An Intersectional Definition of Fairness

Foulds, James; Islam, Rashidul; Keya, Kamrun Naher; Pan, Shimei

doi:10.1109/icde48307.2020.00203

Cited by 108 publications

(81 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Open Sci. 8: 210821 have found that all studied classifiers perform worst on darker female faces (20.8-34.7% error rate) while the maximum error rate for lighter-skinned males was just 0.8% [15].…”

Section: Discussionmentioning

confidence: 87%

Quota-based debiasing can decrease representation of the most under-represented groups

2021

View full text Add to dashboard Cite

Many important decisions in societies such as school admissions, hiring or elections are based on the selection of top-ranking individuals from a larger pool of candidates. This process is often subject to biases, which typically manifest as an under-representation of certain groups among the selected or accepted individuals. The most common approach to this issue is debiasing, for example, via the introduction of quotas that ensure a proportional representation of groups with respect to a certain, often binary attribute. This, however, has the potential to induce changes in representation with respect to other attributes. For the case of two correlated binary attributes, we show that quota-based debiasing based on a single attribute can worsen the representation of the most under-represented intersectional groups and decrease the overall fairness of selection. Our results demonstrate the importance of including all relevant attributes in debiasing procedures and that more efforts need to be put into eliminating the root causes of inequalities as purely numerical solutions such as quota-based debiasing might lead to unintended consequences.

show abstract

Section: Discussionmentioning

confidence: 87%

Quota-based debiasing can decrease representation of the most under-represented groups

2021

View full text Add to dashboard Cite

show abstract

“…We propose to consider more attributes in further experiments to analyze how convergence is affected. Differential fairness 29 is a growing concept highly related with this study, which addresses intersectionality. We propose to run new experiments of our meta-learning algorithm proposing this new fairness definition.…”

Section: Discussionmentioning

confidence: 99%

How fair can we go in machine learning ? Assessing the boundaries of accuracy and fairness

2021

View full text Add to dashboard Cite

Fair machine learning has been focusing on the development of equitable algorithms that address discrimination. Yet, many of these fairness-aware approaches aim to obtain a unique solution to the problem, which leads to a poor understanding of the statistical limits of bias mitigation interventions. In this study, a novel methodology is presented to explore the tradeoff in terms of a Pareto front between accuracy and fairness. To this end, we propose a multiobjective framework that seeks to optimize both measures. The experimental framework is focused on logistiregression and decision tree classifiers since they are well-known by the machine learning community. We conclude experimentally that our method can optimize classifiers by being fairer with a small cost on the classification accuracy. We believe that our contribution will help stakeholders of sociotechnical systems to assess how far they can go being fair and accurate, thus serving in the support of enhanced decision making where machine learning is used.

show abstract

“…The bulk of the work to ensure fairness has focused on making the input data more representative or modifying existing models to ensure fair outcomes (Kamishima et al, 2011;Kearns et al, 2017). Scholars have also recently focused on developing measures that account for sociologically relevant phenomena like intersectionality 3 (Foulds and Pan, 2018), on the tradeoffs between existing measures (Kleinberg, 2018), and on a better understanding of the causal assumptions of different measures (Glymour and Herington, 2019) amongst other tasks.…”

Section: Fairnessmentioning

confidence: 99%

Theory In, Theory Out: The Uses of Social Theory in Machine Learning for Social Science

Radford

Joseph

2020

Front. Big Data

View full text Add to dashboard Cite

Research at the intersection of machine learning and the social sciences has provided critical new insights into social behavior. At the same time, a variety of issues have been identified with the machine learning models used to analyze social data. These issues range from technical problems with the data used and features constructed, to problematic modeling assumptions, to limited interpretability, to the models' contributions to bias and inequality. Computational researchers have sought out technical solutions to these problems. The primary contribution of the present work is to argue that there is a limit to these technical solutions. At this limit, we must instead turn to social theory. We show how social theory can be used to answer basic methodological and interpretive questions that technical solutions cannot when building machine learning models, and when assessing, comparing, and using those models. In both cases, we draw on related existing critiques, provide examples of how social theory has already been used constructively in existing work, and discuss where other existing work may have benefited from the use of specific social theories. We believe this paper can act as a guide for computer and social scientists alike to navigate the substantive questions involved in applying the tools of machine learning to social data.

show abstract

An Intersectional Definition of Fairness

Cited by 108 publications

References 8 publications

Quota-based debiasing can decrease representation of the most under-represented groups

Quota-based debiasing can decrease representation of the most under-represented groups

How fair can we go in machine learning ? Assessing the boundaries of accuracy and fairness

Theory In, Theory Out: The Uses of Social Theory in Machine Learning for Social Science

Contact Info

Product

Resources

About