-
I am trying to create a custom dataset. My `dataset.data` is `Data(edge_index=[2, 93003], edge_to_id=[1], test_mask=[93003], train_mask=[93003], val_mask=[93003], vertice_to_id=[1], y=[93003])`. The n…
-
**Is your feature request related to a problem? Please describe.**
Find a cloud storage service that 1) allows anyone with a link to upload files (something like the Dropbox file request); 2) automat…
-
### Describe the bug
I have been trying to reproduce the results from [kazemi2018](https://arxiv.org/pdf/1802.04868.pdf), without luck.
I have used both homemade pipelines and the one provided in …
-
-
**Describe the bug**
As titled, only around 5 datasets passed loading.
Possible because of https://github.com/Graph-Learning-Benchmarks/gli/pull/325
```
=========================================…
-
**Is your feature request related to a problem? Please describe.**
I have trained some of the models so far by using the parameters in the experiments config files and some of them have taken an hour…
-
## 🚀 Feature
The goal is to use the recently merged DGL data format #728 to host popular datasets.
## Dataset
- [x] KarateClub
- [x] TUDataset
- [x] Planetoid
- [x] CoraFull
- [x] Coauthor
-…
-
您好，我用的参数
INT threads = 8;
INT bernFlag = 0;
INT loadBinaryFlag = 0;
INT outBinaryFlag = 0;
INT trainTimes = 1000;
INT nbatches = 1;
INT dimension = 50;
REAL alpha = 0.001;
REAL margin = 1.0…
-
Hi, I'm trying to use your implementation of R-GCN to replicate the R-GCN paper results on dataset FB15K.
I have launched the training with
```bash
python3 link_predict.py -d FB15k --graph-batch…
-
We can use git-lfs [0] to include the weights of the trained model in this repository.
For HPO I would suggest to only save the best model; for reproducibility, all models are of interest.
[0] h…
mberr updated
2 years ago