PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
February 23, 20240 citationsOpen Access

Machine Unlearning by Suppressing Sample Contribution

View Full Paper
XCXinwen ChengZHZhehao HuangXHXiaolin Huang

Key Points

Key points are not available for this paper at this time.

Abstract

Machine Unlearning (MU) is to forget data from a well-trained model, which is practically important due to the "right to be forgotten". In this paper, we start from the fundamental distinction between training data and unseen data on their contribution to the model: the training data contributes to the final model while the unseen data does not. We theoretically discover that the input sensitivity can approximately measure the contribution and practically design an algorithm, called MU-Mis (machine unlearning via minimizing input sensitivity), to suppress the contribution of the forgetting data. Experimental results demonstrate that MU-Mis outperforms state-of-the-art MU methods significantly. Additionally, MU-Mis aligns more closely with the application of MU as it does not require the use of remaining data.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Cheng et al. (2024) studied this question.

synapsesocial.com/papers/68e77f50b6db6435876f2d43https://doi.org/10.48550/arxiv.2402.15109
Ask AI
Helpful
Bookmark
Share
View Full Paper