Perceptions of the Fairness Impacts of Multiplicity in Machine Learning

要旨

Machine learning (ML) is increasingly used in high-stakes settings, yet multiplicity – the existence of multiple good models – means that some predictions are essentially arbitrary. ML researchers and philosophers posit that multiplicity poses a fairness risk, but no studies have investigated whether stakeholders agree. In this work, we conduct a survey to see how multiplicity impacts lay stakeholders’ – i.e., decision subjects’ – perceptions of ML fairness, and which approaches to address multiplicity they prefer. We investigate how these perceptions are modulated by task characteristics (e.g., stakes and uncertainty). Survey respondents think that multiplicity threatens the fairness of model outcomes, but not the appropriateness of using the model, even though existing work suggests the opposite. Participants are strongly against resolving multiplicity by using a single model (effectively ignoring multiplicity) or by randomizing the outcomes. Our results indicate that model developers should be intentional about dealing with multiplicity in order to maintain fairness.

著者
Anna P.. Meyer
University of Wisconsin - Madison, Madison, Wisconsin, United States
Yea-Seul Kim
Apple, Boulder, Colorado, United States
Loris D'Antoni
University of California - San Diego, San Diego, California, United States
Aws Albarghouthi
University of Wisconsin-Madison, Madison, Wisconsin, United States
DOI

10.1145/3706598.3713524

論文URL

https://dl.acm.org/doi/10.1145/3706598.3713524

動画

会議: CHI 2025

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2025.acm.org/)

セッション: High-Stake Situations

G302
7 件の発表
2025-04-28 23:10:00
2025-04-29 00:40:00
日本語まとめ
読み込み中…