chao1224/GraphMVP

Thank you for your answer!

HICUELA opened this issue · 1 comments

HICUELA commented 
          Thank you for your answer!

I understand that the decoding is not required for the applications you're interested in, but I would be interested in working in this latent space, for instance if I encode a molecule and slightly modify the resulting embedding would it be possible to decode it and get another (valid) molecule?

Originally posted by @htalibart in #17 (comment)

chao1224 commented

Hi @HICUELA,

We actually tried this in another paper called GraphCG. The answer is yes, though the latent space is on the pretrained HierVAE, not on pretrained GraphMVP.