Current studentsExisting staffContact us
 

Machine Unlearning via Null Space Calibration

Simple item page
dc.contributor.authorChen, H.
dc.contributor.authorZhu, T.
dc.contributor.authorYu, X.
dc.contributor.authorZhou, W.
dc.contributor.conferenceInternational Joint Conference on Artificial Intelligence (IJCAI) (3 Aug 2024 - 9 Aug 2024 : Jeju, South Korea)
dc.contributor.editorLarson, K.
dc.date.issued2024
dc.description.abstractMachine 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.
dc.description.statementofresponsibilityHuiqiang Chen, Tianqing Zhu, Xin Yu, Wanlei Zhou
dc.identifier.citationIJCAI International Joint Conference on Artificial Intelligence, 2024 / Larson, K. (ed./s), pp.358-366
dc.identifier.doi10.24963/ijcai.2024/40
dc.identifier.isbn9781956792041
dc.identifier.issn1045-0823
dc.identifier.orcidYu, X. [0000-0001-9890-5489] [0000-0002-0269-5649] [0000-0002-3388-9606] [0000-0002-6265-9519]
dc.identifier.urihttps://hdl.handle.net/2440/148989
dc.language.isoen
dc.publisherInternational Joint Conferences on Artificial Intelligence
dc.publisher.placeUnited States
dc.relation.granthttp://purl.org/au-research/grants/arc/DP230100246
dc.relation.granthttp://purl.org/au-research/grants/arc/DP240100955
dc.rightsCopyright © 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.
dc.source.urihttps://doi.org/10.24963/ijcai.2024/40
dc.subjectMachine unlearning
dc.subjectNull Space Calibration
dc.titleMachine Unlearning via Null Space Calibration
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Research Outputs