-
### 🐛 What's wrong with my code from dgl to pyg？
I am transforming a dgl version code to pyg version code. The dgl one build a GraphSAGE model for transductive and inductive node classification on …
-
### Describe the workflow you want to enable
#### Graph-Based Clustering ([original repo link](https://github.com/dayyass/graph-based-clustering))
**Graph-Based Clustering** using connected comp…
-
Pose a question about one of the following articles:
“[DeepWalk: Online Learning of Social Representations](https://dl.acm.org/doi/pdf/10.1145/2623330.2623732)”, 2014. B. Perozzi, R. Al-Rfou, S. S…
-
Hi @migalkin , thanks for open-sourcing this great work, but I countered an issue when I was trying to run this demo on GPU by:
```
python script/run.py -c /home/ULTRA/config/transductive/inference.…
-
Dear Sir,
I ran the provided code and i can not reproduce the result in the paper. I wonder if the problem is in the random seed ? can you give a reproducible version?
I encounter the below situatio…
-
#### Describe the workflow you want to enable
The t-SNE embedding class has a fit_transform method, and a fit method, but doesnt contain a transform method. This in my understanding, is due to th…
-
Hello! Thank you for your excellent work.
I enjoyed reading your paper, and I am currently running some experiments with your code.
However, in inductive mode, it seems that the accuracy is bein…
-
Title: - Semi-supervised User Geolocation via Graph Convolutional Networks
Year: - 2018
Venue: - arXiv
**Main Problem**
The authors addresses the problem of inaccurate prediction of user geo-loc…
-
Hi Jin,
thanks for the refreshing work. I have a question regarding the split of target domain into training set and test set in the S→U and E→H evaluation.
As UCF101 and HMDB51 both have 3 split…
-
Hello,tkipf !
Thanks for your share! In the trainng process,features are 2708 dims, does it involve test samples? thank you very much!