TY - GEN

T1 - Multi-dimensional Discrimination in Law and Machine Learning

T2 - 6th ACM Conference on Fairness, Accountability, and Transparency, FAccT 2023

AU - Roy, Arjun

AU - Horstmann, Jan

AU - Ntoutsi, Eirini

N1 - Funding Information: This research work is funded by Volkswagen Foundation under the call “Artificial Intelligence and the Society of the Future" project “Bias and Discrimination in Big Data and Algorithmic Processing -BIAS” and by the European Union under the Horizon Europe MAMMOth project, Grant Agreement ID: 101070285. We especially thank our colleagues in the projects for invaluable discussions and helpful suggestions

PY - 2023/6/12

Y1 - 2023/6/12

N2 - AI-driven decision-making can lead to discrimination against certain individuals or social groups based on protected characteristics/attributes such as race, gender, or age. The domain of fairness-aware machine learning focuses on methods and algorithms for understanding, mitigating, and accounting for bias in AI/ML models. Still, thus far, the vast majority of the proposed methods assess fairness based on a single protected attribute, e.g. only gender or race. In reality, though, human identities are multi-dimensional, and discrimination can occur based on more than one protected characteristic, leading to the so-called "multi-dimensional discrimination"or "multi-dimensional fairness"problem. While well-elaborated in legal literature, the multi-dimensionality of discrimination is less explored in the machine learning community. Recent approaches in this direction mainly follow the so-called intersectional fairness definition from the legal domain, whereas other notions like additive and sequential discrimination are less studied or not considered thus far. In this work, we overview the different definitions of multi-dimensional discrimination/fairness in the legal domain as well as how they have been transferred/ operationalized (if) in the fairness-aware machine learning domain. By juxtaposing these two domains, we draw the connections, identify the limitations, and point out open research directions.

AB - AI-driven decision-making can lead to discrimination against certain individuals or social groups based on protected characteristics/attributes such as race, gender, or age. The domain of fairness-aware machine learning focuses on methods and algorithms for understanding, mitigating, and accounting for bias in AI/ML models. Still, thus far, the vast majority of the proposed methods assess fairness based on a single protected attribute, e.g. only gender or race. In reality, though, human identities are multi-dimensional, and discrimination can occur based on more than one protected characteristic, leading to the so-called "multi-dimensional discrimination"or "multi-dimensional fairness"problem. While well-elaborated in legal literature, the multi-dimensionality of discrimination is less explored in the machine learning community. Recent approaches in this direction mainly follow the so-called intersectional fairness definition from the legal domain, whereas other notions like additive and sequential discrimination are less studied or not considered thus far. In this work, we overview the different definitions of multi-dimensional discrimination/fairness in the legal domain as well as how they have been transferred/ operationalized (if) in the fairness-aware machine learning domain. By juxtaposing these two domains, we draw the connections, identify the limitations, and point out open research directions.

KW - additive fairness

KW - intersectional fairness

KW - multi-discrimination

KW - multi-fairness

KW - sequential fairness

UR - http://www.scopus.com/inward/record.url?scp=85163682034&partnerID=8YFLogxK

U2 - 10.48550/arXiv.2302.05995

DO - 10.48550/arXiv.2302.05995

M3 - Conference contribution

AN - SCOPUS:85163682034

T3 - ACM International Conference Proceeding Series

SP - 89

EP - 100

BT - FAccT '23

PB - Association for Computing Machinery (ACM)

Y2 - 12 June 2023 through 15 June 2023

ER -