-
Thanks for your work!
The core of your work is using the target domain data to train the adapter. May I ask what data are used for the training? Is it understandable that one support image, one suppo…
-
Hi, I'm wondering if the project is considering supporting inductive datasets, such as 20NewsGroups (used in many articles).
-
Hi, I read your paper "Unveiling Hidden Links Between Unseen Security Entities" and tried to reproduce it. However, I was unable to improve the MRR when I directly used ULTRA to fine-tune the threat k…
jr011 updated
6 months ago
-
Hello, first off, this tool is it works really well. I am inspired by you all. My name is Bradford Patton, I got to school at Meharry Medical College. I am having one issue of adding my own knowledge …
-
Hello,
I want to know what evaluation metric is used for protein function classification.
I scrutinized the paper and code, but could not found how it was evaluated.
In the paper I found the descri…
-
Hello team,
Thank you for your excellent work! I used your `ultra_50g.pth` to do the inference (zero-shot learning) on my own dataset with the purpose to find the new links between entities. I eval…
-
Hi! Thanks for sharing your great work!
Could you possibly share the inductive split dataset and also the negative samples used for evaluation? I believe it's quite important for correctly benc…
-
### 🐛 Describe the bug
Setup: running [ULTRA](https://github.com/DeepGraphLearning/ULTRA) and, in particular, the [Generalized Relational Convolution](https://github.com/DeepGraphLearning/ULTRA/blo…
-
Starting this issue for tracking the learning progress of GNN
-
hi, your code is causing label leakage.
You used the test and validation sets and edge information during training
wandb_train.py
self.all_edge_index include test edge,val edge
def train(s…