MétaCan
Menu
Back to cohort
Record W4221158899 · doi:10.24963/ijcai.2022/556

ARCANE: An Efficient Architecture for Exact Machine Unlearning

2022· article· en· W4221158899 on OpenAlexafffund
Haonan Yan, Xiaoguang Li, Ziyao Guo, Hui Li, Fenghua Li, Xiaodong Lin

Bibliographic record

VenueProceedings of the Thirty-First International Joint Conference on Artificial Intelligence · 2022
Typearticle
Languageen
FieldComputer Science
TopicPrivacy-Preserving Technologies in Data
Canadian institutionsUniversity of Guelph
FundersHigher Education Discipline Innovation ProjectNational Natural Science Foundation of ChinaUniversity of Guelph
KeywordsComputer scienceRetrainingArtificial intelligenceMachine learningOverhead (engineering)PreprocessorReuseData pre-processingEngineering

Abstract

fetched live from OpenAlex

Recently users’ right-to-be-forgotten is stipulated by many laws and regulations. However, only removing the data from the dataset is not enough, as machine learning models would memorize the training data once the data is involved in model training, increasing the risk of exposing users’ privacy. To solve this problem, currently, the straightforward method, naive retraining, is to discard these data and retrain the model from scratch, which is reliable but brings much computational and time overhead. In this paper, we propose an exact unlearning architecture called ARCANE. Based on ensemble learning, we transform the naive retraining into multiple one-class classification tasks to reduce retraining cost while ensuring model performance, especially in the case of a large number of unlearning requests not considered by previous works. Then we further introduce data preprocessing methods to reduce the retraining overhead and speed up the unlearning, which includes representative data selection for redundancy removal, training state saving to reuse previous calculation results, and sorting to cope with unlearning requests of different distributions. We extensively evaluate ARCANE on three typical datasets with three common model architectures. Experiment results show the effectiveness and superiority of ARCANE over both the naive retraining and the state-of-the-art method in terms of model performance and unlearning speed.

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)0.001
metaresearch head score (Gemma)0.004
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.006
Threshold uncertainty score0.013

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.004
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0010.001
Scholarly communication0.0010.003
Open science0.0040.002
Research integrity0.0010.003
Insufficient payload (model declined to judge)0.0030.002

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 head0.070
GPT teacher head0.300
Teacher spread0.230 · 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 designSimulation or modeling
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

Citations80
Published2022
Admission routes2
Has abstractyes

Explore more

Same venueProceedings of the Thirty-First International Joint Conference on Artificial IntelligenceSame topicPrivacy-Preserving Technologies in DataFrench-language works237,207