.time()
with tf.Session() as sess:
sess.run(init_op)
train_loss_avg = 0
train_acc_avg = 0
val_loss_avg = 0
val_acc_avg = 0
for epoch in range(nb_epochs):
tr_step = 0
tr_size = features.shape[0]
# training steps
while tr_step * batch_size < tr_size:
if sparse:
bbias = biases
else:
bbias = biases[tr_step * batch_size:(tr_step + 1) *
batch_size]
_, loss_value_tr, acc_tr = sess.run(
[train_op, loss, accuracy],
feed_dict={
ftr_in:
features[tr_step * batch_size:(tr_step + 1) *
batch_size],
bias_in:
bbias,
lbl_in:
y_train[tr_step * batch_size:(tr_step + 1) *
batch_size],
msk_in:
train_mask[tr_step * batch_size:(tr_step + 1) *
batch_size],
is_train:
True,
attn_drop:
param_attn_drop,
ffd_drop:
param_ffd_drop
})
train_loss_avg += loss_value_tr
train_acc_avg += acc_tr
tr_step += 1
vl_step = 0
vl_size = features.shape[0]
# validation steps
while vl_step * batch_size < vl_size:
if sparse:
bbias = biases
else:
bbias = biases[vl_step * batch_size:(vl_step + 1) *
batch_size]
loss_value_vl, acc_vl = sess.run(
[loss, accuracy],
feed_dict={
ftr_in:
features[vl_step * batch_size:(vl_step + 1) *
batch_size],
bias_in:
bbias,
lbl_in:
y_val[vl_step * batch_size:(vl_step + 1) *
batch_size],
msk_in:
val_mask[vl_step * batch_size:(vl_step + 1) *
batch_size],
is_train:
False,
attn_drop:
0.0,
ffd_drop:
0.0
})
val_loss_avg += loss_value_vl
val_acc_avg += acc_vl
vl_step += 1
print(
'Training: loss = %.5f, acc = %.5f | Val: loss = %.5f, acc = %.5f'
% (train_loss_avg / tr_step, train_acc_avg / tr_step,
val_loss_avg / vl_step, val_acc_avg / vl_step))
# patience step
if val_acc_avg / vl_step >= vacc_mx or val_loss_avg / vl_step <= vlss_mn:
if val_acc_avg / vl_step >= vacc_mx and val_loss_avg / vl_step <= vlss_mn:
vacc_early_model = val_acc_avg / vl_step
vlss_early_model = val_loss_avg / vl_step
saver.save(sess, checkpt_file)
vacc_mx = np.max((val_acc_avg / vl_step, vacc_mx))
vlss_mn = np.min((val_loss_avg / vl_step, vlss_mn))
curr_step = 0
else:
curr_step += 1
if curr_step == patience:
print('Early stop! Min loss: ', vlss_mn,
', Max accuracy: ', vacc_mx)
print('Early stop model validation loss: ',
vlss_early_model, ', accuracy: ',
vacc_early_model)
break
train_loss_avg = 0
train_acc_avg = 0
val_loss_avg = 0
val_acc_avg = 0
saver.restore(sess, checkpt_file)
ts_size = features.shape[0]
ts_step = 0
ts_loss = 0.0
ts_acc = 0.0
# evaluate on the training set
while ts_step * batch_size < ts_size:
if sparse:
bbias = biases
else:
bbias = biases[ts_step * batch_size:(ts_step + 1) *
batch_size]
loss_value_ts, acc_ts = sess.run(
[loss, accuracy],
feed_dict={
ftr_in:
features[ts_step * batch_size:(ts_step + 1) *
batch_size],
bias_in:
bbias,
lbl_in:
y_test[ts_step * batch_size:(ts_step + 1) *
batch_size],
msk_in:
test_mask[ts_step * batch_size:(ts_step + 1) *
batch_size],
is_train:
False,
attn_drop:
0.0,
ffd_drop:
0.0
})
ts_loss += loss_value_ts
ts_acc += acc_ts
ts_step += 1
print('Test loss:', ts_loss / ts_step, '; Test accuracy:',
ts_acc / ts_step, ' at epoch: ', epoch, ' elapsed time',
time.time() - start)
# log information about the training
if os.path.isfile(os.path.dirname(checkpt_file) + 'log.csv'):
print('loading existing log')
df = pd.read_csv(os.path.dirname(checkpt_file) + 'log.csv',
index_col=['run'])
print('log: ' + str(df))
else:
print('Creating new log')
