-
Hello,
In this, python owe/run_open_world.py -t -c -d -- ,What does refer to?
I wonder what kind of file it is? And how should this file be obtained?
-
Hello, I am trying to replicate the steps to train and test the model. After performing the data processing and pretraining of embeddings, I keep encountering the following runtime error when trainin…
-
Hi,
Thanks for the great work! Could you also share the KGC datasets fb15k-237 and WN18RR (the same format as wikidata5m)? BTW, I also see the dataset codex-m in the shared data but did not find re…
-
Hi, i want to know how many time is needed for testing link prediction task?
I figured out that it will costs 1-2 days for WN18RR link prediction using A100. The utilization of gpu is 0%. And chan…
-
Hi, I am very interested in your paper especially the part about node indegree study. I have checked the FB15k-237 dataset, but I found that the indegree of nodes is almost less than 100. So please ca…
-
你好，非常感谢你的代码，但是在运行ConvR模型时，最后测试集分别取头实体、尾实体预测结果的均值为指标，要远差于论文中ConvR在FB15k-237中对hit@10的0.528，请问有什么解决方法吗
-
Hi, I'm interested in how to get the generated logic rules in Table 4 and Table 7 as your paper shows. And I can't find the relations in the dataset of FB15k-237 as what you have mentioned in Table 4 …
-
I change the model to point.rs.conve.
In fact, there doesn't exist error, but a userwanrning like follows:
_**_"‘UserWarning: RNN module weights are not part of single contiguous chunk of memory. T…
-
This is in comparison to pytorch geometric(some datasets might need to be re verified since they might be implemented in umbrella datasets like OGB):
- [x] Chickenpox
- [x] CiteSeer
- [x] Cora
-…
-
Hello, I need a lot of time in the process of obtaining new _ dev.dict of fb15k-237 data set. Note that there is new _ dev.dict of wn18rr data set in your file, but there is no new _ dev.dict of fb15k…