-
Notifications
You must be signed in to change notification settings - Fork 3.8k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
A New Dataset: City Networks of Long Range Dependency for Transductive Node Classification #10086
base: master
Are you sure you want to change the base?
Conversation
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thank you for the contribution! Could you share the expected test accuracy as a baseline?
class CityNetwork(InMemoryDataset): | ||
r"""The City-Networks are introduced in | ||
`"Towards quantifying long-range interactions in graph machine learning" | ||
<https://arxiv.org/abs/>`_ paper. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Incomplete URL?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hello Serge,
Thank you for reviewing our pull request!
We are still finalizing the baseline results on our dataset. Is it okay to get back to you after we upload our paper online next week?
Best,
Leon
Dear PyG Team,
This is Leon from Oxford EngSci, our research group has just constructed a new dataset of four city networks for transductive node classification and we are about to release the paper very soon. We believe integrating our dataset into PyG will greatly help the other researchers to download and run this dataset more conveniently.
I have modified our code to be consistent with other previous datasets and tested it on my side. However, since I am not very familiar with contributing to open-sourced projects, I am afraid there might be still some unexpected bugs.
I have also sent an email to Matthias, and please let me know if you need any further information.
Best regards,
Huidong (Leon) Liang