-
Hi! Thanks for your brilliant work! There are some parts in the code that I am confused about, I hope you can help me answer them!
What is the logic node I found in the data processing of the ARXIV d…
-
I didn't understand how to define the target triples that will be predicted. Could you enlighten me on this?
-
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…
-
您好！非常感激您在知识图谱的贡献以及开源代码方便后续的复现和研究工作，我在复现您的代码时遇到了问题，具体的问题是，当我运行完sh scripts/FreeBase/TransE_Rev_FB.sh后期望继续运行sh scripts/FreeBase/AnKnn_TransE_FB.sh，但是系统报错为：/code/AnKGE/output/kNN_candidate/FB15K237/TransE…
-
Hello, PyClause is a useful tool for rule learning. Thank you for your contributions !
I find a possible memory leaky problem.
```
# define data & rules & queries
rules, status = [...], [...]
…
-
Hi, I was trying to use your model in my project. I tried running the model on 10 clients. While I'm getting the same mrr in FedR mode as in the paper, I'm getting a way higher mrr in Single mode as c…
-
您好，我没有找到cp IterDE_FB15K237/transe_512.py ./python transe_512.py和cp IterDE_WN18RR/com_wn_512.py ./
python com_wn_512.py的文件
-
### 🐛 Describe the bug
Setup: running [ULTRA](https://github.com/DeepGraphLearning/ULTRA) and, in particular, the [Generalized Relational Convolution](https://github.com/DeepGraphLearning/ULTRA/blo…
-
有没有同学也遇到一样的问题啊，就是文章在这三个数据集上面结果和文章的差不多，但是在fb15k-237，wn18rr上面进行运行的时候，不管是Rela+TripleRE还是TripleRE，HITS@10指标都很好，但是MR和hits@1都非常差，只有零点几的样子，请问是我哪里设置错误了吗，但是理论上来说，就算是rela不适合FB15K这样的数据集上面，那我不用RELA只要tripleRE应该也不会…
-
Hi, thanks for your great work. I want to know how many gpu hours or epochs you need to get the reported results of fb1k5237 and wn18nn on your paper?