JinheonBaek/RGCN

How is a MRR score of 0.20 possible?

moritzblum opened this issue · 1 comments

I trained with your code and got an MRR of 0.2. In the original paper they only reach an MRR score of 0.156. How is my score with a model with fewer parameters than the original approach possible?

Oh sorry, I messed up with "raw" and "filtered". You actually compute the filtered score which is 0.249 in the original paper.