-
Notifications
You must be signed in to change notification settings - Fork 105
New issue
Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? # to your account
Bugs of subgraph augmentation #24
Comments
@hyp1231 Thank you for your carefulness! You are right that the current version only contrasting with small one-hop subgraphs (similar to InfoGraph, global-local contasting), due to my typo. In my later version of the my internal code (will be released in the future), I fixed this bug (simply let A sample of the improved subgraph function:
|
@yyou1996 Thanks for your kind and quick response! BTW, another concern is, whether controling the scale of subgraph has a slight influence to the performance. In the original version of the released code, we have GraphCL/transferLearning_MoleculeNet_PPI/bio/loader.py Lines 288 to 292 in 7eefcc3
|
According to my limited observation, I dont feel it affects too much on performance, compared with the augmentation type. Of course, we did not do explicit ablation on the augmentation strength. I feel type of aug represents more of the prior, rather than strength. Also, I am happy to hear some other opinions. |
Thanks, it's clear and makes sense. Feel free to close this issue. Thank you again. |
Hi,
when browsing the code, I found there might be bugs in the subgraph augmentation.
In Python 3.7+, the
union
operation is not an inplace operation, so thatidx_neigh
will not be updated properly. In this situation, only 1-hop subgraph of a random centor node will be generated.Some examples:
GraphCL/semisupervised_TU/pre-training/tu_dataset.py
Line 251 in e9e598d
GraphCL/unsupervised_TU/aug.py
Line 371 in e9e598d
GraphCL/transferLearning_MoleculeNet_PPI/bio/loader.py
Line 310 in e9e598d
GraphCL/transferLearning_MoleculeNet_PPI/chem/loader.py
Line 844 in e9e598d
The text was updated successfully, but these errors were encountered: