EUVIMEDEUVIMED entdecken
Leitlinie

Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML

Hilde Weerts, Florian Pfisterer, Matthias Feurer, Katharina Eggensperger, Edward Bergman, Noor Awad, Joaquin Vanschoren, Mykola Pechenizkiy, Bernd Bischl, Frank Hutter

Journal of Artificial Intelligence Research · 17.02.2024 · 79 · 639-677

DOI: 10.1613/jair.1.14747 ↗

Kurz gefasst

Leitlinie in der Zeitschrift Journal of Artificial Intelligence Research, online erschienen am 17.02.2024. Verfasst von Hilde Weerts und 9 weiteren Autor:innen. Die Arbeit wurde bisher 26-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The field of automated machine learning (AutoML) introduces techniques that automate parts of the development of machine learning (ML) systems, accelerating the process and reducing barriers for novices. However, decisions derived from ML models can reproduce, amplify, or even introduce unfairness in our societies, causing harm to (groups of) individuals. In response, researchers have started to propose AutoML systems that jointly optimize fairness and predictive performance to mitigate fairness-related harm. However, fairness is a complex and inherently interdisciplinary subject, and solely posing it as an optimization problem can have adverse side effects. With this work, we aim to raise awareness among developers of AutoML systems about such limitations of fairness-aware AutoML, while also calling attention to the potential of AutoML as a tool for fairness research. We present a comprehensive overview of different ways in which fairness-related harm can arise and the ensuing implications for the design of fairness-aware AutoML. We conclude that while fairness cannot be automated, fairness-aware AutoML can play an important role in the toolbox of ML practitioners. We highlight several open technical challenges for future work in this direction. Additionally, we advocate for the creation of more user-centered assistive systems designed to tackle challenges encountered in fairness work. This article appears in the AI & Society track.

Zitieren

APA

Weerts, H., Pfisterer, F., Feurer, M., Eggensperger, K., Bergman, E., Awad, N., Vanschoren, J., Pechenizkiy, M., Bischl, B., & Hutter, F. (2024). Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML. Journal of Artificial Intelligence Research, 79, 639-677. https://doi.org/10.1613/jair.1.14747

Vancouver

Weerts H, Pfisterer F, Feurer M, Eggensperger K, Bergman E, Awad N, et al. Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML. Journal of Artificial Intelligence Research. 2024;79:639-677. doi:10.1613/jair.1.14747

BibTeX
@article{Weerts2024,
  author = {Weerts, Hilde and Pfisterer, Florian and Feurer, Matthias and Eggensperger, Katharina and Bergman, Edward and Awad, Noor and Vanschoren, Joaquin and Pechenizkiy, Mykola and Bischl, Bernd and Hutter, Frank},
  title = {Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML},
  journal = {Journal of Artificial Intelligence Research},
  year = {2024},
  volume = {79},
  pages = {639--677},
  doi = {10.1613/jair.1.14747}
}
Kostenlos starten →