graphdeeplearning / graphtransformer

Graph Transformer Architecture. Source code for "A Generalization of Transformer Networks to Graphs", DLG-AAAI'21.

Home Page:https://arxiv.org/abs/2012.09699

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Eval sign flipping

devnkong opened this issue · comments

Hi Vijay,

Thanks for your repo!

Question: I see your doing sign flipping of eigen pos_enc during training, but it seems that you are not doing so during eval time. I understand that we want to make deterministic predictions so we don't have random flipping when evaluating it. Do you have further comments or justification for this?

Best
Kezhi

Also do you have some reason for choosing eigen vectors with small eigen values?

Hi @devnkong, thanks for your questions.

Q: Why sign flipping is not used during eval?
A: The random sign flipping during the training is to allow the network to be invariant or independent of the choices among 2^k possibilities. By this approach then, the sign flipping is not required during eval.

Q: choosing eigen vectors with small eigen values?
A: Please refer to Section E.1.2 in https://arxiv.org/pdf/2003.00982.pdf

Best,
Vijay

Thanks!