Towards Understanding the Feasibility of Machine Unlearning
In light of recent privacy regulations, machine unlearning has attracted significant attention in the research community. However, current studies predominantly assess the overall success of unlearning approaches, overlooking the varying difficulty of unlearning individual training samples. As a res...
Saved in:
Main Authors | , , |
---|---|
Format | Journal Article |
Language | English |
Published |
03.10.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | In light of recent privacy regulations, machine unlearning has attracted
significant attention in the research community. However, current studies
predominantly assess the overall success of unlearning approaches, overlooking
the varying difficulty of unlearning individual training samples. As a result,
the broader feasibility of machine unlearning remains under-explored. This
paper presents a set of novel metrics for quantifying the difficulty of
unlearning by jointly considering the properties of target model and data
distribution. Specifically, we propose several heuristics to assess the
conditions necessary for a successful unlearning operation, examine the
variations in unlearning difficulty across different training samples, and
present a ranking mechanism to identify the most challenging samples to
unlearn. We highlight the effectiveness of the Kernelized Stein Discrepancy
(KSD), a parameterized kernel function tailored to each model and dataset, as a
heuristic for evaluating unlearning difficulty. Our approach is validated
through multiple classification tasks and established machine unlearning
algorithms, demonstrating the practical feasibility of unlearning operations
across diverse scenarios. |
---|---|
DOI: | 10.48550/arxiv.2410.03043 |