Pith. sign in

REVIEW 2 cited by

Random Relabeling for Efficient Machine Unlearning

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 2305.12320 v1 pith:AGRSFCSU submitted 2023-05-21 cs.LG cs.CR

classification cs.LGcs.CR
keywords datalearningmachineunlearningalgorithmsremovalefficienthowever
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Learning algorithms and data are the driving forces for machine learning to bring about tremendous transformation of industrial intelligence. However, individuals' right to retract their personal data and relevant data privacy regulations pose great challenges to machine learning: how to design an efficient mechanism to support certified data removals. Removal of previously seen data known as machine unlearning is challenging as these data points were implicitly memorized in training process of learning algorithms. Retraining remaining data from scratch straightforwardly serves such deletion requests, however, this naive method is not often computationally feasible. We propose the unlearning scheme random relabeling, which is applicable to generic supervised learning algorithms, to efficiently deal with sequential data removal requests in the online setting. A less constraining removal certification method based on probability distribution similarity with naive unlearning is further developed for logit-based classifiers.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Multi-Objective Large Language Model Unlearning

    cs.CL 2024-12 conditional novelty 5.0 of 10

    MOLLM formulates LLM unlearning as a three-objective optimization problem and uses a bounded unlearning loss plus a common descent direction to forget target data while preserving model utility.

  2. Verifying Machine Unlearning with Explainable AI

    cs.LG 2024-11 conditional novelty 5.0 of 10

    The authors use SIDU heatmaps and two new metrics to test whether machine unlearning removes reliance on human patterns in a thermal object-counting model.

Pith tools