df = pd.DataFrame(columns=tracking_params + result_cols)
log = dict(
zip(tracking_params + result_cols, [
dataset, lr, l2_coef, hid_units, n_heads, residual,
str(nonlinearity).split(' ')[1], param_attn_drop,
param_ffd_drop, nhood
] + [
epoch,
time.time() - start, vlss_mn, vacc_mx, ts_loss / ts_step,
ts_acc / ts_step
]))
print('Adding entry: ' + str(log))
df = df.append(log, ignore_index=True)
print('saving logs')
df.to_csv(os.path.dirname(checkpt_file) + 'log.csv',
index_label='run')
print('log save succesfull')
sess.close()
# restore standard output
sys.stdout = orig_stdout
f.close()
def train(sparse, hid_units, n_heads, residual, edge_attr_directory,
node_features_path, label_path, train_ratio, model_path):
# flags = tf.app.flags
# FLAGS = flags.FLAGS
# flags.DEFINE_string('summaries_dir', log_path, 'Summaries directory')
# if tf.gfile.Exists(log_path):
# tf.gfile.DeleteRecursively(log_path)
# tf.gfile.MakeDirs(log_path)
checkpt_file = model_path
dataset = 'know'
# training params
batch_size = 1
nonlinearity = tf.nn.elu
if sparse:
model = SpGAT
else:
model = GAT
nhood = 1
# in_drop = attention_drop
print('Dataset: ' + dataset)
print('----- Archi. hyperparams -----')
print('nb. layers: ' + str(len(hid_units)))
print('nb. units per layer: ' + str(hid_units))
print('nb. attention heads: ' + str(n_heads))
print('residual: ' + str(residual))
print('nonlinearity: ' + str(nonlinearity))
print('model: ' + str(model))
adjs, features, y_train, y_val, y_test, train_mask, val_mask, test_mask, edge_attr_name = process.load_data(
edge_attr_directory, node_features_path, label_path, train_ratio)
features, spars = process.preprocess_features(features)
nb_nodes = features.shape[0]
ft_size = features.shape[1]
nb_classes = y_train.shape[1]
features = features[np.newaxis]
# adj = adj[np.newaxis]
# adjs = [adj[np.newaxis] for adj in adjs]
y_train = y_train[np.newaxis]
y_val = y_val[np.newaxis]
y_test = y_test[np.newaxis]
train_mask = train_mask[np.newaxis]
val_mask = val_mask[np.newaxis]
test_mask = test_mask[np.newaxis]
if sparse:
biases = process.preprocess_adj_bias(
adjs[0], to_unweighted=True
) # sparse (indices, values, dense_shape), the graph topologies (unweighted)
adjs = [
tf.SparseTensor(
*process.preprocess_adj_bias(adj, to_unweighted=False))
for adj in adjs
]
else:
biases = process.adj_to_bias(adjs[0], [nb_nodes], nhood=nhood)
# biases = process.get_bias_mat(adjs[0], [nb_nodes], nhood=nhood)
print(biases)
# with tf.Graph().as_default():
with tf.name_scope('input'):
ftr_in = tf.placeholder(dtype=tf.float32,
shape=(batch_size, nb_nodes, ft_size))
if sparse:
# bias_in = tf.sparse_placeholder(dtype=tf.float32)
bias_in = tf.SparseTensor(*biases)
else:
bias_in = tf.placeholder(dtype=tf.float32,
shape=(batch_size, nb_nodes, nb_nodes))
lbl_in = tf.placeholder(dtype=tf.int32,
shape=(batch_size, nb_nodes, nb_classes))
msk_in = tf.placeholder(dtype=tf.int32, shape=(batch_size, nb_nodes))
attn_drop = tf.placeholder(dtype=tf.float32, shape=())
ffd_drop = tf.placeholder(dtype=tf.float32, shape=())
is_train = tf.placeholder(dtype=tf.bool, shape=())
logits = model.inference(inputs=ftr_in,
edge_adjs=adjs,
nb_classes=nb_classes,
nb_nodes=nb_nodes,
training=is_train,
attn_drop=attn_drop,
ffd_drop=ffd_drop,
bias_mat=bias_in,
hid_units=hid_units,
