pyGAT icon indicating copy to clipboard operation
pyGAT copied to clipboard

Published 20 hours ago • verified publisher icon Diego999

data split issue

Open Yfhu1103 opened this issue 5 years ago • 2 comments

Hello, thanks for sharing your work. In your implementation, I noticed that you split the dataset as "train:range(140), val:range(200, 500), test:range(500, 1500)", I want to know why you split dataset like this? Is this a good split for evaluating model performance?

Yfhu1103 avatar Dec 15 '19 05:12 Yfhu1103

It seems the same question with https://github.com/Diego999/pyGAT/issues/4#issue-343470929

woolpeeker avatar Dec 16 '19 09:12 woolpeeker

Same question. The official paper uses 500 validation data while the pyGAT uses 300. It is inconsistent.

RocStone avatar Apr 23 '21 11:04 RocStone