政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/157012

English | 正體中文 | 简体中文 | Post-Print筆數 : 27 | 全文筆數/總筆數 : 116028/147069 (79%)
造訪人次 : 58204744 線上人數 : 17

RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.

政大機構典藏 > 資訊學院 > 資訊科學系 > 會議論文 > Item 140.119/157012

請使用永久網址來引用或連結此文件: https://nccur.lib.nccu.edu.tw/handle/140.119/157012

題名:	Investigation of Feature Distribution and Network Weight Updates in the Machine Unlearning Process
作者:	廖文宏 Liao, Wen-Hung;Lin, Yang-Jing
貢獻者:	資訊系
關鍵詞:	Machine Unlearning;Label Reassignment;Model Manipulation;Weight Pruning
日期:	2024-12
上傳時間:	2025-05-19 11:44:30 (UTC+8)
摘要:	Machine unlearning refers to the process of expunging previously learned information and data from a machine learning model to achieve the objective of privacy protection. In this research, we explore two prevalent methods for unlearning, namely, label reassignment and model manipulation. Using the CIFAR-100 classification problem with ResNet-50 architecture as an example, we examine the efficacy of these two mechanisms and their variants in the corresponding unlearning task. We further investigate the changes in feature distribution and the extent of weight updates across various network layers throughout the unlearning process. Experimental results indicate that the degree of network variation is proportional to the number of removed classes. When employing the label reassignment method, the variation is concentrated in the final stage and fully connected layers. On the other hand, using the weight resetting strategy affects more network layers, with the impact gradually decreasing from the later layers to the middle and earlier layers. Overall, when the categories to be forgotten are less than 10%, no significant impact on feature extraction is observed.
關聯:	2024 International Symposium on Multimedia (ISM), IEEE Technical Committee on Multimedia (TCMC)
資料類型:	conference
DOI 連結:	https://doi.org/10.1109/ISM63611.2024.00022
DOI:	10.1109/ISM63611.2024.00022
顯示於類別:	[資訊科學系] 會議論文

文件中的檔案:

檔案	描述	大小	格式	瀏覽次數
index.html		0Kb	HTML	34	檢視/開啟

在政大典藏中所有的資料項目都受到原著作權保護.

社群 sharing

著作權政策宣告 Copyright Announcement

1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。
NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.

資料載入中.....