NoviceCrom

Results 7 issues of NoviceCrom

Hi! The paper argues that in-batch samples can be used as negatives. In the implementation of training, it seems there's no explicit positives, just mm() for all hr_vectors and tail_vectors?

Can not find the FPN part, could you please kindly point it out?

when executing (_, channel, _, _) = img1.size()

During the training process, I observed that my Val_G_Loss curve was quite abnormal using RAGAN-LS due to the unstable Val_Content_Loss. All metrics appear normal except that the curve of Validation_Content_Loss...

Could you please point out where the Residual Feature Augmentation module is?

Can not find RFP part, could you please kindly show me where it is?

![image](https://github.com/yao8839836/kg-llm/assets/48437212/15bb4ddd-a45b-4358-b7a1-4b4f4811211d) Could you share other details of your performance e.g, MRR, Hits@3&10 in your entity prediction of WN18RR and YAGO-3-10?