-
Hey, we have integrated `SimGNN` into PyG, but the datasets are currently broken their since the dataset and GED information is no longer available in the Google Drive. Is it possible to re-upload the…
-
Hello,
I noticed there is an ant build file in the repo so I'm trying to build using it and I'm getting some compile errors that seem to indicate missing dependencies which I wasn't able to find in…
-
Hi! @yunshengb Thanks for your code!
I run main.py and got error at test(). Could you help me? Thanks!!!
Logs:
graph embedding 0.88906
[ 0.10863562 0.08224115 -0.00754932 0.06741448 0.161…
kxhit updated
5 years ago
-
Hi, thanks for the excellent work.
The precision_at_k in LINUX dataset is :
It seems …
-
Is there an implementation about how pickle file is generated for a dataset?
I would like to try SimGNN in the AIDS10K dataset.
Thanks in advance
-
Hi, I found that the error in SimGNN's paper is 0.001, but the error in your implementation results is 0.02, there is a ten-fold gap in the middle. I don't know why,I hope someone can give me an answe…
-
According to the paper:
> p@10 means the precision of finding the closest graph among the predicted top 10 most similar ones.
However, the code is to calculate precision at the lowest k elements. …
ghost updated
2 years ago
-
I hope to receive your reply
-
Hi, @yunshengb . Thank you for sharing your code and dataset.
However, there aren't test data, as mentioned another issue.
And, there are missing file on train set too.
Here is a error messag…
-
Can the labels in the data only represent the degree of the node? Or can it represent a numerical representation of arbitrary features? For example, I use 0 to represent a plane and 1 to represent a c…