-
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?
-
## 🐛 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 …
-
Could you provide the code for the link prediction task? The link prediction results I implemented differ significantly from those in the paper, but I don't know where the problem lies.I would be very…
-
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 (…
-
Title, flipping levers / opening linked doors feels bad.
-
Hits and MRR are another widely-used metrics for link prediction. Can we see the same patterns as AUC-ROC?
-
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!
-
In `generate_data.ipynb`, there is no processing code for citeseer dataset for the link prediction task.
-
I was going through the CVPR paper "Rethinking Human Motion Prediction with Symplectic Integral" and would like to try the model. However, the link from the paper brought me to an empty repo. Can I kn…
-
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…