MétaCan
Menu
Back to cohort
Record W4399151655 · doi:10.48550/arxiv.2405.17878

An Information Theoretic Evaluation Metric For Strong Unlearning

2024· preprint· en· W4399151655 on OpenAlexfundno aff
Dongjae Jeon, Wonje Jeung, Taeheon Kim, Albert No, Jonghyun Choi

Bibliographic record

VenuearXiv (Cornell University) · 2024
Typepreprint
Languageen
FieldMathematics
TopicAdvanced Statistical Methods and Models
Canadian institutionsnot available
FundersInstituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de MéxicoInstitute for Catastrophic Loss Reduction
KeywordsMetric (unit)Computer scienceMathematicsEconomicsOperations management

Abstract

fetched live from OpenAlex

Machine unlearning (MU) aims to remove the influence of specific data from trained models, addressing privacy concerns and ensuring compliance with regulations such as the ``right to be forgotten.'' Evaluating strong unlearning, where the unlearned model is indistinguishable from one retrained without the forgetting data, remains a significant challenge in deep neural networks (DNNs). Common black-box metrics, such as variants of membership inference attacks and accuracy comparisons, primarily assess model outputs but often fail to capture residual information in intermediate layers. To bridge this gap, we introduce the Information Difference Index (IDI), a novel white-box metric inspired by information theory. IDI quantifies retained information in intermediate features by measuring mutual information between those features and the labels to be forgotten, offering a more comprehensive assessment of unlearning efficacy. Our experiments demonstrate that IDI effectively measures the degree of unlearning across various datasets and architectures, providing a reliable tool for evaluating strong unlearning in DNNs.

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.026
metaresearch head score (Gemma)0.127
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.026
Threshold uncertainty score0.139

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0260.127
Meta-epidemiology (narrow)0.0030.001
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0050.003
Science and technology studies0.0010.007
Scholarly communication0.0040.011
Open science0.0030.006
Research integrity0.0040.006
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 head0.266
GPT teacher head0.355
Teacher spread0.089 · 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; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designTheoretical or conceptual
Domainnot available
GenreEmpirical

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
Published2024
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicAdvanced Statistical Methods and ModelsFrench-language works237,207