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.
@article{arxiv.2410.03043,
title = {Instance-Level Difficulty: A Missing Perspective in Machine Unlearning},
author = {Hammad Rizwan and Mahtab Sarvmaili and Hassan Sajjad and Ga Wu},
journal= {arXiv preprint arXiv:2410.03043},
year = {2025}
}