-
## 🐛 Bug
## To Reproduce
Steps to reproduce the behavior:
1. python temporal_link_prediction.py
```
Training in cpu-cuda mode.
Loading data
Downloading datasets/diginetica-r2ne.zip …
-
The link prediction results based on embedding models in the paper are so high, why is the Hit@10 result of the TransE model only 0.47?
-
Title, flipping levers / opening linked doors feels bad.
-
Hi, author:
I notice that the code just be used to node classification. Could you please share the code about link prediction? Thank you very much!
-
With pruning off, incomplete paths will be saved. Does it make sense to try some link prediction to jump these gaps, say after supporting edges are completed? There are numerous link prediction algor…
-
Hi,
For link prediction, the last layer is linear. So the output is in the set R. However, the predicted adjacency of a node i should be in {0,1}. I suppose the output of the last layer should be sof…
-
Hi,
Thank you for such amazing notebooks and sorry if I am missing something basic. Are you doing link prediction in the layoutlm notebooks? If not, any ideas on how it can be done and does the origi…
-
Full reprex to be attached momentarily (comment too large for pasting), bug found in course of identifying problem in #130
Note for #130 will not fix, however, logging here for addressing software…
-
See predictions here: https://www.metaculus.com/accounts/profile/192049/, and look for common themes with why the predictions are incorrect.
Relates to , as we don't have the full research report (…
-
I am so sorry to delete the comments a person recently proposed. Good.
This problem is about baseline. So, I paste the baseline link below,
https://github.com/zouguojian/Traffic-speed-predictio…