Pith. sign in

REVIEW 4 cited by

DUCK: Distance-based Unlearning via Centroid Kinematics

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2312.02052 v2 pith:LKB2VW7F submitted 2023-12-04 cs.CV cs.LG

DUCK: Distance-based Unlearning via Centroid Kinematics

classification cs.CV cs.LG
keywords unlearningcentroidduckperformanceremovalalgorithmconducteddata
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Machine Unlearning is rising as a new field, driven by the pressing necessity of ensuring privacy in modern artificial intelligence models. This technique primarily aims to eradicate any residual influence of a specific subset of data from the knowledge acquired by a neural model during its training. This work introduces a novel unlearning algorithm, denoted as Distance-based Unlearning via Centroid Kinematics (DUCK), which employs metric learning to guide the removal of samples matching the nearest incorrect centroid in the embedding space. Evaluation of the algorithm's performance is conducted across various benchmark datasets in two distinct scenarios, class removal, and homogeneous sampling removal, obtaining state-of-the-art performance. We also introduce a novel metric, called Adaptive Unlearning Score (AUS), encompassing not only the efficacy of the unlearning process in forgetting target data but also quantifying the performance loss relative to the original model. Additionally, we conducted a thorough investigation of the unlearning mechanism in DUCK, examining its impact on the organization of the feature space and employing explainable AI techniques for deeper insights.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Jellyfish: Zero-Shot Federated Unlearning Scheme with Knowledge Disentanglement

    cs.CR 2026-04 unverdicted novelty 6.0

    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.

  2. POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse

    cs.CV 2025-11 unverdicted novelty 6.0

    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...

  3. DECAF: De-Clustering for Adaptive Representational Unlearning

    cs.LG 2026-07 conditional novelty 5.0

    DECAF is a forget-only unlearning method that adds input noise, suppresses the forget-class probability, and diversifies outputs, achieving 0.10% forget accuracy and 79.4% retain accuracy on CIFAR-10/ResNet-18 while d...

  4. Erased, but Not Gone: Output Forgetting Is Not True Forgetting

    cs.LG 2026-06 unverdicted novelty 5.0

    Output forgetting in machine unlearning overestimates success because unlearned models exhibit structured representation mismatches relative to retraining from scratch.