Docs: Add "Unlearning Comparator" as a related resource for small-scale prototyping #146
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Outdated suggestions cannot be applied.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.
Thank you for creating and maintaining this excellent repository. it’s a tremendous service to the community.
I’m the first author of the paper and system “Unlearning Comparator” (a visualization tool for comparing unlearning methods on vision classification). Many researchers start by prototyping ideas in simpler setups before scaling to LLM-focused benchmarks; the tool is meant to support that first step.
Change summary:
If you are new to unlearning or want to prototype on small-scale vision tasks first, try Unlearning Comparator
— an interactive system to visualize and compare unlearning methods. Insights gained here can be used to robustly scale up to the LLM-focused benchmarks in this repo.
Placement:
under 📚 Further Documentation, directly below the table and above Support & Contributors.
Links:
Repo: Machine-Unlearning-Comparator
Paper: arXiv under TVCG revision
I’ve kept the wording minimal and avoided listing it as a core component to respect the repo’s LLM scope. I’m happy to adjust the phrasing or placement if you prefer something different.
Thank you for your consideration!
Best Regards,
Jaeung Lee