Quota-based debiasing can decrease representation of already underrepresented groups

06/13/2020
by   Ivan Smirnov, et al.
0

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 proportional representation of groups with respect to a certain, often binary attribute. Cases include quotas for women on corporate boards or ethnic quotas in elections. 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 already underrepresented groups and decrease overall fairness of selection. We use several data sets from a broad range of domains from recidivism risk assessments to scientific citations to assess this effect in real-world settings. 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/11/2015

Multi-Attribute Proportional Representation

We consider the following problem in which a given number of items has t...
research
05/05/2022

On Disentangled and Locally Fair Representations

We study the problem of performing classification in a manner that is fa...
research
07/25/2022

Estimating and Controlling for Fairness via Sensitive Attribute Predictors

Although machine learning classifiers have been increasingly used in hig...
research
07/29/2020

Intersectional Affirmative Action Policies for Top-k Candidates Selection

We study the problem of selecting the top-k candidates from a pool of ap...
research
04/27/2023

A transparent approach to data representation

We use a binary attribute representation (BAR) model to describe a data ...
research
01/17/2022

Fair Group-Shared Representations with Normalizing Flows

The issue of fairness in machine learning stems from the fact that histo...
research
05/30/2022

Diverse Representation via Computational Participatory Elections – Lessons from a Case Study

Elections are the central institution of democratic processes, and often...

Please sign up or login with your details

Forgot password? Click here to reset