Jekyll2025-01-03T14:05:56+00:00unlearning-challenge.github.io/feed.xmlNeurIPS 2023 Machine Unlearning ChallengeWebsite for the NeurIPS 2023 Machine Unlearning Challenge.Competition has now ended2023-12-06T00:00:00+00:002023-12-06T00:00:00+00:00unlearning-challenge.github.io/announcements/2023/12/06/competition-endedHi everyone,

The competition has now ended. You can read about winning submissions on kaggle’s discussion board.

We’ll release more details about the competition, as well as the code for the evaluation metric in the next couple of months. Stay tuned!

]]>Competition launched!2023-09-11T00:00:00+00:002023-09-11T00:00:00+00:00unlearning-challenge.github.io/announcements/2023/09/11/starting-kit-announcementHi everyone,

We’re excited to announce that the unlearning challenge is now open for submissions on Kaggle! We will accept submissions until November 27, 2023.

We recommend using this starting notebook for making a submission, and simply replacing the contents of the unlearning function. Please see the Kaggle page for more information on how to make a submission.

We are also excited to release our write-up with a formal definition of unlearning, linking it to Differential Privacy, and a description of the metric and evaluation protocol that we use in the challenge.

We look forward to receiving your submissions!

]]>Starting kit now available2023-06-28T00:00:00+00:002023-06-28T00:00:00+00:00unlearning-challenge.github.io/announcements/2023/06/28/starting-kit-announcementWe are excited to announce the availability of a starting kit for the NeurIPS 2023 Machine Unlearning Challenge! This starting kit provides a foundation for participants to build their unlearning models on the CIFAR-10 dataset.

The starting kit includes: a Jupyter notebook with code to:

  • load the CIFAR-10 dataset;
  • train a baseline unlearning model; and
  • score it using a membership inference attack.

The API used in this baseline unlearning method will be the same one that participants will submit once the competition opens. Hence, we hope that this starting kit will help participants get started in developing and trying out their unlearning methods.

The starting kit can be accessed at https://github.com/unlearning-challenge/starting-kit.

We hope this starter kit will be helpful to participants as they prepare for the challenge. Please let us know if you have questions through the group unlearning-challenge or our email unlearning@chalearn.org.

Thank you for your interest in the NeurIPS 2023 Machine Unlearning Challenge!

]]>