xiangwang1223 / disentangled_graph_collaborative_filtering Goto Github PK

Could you tell me the detail of proprocess data to get same statistics of the datasets ? I downloaded the amazon book dataset of 10-core. But i get different statistics of the datasets: item_num = 128939, user_num = 158650, sample = 4701968.

Hi, I have tried several different datasets (including the movielens dataset), the loss is always NAN, no matter how I adjust the hyper-parameters.
Would you give me some suggestions to handle this problem?
Thank you in advance!

Excuse me, why the code is gone?

hi,dear
could you please release the source codes?
if it is in NeuRec, will be much better .
thx