ViT-MUL: A Baseline Study on Recent Machine Unlearning Methods Applied to Vision Transformers

ViT-MUL: A Baseline Study on Recent Machine Unlearning Methods Applied to Vision Transformers

Machine unlearning (MUL) is an arising field in machine learning that seeks to erase the learned information of specific training data points from a trained model. Despite the recent active research in MUL within computer vision, the majority of work has focused on ResNet-based models. Given that Vi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2024-02
Hauptverfasser: Cho, Ikhyun, Park, Changyeon, Hockenmaier, Julia
Format: Artikel
Sprache:eng
Schlagworte:
Ablation
Algorithms
Computer vision
Data points
Machine learning
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Cho, Ikhyun
Park, Changyeon
Hockenmaier, Julia
description Machine unlearning (MUL) is an arising field in machine learning that seeks to erase the learned information of specific training data points from a trained model. Despite the recent active research in MUL within computer vision, the majority of work has focused on ResNet-based models. Given that Vision Transformers (ViT) have become the predominant model architecture, a detailed study of MUL specifically tailored to ViT is essential. In this paper, we present comprehensive experiments on ViTs using recent MUL algorithms and datasets. We anticipate that our experiments, ablation studies, and findings could provide valuable insights and inspire further research in this field.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2962927334</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2962927334</sourcerecordid><originalsourceid>FETCH-proquest_journals_29629273343</originalsourceid><addsrcrecordid>eNqNi70KwjAURoMgKNp3uOBcqElbf7YqioNdtO0mEuxVU2JSc9PBt1fBB3D64Jzz9diQCzEN5zHnAxYQNVEU8XTGk0QM2alSRZiX-yVksJKEWhmEo-_qF1gDB7yg8ZDLy_3LS6NROqPMDXL0d1sTZG2rFdbgLVSK1OdTOGnoat0DHY1Z_yo1YfDbEZtsN8V6F7bOPjskf25s58xHnfki5Qs-EyIW_1VvJctCnw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2962927334</pqid></control><display><type>article</type><title>ViT-MUL: A Baseline Study on Recent Machine Unlearning Methods Applied to Vision Transformers</title><source>Free E- Journals</source><creator>Cho, Ikhyun ; Park, Changyeon ; Hockenmaier, Julia</creator><creatorcontrib>Cho, Ikhyun ; Park, Changyeon ; Hockenmaier, Julia</creatorcontrib><description>Machine unlearning (MUL) is an arising field in machine learning that seeks to erase the learned information of specific training data points from a trained model. Despite the recent active research in MUL within computer vision, the majority of work has focused on ResNet-based models. Given that Vision Transformers (ViT) have become the predominant model architecture, a detailed study of MUL specifically tailored to ViT is essential. In this paper, we present comprehensive experiments on ViTs using recent MUL algorithms and datasets. We anticipate that our experiments, ablation studies, and findings could provide valuable insights and inspire further research in this field.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Ablation ; Algorithms ; Computer vision ; Data points ; Machine learning</subject><ispartof>arXiv.org, 2024-02</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Cho, Ikhyun</creatorcontrib><creatorcontrib>Park, Changyeon</creatorcontrib><creatorcontrib>Hockenmaier, Julia</creatorcontrib><title>ViT-MUL: A Baseline Study on Recent Machine Unlearning Methods Applied to Vision Transformers</title><title>arXiv.org</title><description>Machine unlearning (MUL) is an arising field in machine learning that seeks to erase the learned information of specific training data points from a trained model. Despite the recent active research in MUL within computer vision, the majority of work has focused on ResNet-based models. Given that Vision Transformers (ViT) have become the predominant model architecture, a detailed study of MUL specifically tailored to ViT is essential. In this paper, we present comprehensive experiments on ViTs using recent MUL algorithms and datasets. We anticipate that our experiments, ablation studies, and findings could provide valuable insights and inspire further research in this field.</description><subject>Ablation</subject><subject>Algorithms</subject><subject>Computer vision</subject><subject>Data points</subject><subject>Machine learning</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNi70KwjAURoMgKNp3uOBcqElbf7YqioNdtO0mEuxVU2JSc9PBt1fBB3D64Jzz9diQCzEN5zHnAxYQNVEU8XTGk0QM2alSRZiX-yVksJKEWhmEo-_qF1gDB7yg8ZDLy_3LS6NROqPMDXL0d1sTZG2rFdbgLVSK1OdTOGnoat0DHY1Z_yo1YfDbEZtsN8V6F7bOPjskf25s58xHnfki5Qs-EyIW_1VvJctCnw</recordid><startdate>20240207</startdate><enddate>20240207</enddate><creator>Cho, Ikhyun</creator><creator>Park, Changyeon</creator><creator>Hockenmaier, Julia</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20240207</creationdate><title>ViT-MUL: A Baseline Study on Recent Machine Unlearning Methods Applied to Vision Transformers</title><author>Cho, Ikhyun ; Park, Changyeon ; Hockenmaier, Julia</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_29629273343</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Ablation</topic><topic>Algorithms</topic><topic>Computer vision</topic><topic>Data points</topic><topic>Machine learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Cho, Ikhyun</creatorcontrib><creatorcontrib>Park, Changyeon</creatorcontrib><creatorcontrib>Hockenmaier, Julia</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Cho, Ikhyun</au><au>Park, Changyeon</au><au>Hockenmaier, Julia</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>ViT-MUL: A Baseline Study on Recent Machine Unlearning Methods Applied to Vision Transformers</atitle><jtitle>arXiv.org</jtitle><date>2024-02-07</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>Machine unlearning (MUL) is an arising field in machine learning that seeks to erase the learned information of specific training data points from a trained model. Despite the recent active research in MUL within computer vision, the majority of work has focused on ResNet-based models. Given that Vision Transformers (ViT) have become the predominant model architecture, a detailed study of MUL specifically tailored to ViT is essential. In this paper, we present comprehensive experiments on ViTs using recent MUL algorithms and datasets. We anticipate that our experiments, ablation studies, and findings could provide valuable insights and inspire further research in this field.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2024-02
issn 2331-8422
language eng
recordid cdi_proquest_journals_2962927334
source Free E- Journals
subjects Ablation
Algorithms
Computer vision
Data points
Machine learning
title ViT-MUL: A Baseline Study on Recent Machine Unlearning Methods Applied to Vision Transformers
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-10T04%3A07%3A24IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=ViT-MUL:%20A%20Baseline%20Study%20on%20Recent%20Machine%20Unlearning%20Methods%20Applied%20to%20Vision%20Transformers&rft.jtitle=arXiv.org&rft.au=Cho,%20Ikhyun&rft.date=2024-02-07&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2962927334%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2962927334&rft_id=info:pmid/&rfr_iscdi=true