MétaCan
Menu
Back to cohort
Record W4388213050 · doi:10.32614/rj-2023-034

Fairness Audits and Debiasing Using \pkg{mlr3fairness}

2023· article· en· W4388213050 on OpenAlexaff
Florian Pfisterer, Siyi Wei, Sebastian J. Vollmer, Michel Lang, Bernd Bischl

Bibliographic record

VenueThe R Journal · 2023
Typearticle
Languageen
FieldSocial Sciences
TopicPrivacy, Security, and Data Protection
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsDebiasingComputer scienceAuditVariety (cybernetics)Machine learningSet (abstract data type)Artificial intelligenceData scienceAccounting

Abstract

fetched live from OpenAlex

Given an increase in data-driven automated decision-making based on machine learning (ML) models, it is imperative that, along with tools to develop and improve such models, there are sufficient capabilities to analyze and assess models with respect to potential biases. We present the package mlr3fairness, a collection of metrics and methods that allow for the assessment of bias in machine learning models. Our package implements a variety of widely used fairness metrics that can be used to audit models for potential biases, along with a set of visualizations that can help to provide additional insights into such biases. mlr3fairness furthermore integrates bias mitigation methods for machine learning models through data pre-processing or post-processing of predictions. These allow practitioners to trade off performance and fairness metrics that are appropriate for their use case.

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)0.047
metaresearch head score (Gemma)0.214
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.047
Threshold uncertainty score0.246

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0470.214
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.0040.002
Science and technology studies0.0020.003
Scholarly communication0.0070.008
Open science0.0040.008
Research integrity0.0030.005
Insufficient payload (model declined to judge)0.0200.009

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 head0.080
GPT teacher head0.349
Teacher spread0.270 · 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 designSimulation or modeling
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

Citations0
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueThe R JournalSame topicPrivacy, Security, and Data ProtectionFrench-language works237,207