메뉴 건너뛰기
소속 기관 / 학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
고객센터 ENG
주제분류

논문 기본 정보

저자정보
(Seoul National University of Science and Technology) (Seoul National University of Science and Technology) (Seoul National University of Science and Technology)
저널정보
Korean Institute of Information Scientists and Engineers 한국정보과학회 학술발표논문집 한국정보과학회 2024 한국컴퓨터종합학술대회 논문집
오류 신고하기

검색

    초록·키워드

    In response to stringent data regulation requirements, such as the GDPR's “right to be forgotten”, machine unlearning (MU) has become critical for removing specific datapoints from a given model. While exact unlearning offers a trivial solution by retraining the model from scratch without the samples to be erased, its high computational costs have prompted the development of a more efficient and viable solution, widely referred to as approximate unlearning. Despite claims that approximate unlearning achieves similar performance to exact unlearning, doubts remain about the completeness of data erasure, specifically whe ... 전체 초록 보기

    본문·목차

    최근 본 자료 전체보기