This code use test accuracy to select model

HongyangGao / Graph-U-Nets

Pytorch implementation of Graph U-Nets (ICML19)

http://proceedings.mlr.press/v97/gao19a/gao19a.pdf

GNU General Public License v3.0

513 stars 100 forks source link

This code use test accuracy to select model #16

Closed LingxiaoShawn closed 4 years ago

LingxiaoShawn commented 4 years ago

Hi Hongyang, It's nice structured code, but it seems you are using test accuracy to do model selection, am I correct?

HongyangGao commented 4 years ago

Yes. We follow the common practice in the community and use 10-fold cross-validation.

pursueorigin commented 3 years ago

Hi,

I have a question about selecting models. In DGCNN https://github.com/muhanzhang/pytorch_DGCNN/issues/19, the author uses the accuracy of the test set at the last iteration. In this paper, the best accuracy of the test set is used.

Which one should be used in your opinion? In addition, how did you handle DGCNN in Table 4 of this paper? Thanks.