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!
Table of 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.