def main(dataset_name, yang_splits, nheads, hidden_units, feat_drop_rate,
coefs_drop_rate, l2_weight, data_seed, checkpoint_path, verbose,
tsne):
# reproducibility
np.random.seed(data_seed)
if yang_splits:
features, o_h_labels, graph, mask_train, mask_val, mask_test = read_dataset(
dataset_name, yang_splits=True)
labels = np.array([np.argmax(l) for l in o_h_labels], dtype=np.int32)
else:
if verbose > 0: print("reading dataset")
features, neighbors, labels, o_h_labels, keys = read_dataset(
dataset_name)
num_classes = len(set(labels))
if verbose > 0: print("shuffling dataset")
features, neighbors, labels, o_h_labels, keys = permute(
features, neighbors, labels, o_h_labels, keys)
if verbose > 0: print("obtaining masks")
mask_train, mask_val, mask_test = split(dataset_name, labels)
if verbose > 0: print("calculating adjacency matrix")
graph = adjacency_matrix(neighbors)
# add self loops to adj matrix
graph = graph + sp.eye(graph.shape[0])
num_classes = get_num_classes(dataset_name)
features = normalize_features(features)
y_test = np.multiply(o_h_labels,
np.broadcast_to(mask_test.T, o_h_labels.T.shape).T)
if verbose > 0: print("defining model")
model = GAT(graph, num_classes, hidden_units, nheads, feat_drop_rate,
coefs_drop_rate)
model.compile(loss=lambda y_true, y_pred: masked_loss(
y_true, y_pred) + l2_weight * tf.reduce_sum(
[tf.nn.l2_loss(w) for w in model.weights if not 'bias' in w.name]),
metrics=[masked_accuracy])
if verbose > 0: print("load model from checkpoint")
wpath = os.path.join(checkpoint_path, 'cp.ckpt')
model.load_weights(wpath).expect_partial()
if verbose > 0: print("test the model on test set")
t_loss, t_accuracy = model.evaluate(features,
y_test,
batch_size=len(features),
verbose=0)
print("accuracy on test: " + str(t_accuracy))
if tsne:
if verbose > 0: print("calculating t-SNE plot")
intermediate_output = model.call(features,
training=False,
intermediate=True)
plot_tsne(intermediate_output[mask_test], labels[mask_test],
len(o_h_labels[0]), 'GAT')
def main(dataset_name, yang_splits,
nheads, hidden_units, feat_drop_rate, coefs_drop_rate,
epochs, learning_rate, l2_weight, patience,
data_seed, net_seed, checkpoint_path, verbose):
# reproducibility
np.random.seed(data_seed)
tf.random.set_seed(net_seed)
if yang_splits:
features, o_h_labels, graph, mask_train, mask_val, mask_test = read_dataset(dataset_name, yang_splits=True)
labels = np.array([np.argmax(l) for l in o_h_labels], dtype=np.int32)
else:
if verbose > 0: print("reading dataset")
features, neighbors, labels, o_h_labels, keys = read_dataset(dataset_name)
num_classes = len(set(labels))
if verbose > 0: print("shuffling dataset")
features, neighbors, labels, o_h_labels, keys = permute(features, neighbors, labels, o_h_labels, keys)
if verbose > 0: print("obtaining masks")
mask_train, mask_val, mask_test = split(dataset_name, labels)
if verbose > 0: print("calculating adjacency matrix")
graph = adjacency_matrix(neighbors)
# add self loops to adj matrix
graph = graph + sp.eye(graph.shape[0])
num_classes = get_num_classes(dataset_name)
features = normalize_features(features)
y_train = np.multiply(o_h_labels, np.broadcast_to(mask_train.T, o_h_labels.T.shape).T )
y_val = np.multiply(o_h_labels, np.broadcast_to(mask_val.T, o_h_labels.T.shape).T )
y_test = np.multiply(o_h_labels, np.broadcast_to(mask_test.T, o_h_labels.T.shape).T )
optimizer = tf.keras.optimizers.Adam(learning_rate=learning_rate)
if verbose > 0: print("defining model")
model = GAT(graph, num_classes, hidden_units, nheads, feat_drop_rate, coefs_drop_rate)
model.compile(loss=lambda y_true, y_pred: masked_loss(y_true, y_pred)+l2_weight*tf.reduce_sum([tf.nn.l2_loss(w) for w in model.weights if not 'bias' in w.name]),
optimizer=optimizer, metrics=[masked_accuracy])
if verbose > 0: print("begin training")
tb = TensorBoard(log_dir='logs')
if dataset_name == 'cora':
monitor = 'acc_loss'
elif dataset_name == 'pubmed':
monitor = 'loss'
else:
monitor = 'acc'
es = EarlyStoppingAccLoss(patience, monitor, checkpoint_path)
model.fit(features, y_train, epochs=epochs, batch_size=len(features), shuffle=False, validation_data=(features, y_val), callbacks=[tb, es], verbose=verbose)
file_writer = tf.summary.create_file_writer("./logs/results/")
file_writer.set_as_default()
# log best performances on train and val set
loss, accuracy = model.evaluate(features, y_train, batch_size=len(features), verbose=0)
print("accuracy on training: " + str(accuracy))
tf.summary.scalar('bw_loss', data=loss, step=1)
tf.summary.scalar('bw_accuracy', data=accuracy, step=1)
v_loss, v_accuracy = model.evaluate(features, y_val, batch_size=len(features), verbose=0)
print("accuracy on validation: " + str(v_accuracy))
tf.summary.scalar('bw_val_loss', data=v_loss, step=1)
tf.summary.scalar('bw_val_accuracy', data=v_accuracy, step=1)
tf.summary.scalar('bw_epoch', data=es.stopped_epoch, step=1)
if verbose > 0: print("test the model on test set")
t_loss, t_accuracy = model.evaluate(features, y_test, batch_size=len(features), verbose=0)
print("accuracy on test: " + str(t_accuracy))
