MétaCan
Menu
Back to cohort
Record W4382318343 · doi:10.1609/aaai.v37i12.26751

Rethinking Label Refurbishment: Model Robustness under Label Noise

2023· article· en· W4382318343 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.

Bibliographic record

VenueProceedings of the AAAI Conference on Artificial Intelligence · 2023
Typearticle
Languageen
FieldComputer Science
TopicMachine Learning and Data Classification
Canadian institutionsMcMaster University
Fundersnot available
KeywordsRobustness (evolution)GeneralizationComputer scienceRegularization (linguistics)Deep neural networksArtificial neural networkArtificial intelligenceNoise (video)Machine learningPattern recognition (psychology)Mathematics

Abstract

fetched live from OpenAlex

A family of methods that generate soft labels by mixing the hard labels with a certain distribution, namely label refurbishment, are widely used to train deep neural networks. However, some of these methods are still poorly understood in the presence of label noise. In this paper, we revisit four label refurbishment methods and reveal the strong connection between them. We find that they affect the neural network models in different manners. Two of them smooth the estimated posterior for regularization effects, and the other two force the model to produce high-confidence predictions. We conduct extensive experiments to evaluate related methods and observe that both effects improve the model generalization under label noise. Furthermore, we theoretically show that both effects lead to generalization guarantees on the clean distribution despite being trained with noisy labels.

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)0.000
Version: codex-gemma-dda1882f352aValidation 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: Empirical
Teacher disagreement score0.725
Threshold uncertainty score0.754

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0030.001
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 head0.165
GPT teacher head0.334
Teacher spread0.169 · 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