n_heads=n_heads,
residual=residual,
activation=nonlinearity,
edge_attr_name=edge_attr_name)
log_resh = tf.reshape(logits, [-1, nb_classes])
lab_resh = tf.reshape(lbl_in, [-1, nb_classes])
msk_resh = tf.reshape(msk_in, [-1])
loss = model.masked_softmax_cross_entropy(log_resh, lab_resh, msk_resh)
micro_f1 = model.micro_f1(log_resh, lab_resh, msk_resh)
accuracy = model.masked_accuracy(log_resh, lab_resh, msk_resh)
# train_op = model.training(loss, lr, l2_coef)
saver = tf.train.Saver()
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
with tf.Session() as sess:
sess.run(init_op)
saver.restore(sess, checkpt_file)
ts_size = features.shape[0]
ts_step = 0
ts_loss = 0.0
ts_acc = 0.0
while ts_step * batch_size < ts_size:
if sparse:
bbias = biases
else:
bbias = biases[ts_step * batch_size:(ts_step + 1) * batch_size]
loss_value_ts, acc_ts = sess.run(
[loss, accuracy],
feed_dict={
ftr_in:
features[ts_step * batch_size:(ts_step + 1) * batch_size],
# bias_in: bbias,
lbl_in:
y_test[ts_step * batch_size:(ts_step + 1) * batch_size],
msk_in:
test_mask[ts_step * batch_size:(ts_step + 1) * batch_size],
is_train:
False,
attn_drop:
0.0,
ffd_drop:
0.0
})
ts_loss += loss_value_ts
ts_acc += acc_ts
ts_step += 1
print('Test loss:', ts_loss / ts_step, '; Test accuracy:',
ts_acc / ts_step)
sess.close()
def train():
sparse = True
adj, features, y_train, y_val, y_test, train_mask, val_mask, test_mask = process.load_data(dataset, train_size, validation_size)
features, spars = process.preprocess_features(features)
nb_nodes = features.shape[0]
ft_size = features.shape[1]
nb_classes = y_train.shape[1]
features = features[np.newaxis]
y_train = y_train[np.newaxis]
y_val = y_val[np.newaxis]
y_test = y_test[np.newaxis]
train_mask = train_mask[np.newaxis]
val_mask = val_mask[np.newaxis]
test_mask = test_mask[np.newaxis]
if sparse:
biases = process.preprocess_adj_bias(adj)
else:
adj = adj.todense()
adj = adj[np.newaxis]
biases = process.adj_to_bias(adj, [nb_nodes], nhood=1)
with tf.Graph().as_default():
with tf.name_scope('input'):
ftr_in = tf.placeholder(dtype=tf.float32, shape=(batch_size, nb_nodes, ft_size))
if sparse:
#bias_idx = tf.placeholder(tf.int64)
#bias_val = tf.placeholder(tf.float32)
#bias_shape = tf.placeholder(tf.int64)
bias_in = tf.sparse_placeholder(dtype=tf.float32)
else:
bias_in = tf.placeholder(dtype=tf.float32, shape=(batch_size, nb_nodes, nb_nodes))
lbl_in = tf.placeholder(dtype=tf.int32, shape=(batch_size, nb_nodes, nb_classes))
msk_in = tf.placeholder(dtype=tf.int32, shape=(batch_size, nb_nodes))
attn_drop = tf.placeholder(dtype=tf.float32, shape=())
ffd_drop = tf.placeholder(dtype=tf.float32, shape=())
is_train = tf.placeholder(dtype=tf.bool, shape=())
logits = model.inference(ftr_in, nb_classes, nb_nodes, is_train,
attn_drop, ffd_drop,
bias_mat=bias_in,
hid_units=hid_units, n_heads=n_heads,
residual=residual, activation=nonlinearity)
log_resh = tf.reshape(logits, [-1, nb_classes])
lab_resh = tf.reshape(lbl_in, [-1, nb_classes])
msk_resh = tf.reshape(msk_in, [-1])
loss = model.masked_softmax_cross_entropy(log_resh, lab_resh, msk_resh)
accuracy = model.masked_accuracy(log_resh, lab_resh, msk_resh)
train_op = model.training(loss, lr, l2_coef)
saver = tf.train.Saver()
init_op = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer())
vlss_mn = np.inf
vacc_mx = 0.0
curr_step = 0
gpu_options = tf.GPUOptions(allow_growth=True)
with tf.Session(config=tf.ConfigProto(gpu_options=gpu_options)) as sess:
sess.run(init_op)
train_loss_avg = 0
train_acc_avg = 0
val_loss_avg = 0
val_acc_avg = 0
for epoch in range(nb_epochs):
tr_step = 0
tr_size = features.shape[0]
while tr_step * batch_size < tr_size:
if sparse:
bbias = biases
else:
bbias = biases[tr_step*batch_size:(tr_step+1)*batch_size]
_, loss_value_tr, acc_tr = sess.run([train_op, loss, accuracy],
feed_dict={
ftr_in: features[tr_step*batch_size:(tr_step+1)*batch_size],
bias_in: bbias,
lbl_in: y_train[tr_step*batch_size:(tr_step+1)*batch_size],
msk_in: train_mask[tr_step*batch_size:(tr_step+1)*batch_size],
is_train: True,
attn_drop: 0.6, ffd_drop: 0.6})
train_loss_avg += loss_value_tr
train_acc_avg += acc_tr
tr_step += 1
if args.validate:
vl_step = 0
vl_size = features.shape[0]
while vl_step * batch_size < vl_size:
if sparse:
bbias = biases
else:
bbias = biases[vl_step*batch_size:(vl_step+1)*batch_size]
loss_value_vl, acc_vl = sess.run([loss, accuracy],
feed_dict={
ftr_in: features[vl_step*batch_size:(vl_step+1)*batch_size],
bias_in: bbias,
lbl_in: y_val[vl_step*batch_size:(vl_step+1)*batch_size],
msk_in: val_mask[vl_step*batch_size:(vl_step+1)*batch_size],
is_train: False,
attn_drop: 0.0, ffd_drop: 0.0})
val_loss_avg += loss_value_vl
val_acc_avg += acc_vl
vl_step += 1
else:
tr_step = 0
vl_step = 0
vl_size = features.shape[0]
val_loss_avg = 0
val_acc_avg = 0
while tr_step * batch_size < tr_size:
if sparse:
bbias = biases
else:
bbias = biases[tr_step*batch_size:(tr_step+1)*batch_size]
loss_value_vl, acc_vl = sess.run([loss, accuracy],
feed_dict={
ftr_in: features[tr_step*batch_size:(tr_step+1)*batch_size],
bias_in: bbias,
lbl_in: y_train[tr_step*batch_size:(tr_step+1)*batch_size],
msk_in: train_mask[tr_step*batch_size:(tr_step+1)*batch_size],
is_train: False,
attn_drop: 0., ffd_drop: 0.})
val_loss_avg += loss_value_vl
val_acc_avg += acc_vl
vl_step += 1
tr_step += 1
print('%d Training: loss = %.5f, acc = %.5f | Val: loss = %.5f, acc = %.5f' %
(epoch, train_loss_avg/tr_step, train_acc_avg/tr_step,
val_loss_avg/vl_step, val_acc_avg/vl_step))
if val_acc_avg/vl_step > vacc_mx or val_loss_avg/vl_step < vlss_mn:
if val_acc_avg/vl_step >= vacc_mx and val_loss_avg/vl_step <= vlss_mn:
vacc_early_model = val_acc_avg/vl_step
vlss_early_model = val_loss_avg/vl_step
saver.save(sess, checkpt_file)
ts_size = features.shape[0]
ts_step = 0
ts_loss = 0.0
ts_acc = 0.0
while ts_step * batch_size < ts_size:
if sparse:
bbias = biases
else:
bbias = biases[ts_step * batch_size:(ts_step + 1) * batch_size]
loss_value_ts, acc_ts = sess.run([loss, accuracy],
feed_dict={
ftr_in: features[ts_step * batch_size:(ts_step + 1) * batch_size],
bias_in: bbias,
lbl_in: y_test[ts_step * batch_size:(ts_step + 1) * batch_size],
msk_in: test_mask[ts_step * batch_size:(ts_step + 1) * batch_size],
is_train: False,
attn_drop: 0.0, ffd_drop: 0.0})
ts_loss += loss_value_ts
ts_acc += acc_ts
ts_step += 1
print('Test loss:', ts_loss / ts_step, '; Test accuracy:', ts_acc / ts_step)
vacc_mx = np.max((val_acc_avg/vl_step, vacc_mx))
vlss_mn = np.min((val_loss_avg/vl_step, vlss_mn))
curr_step = 0
else:
curr_step += 1
if curr_step == patience:
