Perceptions of the Fairness Impacts of Multiplicity in Machine Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915118143504384 |
|---|---|
| author | Meyer, Anna P. Kim, Yea-Seul Albarghouthi, Aws D'Antoni, Loris |
| author_facet | Meyer, Anna P. Kim, Yea-Seul Albarghouthi, Aws D'Antoni, Loris |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_12332 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Perceptions of the Fairness Impacts of Multiplicity in Machine Learning Meyer, Anna P. Kim, Yea-Seul Albarghouthi, Aws D'Antoni, Loris Computers and Society Human-Computer Interaction 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. |
| title | Perceptions of the Fairness Impacts of Multiplicity in Machine Learning |
| topic | Computers and Society Human-Computer Interaction |
| url | https://arxiv.org/abs/2409.12332 |