Validation set generated but never used

[saedr]

Dear Phi, In the following piece of code you generate the validation set but never return it, instead you use the test set instead of validation set and there is no actual test set to be used for testing purposes.

graph-representation-learning/longae/utils_gcn.py

Lines 153 to 172 in 48d5978

	val_edges_false = []
	while len(val_edges_false) < len(val_edges):
	idx_i = np.random.randint(0, adj.shape[0])
	idx_j = np.random.randint(0, adj.shape[0])
	if idx_i == idx_j:
	continue
	if ismember([idx_i, idx_j], train_edges):
	continue
	if ismember([idx_j, idx_i], train_edges):
	continue
	if ismember([idx_i, idx_j], val_edges):
	continue
	if ismember([idx_j, idx_i], val_edges):
	continue
	if val_edges_false:
	if ismember([idx_j, idx_i], np.array(val_edges_false)):
	continue
	if ismember([idx_i, idx_j], np.array(val_edges_false)):
	continue
	val_edges_false.append([idx_i, idx_j])

Am I missing something?

[vuptran]

@saedr sorry for the really late response. You are correct, I don't use the val set, but subsume it into the training set. The test set (see below) is used for testing purposes.

https://github.com/vuptran/graph-representation-learning/blob/master/longae/utils_gcn.py#L183