Show HN: Unlearning Comparator, a visual tool to compare machine unlearning
jaeunglee Monday, July 07, 2025I built Unlearning Comparator, a visual analytics toolkit to help researchers and developers compare how different machine unlearning methods work. It provides a unified workflow to test for accuracy, efficiency, and privacy. You can check out the live demo linked in the post, and the source code is on GitHub: https://github.com/gnueaj/Machine-Unlearning-Comparator Our accompanying paper is currently under review at IEEE TVCG. Happy to answer any questions and would love to hear your feedback!
Summary
The article explores a novel technique called 'Machine Unlearning' that enables the selective removal of specific data points from a trained machine learning model, without retraining the entire model from scratch. This process can be useful for updating models, addressing privacy concerns, or correcting mistakes in the training data.
40
2
Summary
gnueaj.github.io