MétaCan
Menu
Back to cohort

FairDETOCS: An approach to detect and connect unfair models

2024· article· en· W4405709739 on OpenAlexaffabout
Mayssa Bejaoui, Fehmi Jaafar

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldEngineering
TopicSafety Systems Engineering in Autonomy
Canadian institutionsUniversité du Québec à Chicoutimi
Fundersnot available
KeywordsComputer scienceComputer security

Abstract

fetched live from OpenAlex

In the dawn of the digital age, Artificial Intelli-gence and decision-making systems have become omnipresent, completely shaping various aspects of our daily lives. Unfortu-nately, as these systems grow more complex and influential, they also raise significant ethical and societal concerns. As machine learning and AI continue to evolve, ensuring fairness in these systems has become increasingly important. The challenge lies in making models fair, necessitating algorithms that mitigate biases, particularly intersectional biases. Numerous studies have highlighted the lack of intersectional bias treatment in current methodologies. Thus, we propose in this paper a novel approach named FairDetocs. This method incorporates fairness metrics to measure intersectional biases and employs a reweighting algorithm to mitigate them. The process begins with the initial evaluation of biases, followed by data adjustment through the reweighting algorithm, and concludes with a re-evaluation of biases to ensure effective reduction. We base our study on the Adult Income dataset, modified with Canadian statistics. Our results demonstrate a noticeable attenuation of biases, showcasing the effectiveness of FairDetocs in promoting fairness in machine learning models. Overall, our exploratory study provides a significant contribution to the field of fairness in machine learning and sets the stage for further research on this topic.

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)0.030
metaresearch head score (Gemma)0.124
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: Empirical · Consensus signal: none
Teacher disagreement score0.030
Threshold uncertainty score0.159

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0300.124
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0030.002
Bibliometrics0.0080.004
Science and technology studies0.0040.005
Scholarly communication0.0060.009
Open science0.0050.012
Research integrity0.0040.006
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 head0.015
GPT teacher head0.203
Teacher spread0.188 · 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
GenreEmpirical

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
Published2024
Admission routes2
Has abstractyes

Explore more

Same topicSafety Systems Engineering in AutonomyFrench-language works237,207