Statistical Equity: A Fairness Classification Objective

By Ninareh Mehrabi, Yuzhong Huang, Fred Morstatter. 2020

10 citations recorded by the source corpus.

Machine learning systems have been shown to propagate the societal errors of the past. In light of this, a wealth of research focuses on designing solutions that are "fair." Even with this abundance of work, there is no singular definition of fairness, mainly because fairness is subjective and context dependent. We propose a new fairness definition, motivated by the principle of equity, that considers existing biases in the data and attempts to make equitable decisions that account for these previous historical biases. We formalize our definition of fairness, and motivate it with its appropriate contexts. Next, we operationalize it for equitable classification. We perform multiple automatic and human evaluations to show the effectiveness of our definition and demonstrate its utility for aspects of fairness, such as the feedback loop.

Subfields: Artificial Intelligence, Safety Research, AI Ethics, Fairness & Society

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Safety Research

In AI Ethics, Fairness & Society

Citations in the corpus

A Survey on Bias and Fairness in Machine Learning (2019, background): “However, little attention has been paid to equity, which is the concept that each individual or group is given the resources they need to succeed [60, 103].”
Attributing Fair Decisions with Attention Interventions (2021, background): “…Roy and Boddeti 2019; Jaiswal et al. 2020; Song et al. 2019), adding regularizers to incorporate fairness (Zafar et al. 2017; Kamishima et al. 2012; Mehrabi, Huang, and Morstatter 2020), or modifying the outcomes of unfair machine learning algorithms to ensure fairness (Hardt et al. 2016), among…”
Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation (2021, background): “For instance, to address the negative repercussions that historical bias has had on a group may require treatment that purposely violates parity (Mehrabi, Huang, and Morstatter 2020).”