Machine Unlearning via Null Space Calibration

Date

2024

Authors

Chen, H.
Zhu, T.
Yu, X.
Zhou, W.

Editors

Larson, K.

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

Citation

IJCAI International Joint Conference on Artificial Intelligence, 2024 / Larson, K. (ed./s), pp.358-366

Statement of Responsibility

Huiqiang Chen, Tianqing Zhu, Xin Yu, Wanlei Zhou

Conference Name

International Joint Conference on Artificial Intelligence (IJCAI) (3 Aug 2024 - 9 Aug 2024 : Jeju, South Korea)

Abstract

Machine unlearning aims to enable models to forget specific data instances when receiving deletion requests. Current research centers on efficient unlearning to erase the influence of data from the model and neglects the subsequent impacts on the remaining data. Consequently, existing unlearning algorithms degrade the model's performance after unlearning, known as over-unlearning. This paper addresses this critical yet under-explored issue by introducing machine Unlearning via Null Space Calibration (UNSC), which can accurately unlearn target samples without over-unlearning. On the contrary, by calibrating the decision space during unlearning, UNSC can significantly improve the model's performance on the remaining samples. In particular, our approach hinges on confining the unlearning process to a specified null space tailored to the remaining samples, which is augmented by strategically pseudo-labeling the unlearning samples. Comparison against several established baselines affirms the superiority of our approach.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

Copyright © 2024 International Joint Conferences on Artificial Intelligence All rights reserved. No part of this book may be reproduced in any form by any electronic or mechanical means (including photocopying, recording, or information storage and retrieval) without permission in writing from the publisher.

License

Call number

Persistent link to this record