One Model Many Scores: Using Multiverse Analysis to Prevent Fairness Hacking and Evaluate the Influence of Model Design Decisions-Reference-Cited by-同舟云学术

One Model Many Scores: Using Multiverse Analysis to Prevent Fairness Hacking and Evaluate the Influence of Model Design Decisions

Published:2024-06-03 Issue: Volume: Page:
ISSN:
Container-title:The 2024 ACM Conference on Fairness, Accountability, and Transparency
language:
Short-container-title:

Author:

Simson Jan¹^ORCID,Pfisterer Florian²^ORCID,Kern Christoph¹^ORCID

Affiliation:

1. Institute of Statistics, LMU Munich, Germany and Munich Center for Machine Learning (MCML), Germany

2. Institute of Statistics, LMU Munich, Germany

Funder

Federal Statistical Office of Germany

Munich Center for Machine Learning

Konrad Zuse Schools of Excellence in Artificial Intelligence, sponsored by the Federal Ministry of Education and Research

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3630106.3658974

Reference64 articles.

1. Alekh Agarwal Alina Beygelzimer Miroslav Dudík John Langford and Hanna Wallach. 2018. A Reductions Approach to Fair Classification. (2018).

2. Ulrich Aïvodji, Hiromi Arai, Olivier Fortineau, Sébastien Gambs, Satoshi Hara, and Alain Tapp. 2019. Fairwashing: the risk of rationalization. In International Conference on Machine Learning. PMLR, 161–170.

3. J.J. Allaire Charles Teague Carlos Scheidegger Yihui Xie and Christophe Dervieux. 2022. Quarto. https://doi.org/10.5281/zenodo.5960048 DOI: 10.5281/zenodo.5960048.

4. Julia Angwin, Jeff Larson, Surya Mattu, and Lauren Kirchner. 2016. Machine bias. ProPublica (05 2016), 254–264. https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing

Cited by 1 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. When Small Decisions Have Big Impact: Fairness Implications of Algorithmic Profiling Schemes;ACM Journal on Responsible Computing;2024-08-22