Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement
This work proposes a fast-slow parameter update strategy to implicitly approximate the up-to-date salient unlearning direction, free from specific modal constraints, and adaptable across computer vision unlearning tasks, including classification and generation.
Oct 7, 2024
Towards Natural Machine Unlearning
This method substantially reduces the over-forgetting and leads to strong robustness to hyperparameters, making it a promising candidate for practical machine unlearning.
May 24, 2024
Machine Unlearning by Suppressing Sample Contribution
This paper theoretically discover that the input sensitivity can approximately measure the contribution of the forgetting data and practically design an algorithm, called MU-Mis (machine unlearning via minimizing input sensitivity), to suppress the contribution of the forgetting data.
Feb 23, 2024