Saved in:
Bibliographic Details
Main Authors: Rizwan, Hammad, Sarvmaili, Mahtab, Sajjad, Hassan, Wu, Ga
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.03043
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913700987797504
author Rizwan, Hammad
Sarvmaili, Mahtab
Sajjad, Hassan
Wu, Ga
author_facet Rizwan, Hammad
Sarvmaili, Mahtab
Sajjad, Hassan
Wu, Ga
contents Current research on deep machine unlearning primarily focuses on improving or evaluating the overall effectiveness of unlearning methods while overlooking the varying difficulty of unlearning individual training samples. As a result, the broader feasibility of machine unlearning remains under-explored. This paper studies the cruxes that make machine unlearning difficult through a thorough instance-level unlearning performance analysis over various unlearning algorithms and datasets. In particular, we summarize four factors that make unlearning a data point difficult, and we empirically show that these factors are independent of a specific unlearning algorithm but only relevant to the target model and its training data. Given these findings, we argue that machine unlearning research should pay attention to the instance-level difficulty of unlearning.
format Preprint
id arxiv_https___arxiv_org_abs_2410_03043
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Instance-Level Difficulty: A Missing Perspective in Machine Unlearning
Rizwan, Hammad
Sarvmaili, Mahtab
Sajjad, Hassan
Wu, Ga
Machine Learning
Current research on deep machine unlearning primarily focuses on improving or evaluating the overall effectiveness of unlearning methods while overlooking the varying difficulty of unlearning individual training samples. As a result, the broader feasibility of machine unlearning remains under-explored. This paper studies the cruxes that make machine unlearning difficult through a thorough instance-level unlearning performance analysis over various unlearning algorithms and datasets. In particular, we summarize four factors that make unlearning a data point difficult, and we empirically show that these factors are independent of a specific unlearning algorithm but only relevant to the target model and its training data. Given these findings, we argue that machine unlearning research should pay attention to the instance-level difficulty of unlearning.
title Instance-Level Difficulty: A Missing Perspective in Machine Unlearning
topic Machine Learning
url https://arxiv.org/abs/2410.03043