Comprehensive Validation on Reweighting Samples for Bias Mitigation via AIF360
It addresses data bias for fairness in AI, but is incremental as it validates existing reweighting methods on standard datasets.
This paper systematically examined reweighting samples for bias mitigation in traditional machine learning models, using five models on Adult Income and COMPUS datasets with various protected attributes, and found that effectiveness is nuanced and model-specific while revealing complex bias dynamics.
Fairness AI aims to detect and alleviate bias across the entire AI development life cycle, encompassing data curation, modeling, evaluation, and deployment-a pivotal aspect of ethical AI implementation. Addressing data bias, particularly concerning sensitive attributes like gender and race, reweighting samples proves efficient for fairness AI. This paper contributes a systematic examination of reweighting samples for traditional machine learning (ML) models, employing five models for binary classification on the Adult Income and COMPUS datasets with various protected attributes. The study evaluates prediction results using five fairness metrics, uncovering the nuanced and model-specific nature of reweighting sample effectiveness in achieving fairness in traditional ML models, as well as revealing the complexity of bias dynamics.