Algorithmic Fairness in Performative Policy Learning: Escaping the Impossibility of Group Fairness
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916266863755264 |
|---|---|
| author | Somerstep, Seamus Ritov, Ya'acov Sun, Yuekai |
| author_facet | Somerstep, Seamus Ritov, Ya'acov Sun, Yuekai |
| contents | In many prediction problems, the predictive model affects the distribution of the prediction target. This phenomenon is known as performativity and is often caused by the behavior of individuals with vested interests in the outcome of the predictive model. Although performativity is generally problematic because it manifests as distribution shifts, we develop algorithmic fairness practices that leverage performativity to achieve stronger group fairness guarantees in social classification problems (compared to what is achievable in non-performative settings). In particular, we leverage the policymaker's ability to steer the population to remedy inequities in the long term. A crucial benefit of this approach is that it is possible to resolve the incompatibilities between conflicting group fairness definitions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_20447 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Algorithmic Fairness in Performative Policy Learning: Escaping the Impossibility of Group Fairness Somerstep, Seamus Ritov, Ya'acov Sun, Yuekai Machine Learning Computers and Society In many prediction problems, the predictive model affects the distribution of the prediction target. This phenomenon is known as performativity and is often caused by the behavior of individuals with vested interests in the outcome of the predictive model. Although performativity is generally problematic because it manifests as distribution shifts, we develop algorithmic fairness practices that leverage performativity to achieve stronger group fairness guarantees in social classification problems (compared to what is achievable in non-performative settings). In particular, we leverage the policymaker's ability to steer the population to remedy inequities in the long term. A crucial benefit of this approach is that it is possible to resolve the incompatibilities between conflicting group fairness definitions. |
| title | Algorithmic Fairness in Performative Policy Learning: Escaping the Impossibility of Group Fairness |
| topic | Machine Learning Computers and Society |
| url | https://arxiv.org/abs/2405.20447 |