-
dear bro, very lucky to be able to read such a good paper, and open source, when I run the program, some errors occurred, the same server, when I use the data set FB15K, he is working, when I changed …
-
Hi,
I have a graph based on the wordnet knowledge base. I want to convert each relation edge into a vector with ConvE and TransE model using pykg2vec. Can anyone help me with the same?
Thanks!
-
I am trying to reproduce results, as well as try a new dataset, FB15K-237; I'd appreciate any thoughts you have (see questions at the end):
**Reproducing FB15K results**: I am using Windows10, pyto…
drcdr updated
4 years ago
-
Is there a bug on WN18? just on FB15k-237?
-
The manuscript describes the creation of a new biomedical knowledge graph to use as a benchmark for link prediction. One of the first questions I had was the manuscript did not discuss previously prep…
-
Could you please provide the training parameters of 4 datasets(FB15K, FB15K237, WN18, WN11), since I can't reproduce the result in the paper.
-
你好，TranE代码似乎并没有预设为最优的参数，直接跑的结果和transE论文有所差距，但是按照原论文Translating Embeddings for Modeling Multi-relational Data (2013) 中的参数来跑，结果竟然差得离谱，想请教一下参数如何设定才能跑出原论文以及TransR论文中的结果。以下是我再WN18上直接运行代码的结果;
18 40943
lef…
-
## 🐛 Bug
I try to use RGCN in wn18 ，but i get something wrong when evaluation starts,can you help me?
and it works well in FB15k-237 (has the same data format with the wn18).I wonder why this cod…
-
thanks for your sharing, could you please support some data link to download in your code, thx
-
Hello,
I found that when I run the doctest in the protocol.py (ampligraph/evaulation/protocol.py), each triple has two ranks when I call evaluate_performance, but if I call model.predict, I got onl…