MétaCan
Menu
Back to cohort
Record W4382203029 · doi:10.1609/aaai.v37i8.26196

A Fair Generative Model Using LeCam Divergence

2023· article· en· W4382203029 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
FieldSocial Sciences
TopicComputational and Text Analysis Methods
Canadian institutionsKootenay Association for Science & Technology
FundersMinistry of Science and ICT, South KoreaKorea Advanced Institute of Science and TechnologyNational Research Foundation of KoreaInstitute for Information and Communications Technology PromotionKorea Customs ServiceNational Research Foundation
KeywordsBenchmark (surveying)Divergence (linguistics)Measure (data warehouse)Computer scienceSet (abstract data type)Range (aeronautics)Generative grammarSample size determinationGenerative modelStatistical powerSample (material)Machine learningData miningArtificial intelligenceStatisticsMathematics

Abstract

fetched live from OpenAlex

We explore a fairness-related challenge that arises in generative models. The challenge is that biased training data with imbalanced demographics may yield a high asymmetry in size of generated samples across distinct groups. We focus on practically-relevant scenarios wherein demographic labels are not available and therefore the design of a fair generative model is non-straightforward. In this paper, we propose an optimization framework that regulates the unfairness under such practical settings via one statistical measure, LeCam (LC)-divergence. Specifically to quantify the degree of unfairness, we employ a balanced-yet-small reference dataset and then measure its distance with generated samples using the LC-divergence, which is shown to be particularly instrumental to a small size of the reference dataset. We take a variational optimization approach to implement the LC-based measure. Experiments on benchmark real datasets demonstrate that the proposed framework can significantly improve the fairness performance while maintaining realistic sample quality for a wide range of the reference set size all the way down to 1% relative to training set.

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: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.507
Threshold uncertainty score0.594

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.002
Science and technology studies0.0010.001
Scholarly communication0.0000.000
Open science0.0010.000
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 head0.293
GPT teacher head0.424
Teacher spread0.131 · 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