Jellyfish enables zero-shot federated unlearning through synthetic proxy data generation, channel-restricted knowledge disentanglement, and a composite loss with repair to forget target data while retaining model utility.
Duck: Distance- based unlearning via centroid kinematics
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
baseline 1polarities
baseline 1representative citing papers
POUR derives a provably optimal forgetting operator by showing that orthogonal projections of simplex equiangular tight frames remain ETFs in lower dimensions, enabling representation-level unlearning with closed-form and distillation variants.
Output forgetting in machine unlearning overestimates success because unlearned models exhibit structured representation mismatches relative to retraining from scratch.
citing papers explorer
-
Jellyfish: Zero-Shot Federated Unlearning Scheme with Knowledge Disentanglement
Jellyfish enables zero-shot federated unlearning through synthetic proxy data generation, channel-restricted knowledge disentanglement, and a composite loss with repair to forget target data while retaining model utility.
-
POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse
POUR derives a provably optimal forgetting operator by showing that orthogonal projections of simplex equiangular tight frames remain ETFs in lower dimensions, enabling representation-level unlearning with closed-form and distillation variants.
-
Erased, but Not Gone: Output Forgetting Is Not True Forgetting
Output forgetting in machine unlearning overestimates success because unlearned models exhibit structured representation mismatches relative to retraining from scratch.