MétaCan
Menu
Back to cohort
Record W1589919686

Does Unlabeled Data Provably Help? Worst-case Analysis of the Sample Complexity of Semi-Supervised Learning.

2008· article· en· W1589919686 on OpenAlexaff
Shai Ben-David, Tyler Lu, Dávid Pál

Bibliographic record

VenueConference on Learning Theory · 2008
Typearticle
Languageen
FieldComputer Science
TopicMachine Learning and Data Classification
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsSample complexityComputer scienceSemi-supervised learningHomogeneousDistribution (mathematics)Artificial intelligenceConjectureSample (material)Class (philosophy)Labeled dataSupervised learningMachine learningPattern recognition (psychology)MathematicsArtificial neural networkDiscrete mathematicsCombinatorics
DOInot available

Abstract

fetched live from OpenAlex

We study the potential benefits of unlabeled data to classification prediction to the learner. We compare learning in the semi-supervised model to the standard, supervised PAC (distribution free) model, considering both the realizable and the unrealizable (agnostic) settings. Roughly speaking, our conclusion is that access to unlabeled samples cannot provide sample size guarantees that are better than those obtainable without access to unlabeled data, unless one postulates very strong assumptions about the distribution of the labels. In particular, we prove that for basic hypothesis classes over the real line, if the distribution of unlabeled data is ‘smooth’, knowledge of that distribution cannot improve the labeled sample complexity by more than a constant factor (e.g., 2). We conjecture that a similar phenomena holds for any hypothesis class and any unlabeled data distribution. We also discuss the utility of semi-supervised learning under the common cluster assumption concerning the distribution of labels, and show that even in the most accommodating cases, where data is generated by two uni-modal label-homogeneous distributions, common SSL paradigms may be misleading and inflict poor prediction performance.

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)0.049
metaresearch head score (Gemma)0.244
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: Methods · Consensus signal: Methods
Teacher disagreement score0.049
Threshold uncertainty score0.260

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0490.244
Meta-epidemiology (narrow)0.0020.002
Meta-epidemiology (broad)0.0030.002
Bibliometrics0.0020.002
Science and technology studies0.0020.007
Scholarly communication0.0070.018
Open science0.0050.007
Research integrity0.0040.008
Insufficient payload (model declined to judge)0.0050.001

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 head0.109
GPT teacher head0.301
Teacher spread0.191 · 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
GenreMethods

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

Citations108
Published2008
Admission routes1
Has abstractyes

Explore more

Same venueConference on Learning TheorySame topicMachine Learning and Data ClassificationFrench-language works237,207