question of confusing result and request of the sparse matrix version

Open ghost opened this issue 7 years ago • 1 comments

Hi, Sorry to interupt you. I got really impressed on your work of 'cafe-nade' and after reading the paper I found that the best rmse result on Movielen1M can reach down to 0.830, however I can't make the result that good, and I wonder if there's something wrong with parameters or this is not the Cordinal input version? Could you please tell me the parameters' set of the lowest RMSE and could you please tell me the sparse code version? I really need your help, Thanks a ton!

Mar 11 '18 07:03 ghost

@xiaoyuer I can get it down to 0.835236 or polyak 0.833020. The point is to use device=cuda and train for 200 epochs.

Dec 11 '18 22:12 yifeim