This is the official repository for our ICML paper:
No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning Datasets
which introduces RINGS: a perturbation framework for attributed graphs, designed to facilitate better evaluations of GL benchmarks using first principles.
This repository is under active development. We’ve made it public early to invite feedback, discussion, and transparency as we transition from research prototypes to a stable, user-friendly package.
In the coming weeks, we’ll be releasing updates, architectural notes, and implementation details via a series of pull requests. You're welcome to follow along, open issues, or suggest improvements!
We are developing a community-friendly implementation of the RINGS framework introduced in the paper. Our goal is to make it easy for the graph learning community to:
- Apply dataset perturbations tailored to graph learning benchmarks
- Conduct more rigorous and insightful evaluations of graph-based models
- Encourage better dataset practices and evaluation hygiene across the field
If you have feedback on the paper or suggestions for how this package can better integrate with popular frameworks, please feel free to reach out to the authors.
Stay tuned!