MétaCan
Menu
Back to cohort
Record W4415706964 · doi:10.1109/tai.2025.3627517

MaxDiv: Zero-Shot Machine Unlearning via Distributionally Divergent Erasing Samples

2025· article· W4415706964 on OpenAlexafffund
Sayedmoslem Shokrolahi, I.-M. Kim

Bibliographic record

VenueIEEE Transactions on Artificial Intelligence · 2025
Typearticle
Language
FieldComputer Science
TopicDomain Adaptation and Few-Shot Learning
Canadian institutionsQueen's University
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsForgettingOrder (exchange)Training setMachine translationEmpirical research

Abstract

fetched live from OpenAlex

For the sake of data privacy, erasing some knowledge that was acquired during the original training emerges as a pivotal necessity, which is called machine unlearning. Particularly, when the model does not have access to the original training data, such unlearning is even more difficult. In this paper, we address the challenging problem of zero-shot machine unlearning by introducing an innovative approach, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MaxDiv</i>, which generates specially crafted erasing samples. These samples are strategically generated by negating the distributions of the data to be forgotten. We also integrate knowledge distillation techniques into MaxDiv in order to prevent the catastrophic forgetting about the information to be retained. Through extensive empirical evaluations conducted on MNIST, SVHN, CIFAR-10, CIFAR-100, and TinyImageNet datasets, our proposed zero-shot unlearning paradigm showcases superior performance compared to the current state-of-the-art methods.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Science and technology studies, Scholarly communication, Insufficient payload (model declined to judge)
Consensus categoriesInsufficient payload (model declined to judge)
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.975
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.003
Science and technology studies0.0030.001
Scholarly communication0.0010.001
Open science0.0010.000
Research integrity0.0000.002
Insufficient payload (model declined to judge)0.0020.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.072
GPT teacher head0.315
Teacher spread0.243 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; both teacher heads agree on what is shown here.

Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes2
Has abstractyes

Explore more

Same venueIEEE Transactions on Artificial IntelligenceSame topicDomain Adaptation and Few-Shot LearningFrench-language works237,207