MétaCan
Menu
Back to cohort
Record W4413846568 · doi:10.1016/j.infsof.2025.107876

Representation-based fairness evaluation and bias correction robustness assessment in neural networks

2025· article· en· W4413846568 on OpenAlex
Qiaolin Qin, Benjamin Djian, Ettore Merlo, Heng Li, Sébastien Gambs

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

VenueInformation and Software Technology · 2025
Typearticle
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsUniversité du Québec à MontréalPolytechnique Montréal
Fundersnot available
KeywordsRobustness (evolution)Artificial neural networkComputer scienceArtificial intelligenceDeep neural networksMachine learningRepresentation (politics)Political scienceChemistry

Abstract

fetched live from OpenAlex

Context: While machine learning has achieved high predictive performance in many domains, decisions may still be biased and unfair regarding specific demographic groups characterized by sensitive attributes such as gender, age, or race. Objectives: In this paper, we introduce a novel approach to assess model fairness and bias correction robustness based on Computational Profile Distance (CPD) analysis with respect to sensitive attributes. Methods: To study model fairness, we quantify the model’s representation difference using the computational profile learned from different subgroups (e.g., male and female) on the individual and group level. To analyze the robustness of bias correction outcomes, we compare the correction suggestions provided based on confidence (i.e., softmax score) and likelihood (i.e., CPD). Results: To demonstrate the potential of the proposed approach, experiments have been performed using 24 models targeting 3 datasets used in previous fairness studies. Our experiments showed that computational profile distributions can effectively address model fairness from a representation perspective. Further, the experiments indicated that confidence-based bias correction decisions can vary largely from likelihood-based ones, and we should take both suggestions into account to obtain robust outcomes. Conclusion: Demonstrated with a set of experiments, our CPD-based approaches can help users build their trust in fairness assessment and bias mitigation of AI decisions, in ethically sensitive domains such as human resources, finance, health, and more.

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: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.920
Threshold uncertainty score0.443

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0000.000
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 head0.015
GPT teacher head0.309
Teacher spread0.293 · 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