Resource-constrained Fairness
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913683644350464 |
|---|---|
| author | Goethals, Sofie Delaney, Eoin Mittelstadt, Brent Russell, Chris |
| author_facet | Goethals, Sofie Delaney, Eoin Mittelstadt, Brent Russell, Chris |
| contents | Access to resources strongly constrains the decisions we make. While we might wish to offer every student a scholarship, or schedule every patient for follow-up meetings with a specialist, limited resources mean that this is not possible. When deploying machine learning systems, these resource constraints are simply enforced by varying the threshold of a classifier. However, these finite resource limitations are disregarded by most existing tools for fair machine learning, which do not allow the specification of resource limitations and do not remain fair when varying thresholds. This makes them ill-suited for real-world deployment. Our research introduces the concept of "resource-constrained fairness" and quantifies the cost of fairness within this framework. We demonstrate that the level of available resources significantly influences this cost, a factor overlooked in previous evaluations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_01290 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Resource-constrained Fairness Goethals, Sofie Delaney, Eoin Mittelstadt, Brent Russell, Chris Machine Learning Computers and Society Access to resources strongly constrains the decisions we make. While we might wish to offer every student a scholarship, or schedule every patient for follow-up meetings with a specialist, limited resources mean that this is not possible. When deploying machine learning systems, these resource constraints are simply enforced by varying the threshold of a classifier. However, these finite resource limitations are disregarded by most existing tools for fair machine learning, which do not allow the specification of resource limitations and do not remain fair when varying thresholds. This makes them ill-suited for real-world deployment. Our research introduces the concept of "resource-constrained fairness" and quantifies the cost of fairness within this framework. We demonstrate that the level of available resources significantly influences this cost, a factor overlooked in previous evaluations. |
| title | Resource-constrained Fairness |
| topic | Machine Learning Computers and Society |
| url | https://arxiv.org/abs/2406.01290 |