Online Algorithmic Recourse by Collective Action
Abstract
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- December 2023
- DOI:
- 10.48550/arXiv.2401.00055
- arXiv:
- arXiv:2401.00055
- Bibcode:
- 2024arXiv240100055C
- Keywords:
-
- Computer Science - Machine Learning
- E-Print:
- Appeared in the ICML 2021 Workshop on Algorithmic Recourse