Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2401.00055 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911744163577856 |
|---|---|
| author | Creager, Elliot Zemel, Richard |
| author_facet | Creager, Elliot Zemel, Richard |
| contents | Research on algorithmic recourse typically considers how an individual can reasonably change an unfavorable automated decision when interacting with a fixed decision-making system. This paper focuses instead on the online setting, where system parameters are updated dynamically according to interactions with data subjects. Beyond the typical individual-level recourse, the online setting opens up new ways for groups to shape system decisions by leveraging the parameter update rule. We show empirically that recourse can be improved when users coordinate by jointly computing their feature perturbations, underscoring the importance of collective action in mitigating adverse automated decisions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_00055 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Online Algorithmic Recourse by Collective Action Creager, Elliot Zemel, Richard Machine Learning Research on algorithmic recourse typically considers how an individual can reasonably change an unfavorable automated decision when interacting with a fixed decision-making system. This paper focuses instead on the online setting, where system parameters are updated dynamically according to interactions with data subjects. Beyond the typical individual-level recourse, the online setting opens up new ways for groups to shape system decisions by leveraging the parameter update rule. We show empirically that recourse can be improved when users coordinate by jointly computing their feature perturbations, underscoring the importance of collective action in mitigating adverse automated decisions. |
| title | Online Algorithmic Recourse by Collective Action |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2401.00055 |