Machine-unlearning evaluation with a single training seed can misrepresent method performance, particularly for deterministic unlearning methods, and extra unlearning seeds do not fix it.
In: Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence
1 Pith paper cite this work, alongside 59 external citations. Polarity classification is still indexing.
1
Pith paper citing it
59
external citations · OpenAlex
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On the importance of multiple training seeds for evaluating machine unlearning
Machine-unlearning evaluation with a single training seed can misrepresent method performance, particularly for deterministic unlearning methods, and extra unlearning seeds do not fix it.