MétaCan
Menu
Back to cohort
Record W3217600415 · doi:10.48550/arxiv.2012.12896

How Does a Neural Network's Architecture Impact Its Robustness to Noisy\n Labels?

2020· preprint· en· W3217600415 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

VenuearXiv (Cornell University) · 2020
Typepreprint
Languageen
FieldComputer Science
TopicMachine Learning and Data Classification
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsRobustness (evolution)Computer scienceNetwork architectureArchitecturePredictive powerArtificial intelligenceArtificial neural networkMachine learningDeep neural networks

Abstract

fetched live from OpenAlex

Noisy labels are inevitable in large real-world datasets. In this work, we\nexplore an area understudied by previous works -- how the network's\narchitecture impacts its robustness to noisy labels. We provide a formal\nframework connecting the robustness of a network to the alignments between its\narchitecture and target/noise functions. Our framework measures a network's\nrobustness via the predictive power in its representations -- the test\nperformance of a linear model trained on the learned representations using a\nsmall set of clean labels. We hypothesize that a network is more robust to\nnoisy labels if its architecture is more aligned with the target function than\nthe noise. To support our hypothesis, we provide both theoretical and empirical\nevidence across various neural network architectures and different domains. We\nalso find that when the network is well-aligned with the target function, its\npredictive power in representations could improve upon state-of-the-art (SOTA)\nnoisy-label-training methods in terms of test accuracy and even outperform\nsophisticated methods that use clean labels.\n

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)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.848
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0010.000
Open science0.0030.003
Research integrity0.0000.001
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 head0.064
GPT teacher head0.210
Teacher spread0.146 · 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