print('Early stop! Min loss: ', vlss_mn, ', Max accuracy: ', vacc_mx)
print('Early stop model validation loss: ', vlss_early_model, ', accuracy: ', vacc_early_model)
break
train_loss_avg = 0
train_acc_avg = 0
val_loss_avg = 0
val_acc_avg = 0
saver.restore(sess, checkpt_file)
ts_size = features.shape[0]
ts_step = 0
ts_loss = 0.0
ts_acc = 0.0
while ts_step * batch_size < ts_size:
if sparse:
bbias = biases
else:
bbias = biases[ts_step*batch_size:(ts_step+1)*batch_size]
loss_value_ts, acc_ts = sess.run([loss, accuracy],
feed_dict={
ftr_in: features[ts_step*batch_size:(ts_step+1)*batch_size],
bias_in: bbias,
lbl_in: y_test[ts_step*batch_size:(ts_step+1)*batch_size],
msk_in: test_mask[ts_step*batch_size:(ts_step+1)*batch_size],
is_train: False,
attn_drop: 0.0, ffd_drop: 0.0})
ts_loss += loss_value_ts
ts_acc += acc_ts
ts_step += 1
print('Test loss:', ts_loss/ts_step, '; Test accuracy:', ts_acc/ts_step)
sess.close()
return ts_loss/ts_step, ts_acc/ts_step
def __init__(self,params):
self.num_factors = params.num_factors
self.num_users = params.num_users
self.num_items = params.num_items
self.num_doms = params.num_doms
self.attr_dim = params.attn_head_size
self.reg_lam = params.reg_lam
self.reg_w = params.reg_w
self.reg_b = params.reg_b
self.initializer = params.initializer
self.num_views = params.num_views
self.num_attn_heads = params.num_attn_heads
self.num_memory_heads = params.num_memory_heads
self.attn_head_size = params.attn_head_size
self.memory_head_size = params.memory_head_size
self.proj_keep = params.proj_keep
self.attention_keep = params.attention_keep
self.params = params
# list initializtion ====================================
self.memnet = [None] * self.num_views
self.mult_views = [None] * self.num_views
self.item_view_embeds = [None] * self.num_views
self.item_attr_mat = [None] * self.num_views
self.user_embeds_view = [None] * self.num_views
self.proj_item_view = [None] * self.num_views
self.mhead_item_view_output = [None] * self.num_views
self.m3_item_view_output = [None] * self.num_views
# gat ====
self.model = [None] * self.num_views
self.biases = [None] * self.num_views
self.num_nodes = [None] * self.num_views
self.X_features_view = [None] * self.num_views
self.bias_in = [None] * self.num_views
self.logits = [None] * self.num_views
self.item_view_embeddings = [None] * self.num_views
self.item_view_embeds = [None] * self.num_views
self.X_features_item_entity_view = [None] * self.num_views
# =====================================================
self.adjacency_view_matrix = params.adjacency_view_matrix
for view in range(self.num_views):
self.model[view] = SpGAT()
self.biases[view] = process.preprocess_adj_bias(params.adjacency_view_matrix[view])
self.num_nodes[view] = params.adjacency_view_matrix[view].shape[0]
self.out_size = params.num_factors
self.hid_units = params.hid_units
self.n_heads = params.n_heads
self.attn_keep = params.attn_keep
self.ffd_keep = params.ffd_keep
self.proj_keep = params.proj_keep
self.residual = False
self.nonlinearity = tf.nn.elu
self.dense = tf.keras.layers.Dense(self.attn_head_size,use_bias=True,activation='elu')
self.dense_attn = tf.keras.layers.Dense(self.attn_head_size/2,use_bias=True,activation='elu')
self.dense_w = tf.keras.layers.Dense(1,use_bias=False,activation='sigmoid')
