MétaCan
Menu
Back to cohort
Record W4404520567 · doi:10.1109/access.2024.3502164

Beyond the Seeds: Fairness Testing via Counterfactual Analysis of Non-Seed Instances

2024· article· en· W4404520567 on OpenAlexaff
Hussaini Mamman, Shuib Basri, Abdullateef Oluwagbemiga Balogun, Abdul Rehman Gilal, Abdullahi Abubakar Imam, Ganesh Kumar, Luiz Fernando Capretz

Bibliographic record

VenueIEEE Access · 2024
Typearticle
Languageen
FieldSocial Sciences
TopicEthics and Social Impacts of AI
Canadian institutionsWestern University
FundersMinistry of Higher Education, Malaysia
KeywordsCounterfactual thinkingComputer sciencePsychologySocial psychology

Abstract

fetched live from OpenAlex

As machine learning software increasingly shapes crucial decisions in our daily lives, ensuring the fairness of these decisions is paramount. Individual fairness guarantees non-discrimination based on protected attributes, such as race or gender. Discriminatory instances reveal individual discrimination included in machine learning software. Existing methods for detecting individual discrimination often rely on initial “seed” instances, which are data points selected from the dataset that have more likelihood of exhibiting discrimination. These seed instances are then used as the basis for generating more discriminatory instances. While effective, this approach may inadvertently overlook discrimination embedded within seemingly fair non-seed instances. To overcome this limitation, this paper proposes FairBS, an approach that utilizes non-seed instances to generate discriminatory instances using counterfactual analysis. FairBS first constructs an explainer based on dataset input features and a model under test. It then generates an input instance and checks it for discrimination. If the input instance is non-discriminatory, FairBS uses the explainer to create counterfactual examples of that instance, by causing minimal perturbation to its feature values, which then produce other instances with opposite predictions. Extensive experiments on five datasets and five machine learning models demonstrate that our proposed approach outperforms state-of-the-art methods in both efficiency and effectiveness across all datasets and models. Our approach generates an average of$\times 13.44$more discriminatory instances at$\times 14.51$faster speed compared to existing seed-based methods. These findings indicate that FairBS expands the boundaries of fairness testing beyond the discriminatory seed instances, providing a powerful tool that can be used by software engineers to better ensure fairness in machine learning software.

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)0.077
metaresearch head score (Gemma)0.266
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: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.077
Threshold uncertainty score0.409

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0770.266
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0020.003
Bibliometrics0.0030.002
Science and technology studies0.0020.006
Scholarly communication0.0040.007
Open science0.0050.005
Research integrity0.0030.005
Insufficient payload (model declined to judge)0.0020.000

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 head0.069
GPT teacher head0.411
Teacher spread0.342 · 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

Citations1
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueIEEE AccessSame topicEthics and Social Impacts of AIFrench-language works237,207