hexiangnan
commented
3 years ago Thanks for your efforts!
On Tue, Feb 2, 2021 at 12:09 PM Davezqq notifications@github.com wrote:
Closed #71.
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or unsubscribe.
-- Xiangnan HE (Dr) :: Professor :: Vice Dean, School of Data Science :: University of Science and Technology of China (USTC) :: 443 Huangshan Road, Hefei, China 230027 :: (0551) 63607236 (DID) :: hexn@ustc.edu.cn (E) :: http://staff.ustc.edu.cn/~hexn/ (W)
Mr.He, Thanks a lot for your great work! I have learned a lot from it！ I've noticed that the get_train_instances() method is trying to get the input consists of positive and negative examples.The way to get the negative examples is sampling the item that [user,item] is not appeared in the train set.But there is a small possibility that [user,item] shows in the test set.So I just edit the GMF.py,MLP.py,NeuMF.py files to add a condition to determine whether the [user,item] exists in the test set. I am just a general graduate,so I'm a little bit nervous that if I have made any mistake.I'll appreciate a lot if you can point out any mistake that I've made. Thank you again！