-
**Description**
- Add missing dostrings (WN11, FB13)
- Add biblio references for each dataset (see slack for list)
- Add orginal URL from which dataset has been downloaded
- Update `installation.m…
-
### Description
There can be datasets with unseen entities from validation/test sets. This results in the library crashes.
### Actual Behavior
The library crashes when evaluate performance for vali…
-
When i install on colab from souce, i get the finished output.
my command is
```
!git clone https://github.com/DeepGraphLearning/graphvite
%cd graphvite
!conda install -y --file conda/requirement…
-
**Background and Context**
The current examples require publicly available datasets in order to run. Obtaining these datasets manually may be tedious. This process should be automated.
**Descripti…
-
Thank you very much for your implementation. I just re-read your extended AAAI 2018 paper and see your updated results on WN18RR: MRR: 0.43 Hits@10: 0.52. You rounded the results to 2 decimal places. …
-
Hi, I have failed to reproduce results of ComplEx on WN18RR and FB15K237 reported in ConvE paper. I use an implementation of myself and it can reproduce results of FB15K and WN18 correctly. Could you …
-
You state
> Used in the paper, but do not use these datasets for your research: FB15k and WN18.
What is the problem with using these datasets? They are commonly used in this domain.
-
It seems that some enities in the testing set does not appear in the training set. So, about 210 number of triples in testing set are meaningless?
-
Hi, I have noticed that test.txt/valid.txt of WN18RR and FB15K237 contains entities that are not appear at train.txt,. It means that these entities will never be updated during the training, how to de…
-
I have tried the generic command for reproducing results in the paper for WN18RR dataset, but it could not reproduce MRR reported in the paper, I managed only to get `0.42`.
Which hyperparameters…