University of Sussex
Browse
frai-03-00033.pdf (984.51 kB)

Tuning fairness by balancing target labels

Download (984.51 kB)
journal contribution
posted on 2023-06-10, 01:52 authored by Thomas Maximilian Kehrenberg, Zexun Chen, Novi QuadriantoNovi Quadrianto
The issue of fairness in machine learning models has recently attracted a lot of attention as ensuring it will ensure continued confidence of the general public in the deployment of machine learning systems. We focus on mitigating the harm incurred by a biased machine learning system that offers better outputs (e.g., loans, job interviews) for certain groups than for others. We show that bias in the output can naturally be controlled in probabilistic models by introducing a latent target output. This formulation has several advantages: first, it is a unified framework for several notions of group fairness such as Demographic Parity and Equality of Opportunity; second, it is expressed as a marginalization instead of a constrained problem; and third, it allows the encoding of our knowledge of what unbiased outputs should be. Practically, the second allows us to avoid unstable constrained optimization procedures and to reuse off-the-shelf toolboxes. The latter translates to the ability to control the level of fairness by directly varying fairness target rates. In contrast, existing approaches rely on intermediate, arguably unintuitive, control parameters such as covariance thresholds.

History

Publication status

  • Published

File Version

  • Published version

Journal

Frontiers in Artificial Intelligence

ISSN

2624-8212

Publisher

Frontiers Media

Volume

3

Article number

a33

Department affiliated with

  • Informatics Publications

Full text available

  • Yes

Peer reviewed?

  • Yes

Legacy Posted Date

2021-11-25

First Open Access (FOA) Date

2021-11-25

First Compliant Deposit (FCD) Date

2021-11-25

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC