MétaCan
Menu
Back to cohort
Record W4393112045 · doi:10.1186/s40537-024-00898-6

Multi-sample $$\zeta $$-mixup: richer, more realistic synthetic samples from a p-series interpolant

2024· article· en· W4393112045 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenueJournal Of Big Data · 2024
Typearticle
Languageen
FieldComputer Science
TopicDomain Adaptation and Few-Shot Learning
Canadian institutionsSimon Fraser University
FundersNatural Sciences and Engineering Research Council of CanadaAlliance de recherche numérique du CanadaCompute CanadaSimon Fraser UniversityNvidia
KeywordsAlgorithmComputer scienceMachine learningArtificial intelligenceSeries (stratigraphy)

Abstract

fetched live from OpenAlex

Abstract Modern deep learning training procedures rely on model regularization techniques such as data augmentation methods, which generate training samples that increase the diversity of data and richness of label information. A popular recent method, mixup , uses convex combinations of pairs of original samples to generate new samples. However, as we show in our experiments, mixup can produce undesirable synthetic samples, where the data is sampled off the manifold and can contain incorrect labels. We propose $$\zeta $$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mi>ζ</mml:mi></mml:math> - mixup , a generalization of mixup with provably and demonstrably desirable properties that allows convex combinations of $${T} \ge 2$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mrow><mml:mi>T</mml:mi><mml:mo>≥</mml:mo><mml:mn>2</mml:mn></mml:mrow></mml:math> samples, leading to more realistic and diverse outputs that incorporate information from $${T}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mi>T</mml:mi></mml:math> original samples by using a p -series interpolant. We show that, compared to mixup , $$\zeta $$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mi>ζ</mml:mi></mml:math> - mixup better preserves the intrinsic dimensionality of the original datasets, which is a desirable property for training generalizable models. Furthermore, we show that our implementation of $$\zeta $$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mi>ζ</mml:mi></mml:math> - mixup is faster than mixup , and extensive evaluation on controlled synthetic and 26 diverse real-world natural and medical image classification datasets shows that $$\zeta $$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mi>ζ</mml:mi></mml:math> - mixup outperforms mixup , CutMix, and traditional data augmentation techniques. The code will be released at https://github.com/kakumarabhishek/zeta-mixup .

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.

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)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.884
Threshold uncertainty score0.662

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0020.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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 head0.182
GPT teacher head0.335
Teacher spread0.153 · 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