Add CityNetwork dataset for testing long range dependency
#10115
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Contributor
Author
|
@wsad1 Hello Jinu! Thanks for helping us with the PR! Could you please help us review the new changes? Please let me know if you need any information from us! Best, |
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
akihironitta
approved these changes
May 2, 2025
Member
akihironitta
left a comment
akihironitta
left a comment
There was a problem hiding this comment.
Great work, thank you for your contribution!
akihironitta
changed the title
CityNetwork dataset for testing long range dependency
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## master #10115 +/- ##
==========================================
- Coverage 86.11% 85.41% -0.70%
==========================================
Files 496 496
Lines 33655 33993 +338
==========================================
+ Hits 28981 29036 +55
- Misses 4674 4957 +283 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
Contributor
Author
Thank you Akihiro for helping us with the PR!😃 |
rusty1s
added a commit
that referenced
this pull request
Jun 3, 2025
Dear PyG Team, Thank you for your effort in supporting our graph learning community! This is Huidong from the _Machine Learning Research Group_ at _University of Oxford_. As a follow-up to our recent PR[[#10115]](#10115) of the [_**CityNetwork**_](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.datasets.CityNetwork.html?highlight=city#torch_geometric.datasets.CityNetwork) dataset, we now release **_Total Influence_**, a measurement introduced in our [paper](https://arxiv.org/abs/2503.09008) which quantifies the long-range dependency in GNNs. Additionally, we also fixed some typos and slightly modified the comment description of CityNetwork in this current PR. Please let me know if you need further information from me. Thanks again for helping us with our work! Huidong Liang PhD Student @ MLRG Department of Engineering Science Univeristy of Oxford --------- Co-authored-by: Leon <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Matthias Fey <[email protected]>
chrisn-pik
pushed a commit
to chrisn-pik/pytorch_geometric
that referenced
this pull request
Jun 30, 2025
…eam#10263) Dear PyG Team, Thank you for your effort in supporting our graph learning community! This is Huidong from the _Machine Learning Research Group_ at _University of Oxford_. As a follow-up to our recent PR[[pyg-team#10115]](pyg-team#10115) of the [_**CityNetwork**_](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.datasets.CityNetwork.html?highlight=city#torch_geometric.datasets.CityNetwork) dataset, we now release **_Total Influence_**, a measurement introduced in our [paper](https://arxiv.org/abs/2503.09008) which quantifies the long-range dependency in GNNs. Additionally, we also fixed some typos and slightly modified the comment description of CityNetwork in this current PR. Please let me know if you need further information from me. Thanks again for helping us with our work! Huidong Liang PhD Student @ MLRG Department of Engineering Science Univeristy of Oxford --------- Co-authored-by: Leon <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Matthias Fey <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
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 just released our paper on arXiv. We believe integrating our dataset into PyG will greatly help other researchers download and run this dataset more conveniently.
For your reference, this is the previous Pull Request page where we did not update the paper link.
Best regards,
Huidong (Leon) Liang