-
### Description
To train the GraphSAGE or HinSAGE model without node attributes we currently need use a one-hot input feature matrix which is computationally intractable for a large number of nodes. …
-
what is the use of x in load_data function as from what I see it's just loaded and isn't used, but the one used is allx, what are the differences between them.
-
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…
-
Difference of the model design.
It seems the difference is that GraphSAGE sample the data.
But what is the difference in model architecture.
Thank you very much.
@tkipf
-
Hi,
I have allx but i do not have ally (tagged labels) in this case how to make model train in semi-supervised (inductive learning) as mentioned in https://github.com/kimiyoung/planetoid way. Pleas…
-
## General Information
Author: William L. Hamilton, Rex Ying, and Jure Leskovec
Published: 2017
## Why and What
### Key word
Inductive learning is learning from the specific data and reasoning …
-
## 📚 Documentation
We should demonstrate the power of GNN in inductive learning. That is, when a new node comes to a graph, we can apply GNN to do a good prediction.
-
Post your questions here about: “[Network Learning](https://docs.google.com/document/d/1hjXUvBRS779HDvbYXMKjyVbO3wVg6SaWNtxwof6s6LM/edit?usp=sharing)” & “Knowledge and Table Learning”, Thinking with D…
-
Hi Dr. Afifi, Thanks for your great work!
I have read many of your inspiring papers about color constancy. From a private point of view, most of your papers are elegant enough and easy to understand…
-
# jargon 리스트
- [x] transduction model
- [x] constituency parsing
- [x] sinusoids
- [x] Positional Encodings
- [x] BLEU
- [x] WMT
- [x] factorization tricks
- [x] desiderata
- [x] transform…