ManiF-SMC uses manifold representation forgetting with self-mode connectivity to achieve approximate unlearning comparable to SOTA methods on four datasets while staying in representation space.
In Proceedings of the Thirty-First International Joint Conference on Artificial Intelli- gence, IJCAI 2022, Vienna, Austria, 23-29 July 2022 , Luc De Raedt (Ed.)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Approximate Machine Unlearning through Manifold Representation Forgetting Guided by Self Mode Connectivity
ManiF-SMC uses manifold representation forgetting with self-mode connectivity to achieve approximate unlearning comparable to SOTA methods on four datasets while staying in representation space.