Xi Bai

Hi, @dany-nonstop, Thanks for the suggestion and I think you are right in say `parameter_list` is not the torch way and can be superseded by `register_parameter()`. The torch version of...

Hi, @louisccc . Can you pls share some history about the saved embeddings as mentioned above and guide @dany-nonstop through the contributing process?

Hi, @Diqingling. Looks like the original [FB15K_237 paper](https://www.aclweb.org/anthology/W15-4007/) has no code published and it does not mention things like learning rate for `model E` and `DistMult` they used either. In...

Probably there was nothing wrong with your training process coz the best result we can get so far is 60.7%: Model | MR/FMR | MRR/FMRR | HIT-1 | HIT-3 |...

All hyperparameters are derived from the original [paperswithcode](https://paperswithcode.com/) and there might be a slim chance that some authors later corrected errors in their published work, which have not been incorporated...

Is there any further evidence which can be shared here? Such as top X predicted tails/heads on UMLS as well as the true X most likely tails/heads but treated as...

Hi, @Rodrigo-A-Pereira , Thanks for reporting that. I ran 500 epochs with the default hyperparamters and got a similar result for Hits@10 while the filtered MR is much higher than...

Oh cool! In that case, we will add WR18 as a canonical dataset for TransE which may benefit other users. Sounds like the disparity in Hits* is definitely worth some...

Hi, there was a command name mismatch between the README and the implementation. It has been fixed and merged. Thanks for reporting this.

Hi, @ArkDu, I noticed the default learning rate for KG2E is 0.01, which may have been too high and resulted in a large gradient during the training. Would you like...