analiza aiqbench
This research proposes a novel "user-side" approach to algorithmic fairness where minority groups strategically relabel their own data to counteract model biases, bypassing the need for corporate intervention or utility loss. By validating these model-agnostic methods on real-world datasets, the study demonstrates that coordinated collective action can significantly reduce unfairness with minimal impact on overall prediction accuracy. This shifts the paradigm from firm-centric mitigation to empowering end-users as active agents in correcting systemic bias within machine learning systems.
Minority Collective Action for User-Side Fairness
arXiv:2508.15374v3 Announce Type: replace Abstract: Machine learning models often preserve biases present in training data, leading to unfair treatment of certain minority groups. Despite an array of existing firm-side bias mitigation techniques, they typically incur utility costs and require organizational buy-in. Recognizing that many models rely on user-contributed data, end-users can induce fairness through the framework of Algorithmic Collective Action, where a coordinated minority group strategically relabels its own data to enhance fairness, without altering the firm's training process. We propose three practical, model-agnostic methods to approximate ideal relabeling and validate them on real-world datasets. Our findings show that a subgroup of the minority can substantially reduce unfairness with a small impact on the overall prediction error.
Abstract:Machine learning models often preserve biases present in training data, leading to unfair treatment of certain minority groups. Despite an array of existing firm-side bias mitigation techniques, they typically incur utility costs and require organizational buy-in. Recognizing that many models rely on user-contributed data, end-users can induce fairness through the framework of Algorithmic Collective Action, where a coordinated minority group strategically relabels its own data to enhance fairness, without altering the firm's training process. We propose three practical, model-agnostic methods to approximate ideal relabeling and validate them on real-world datasets. Our findings show that a subgroup of the minority can substantially reduce unfairness with a small impact on the overall prediction error.
Machine Learning (cs.LG); Computers and Society (cs.CY)
arXiv:2508.15374 [cs.LG]
(or arXiv:2508.15374v3 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2508.15374 Focus to learn more arXiv-issued DOI via DataCite
https://doi.org/10.1145/3846167.3848593 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 218 cuvinte
Subiecte conexe
State of the Field: AI for Epistemics and Coordination
LessWrong · 2 oct. 2026
Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident
METR · 26 aug. 2026
BRICS Draws a New Global Line: Full Text of New Delhi Declaration
slguardian.org · 12 sept. 2026
Game-Theoretic Disempowerment: Loss of Control to Agencyless AI
LessWrong · 27 sept. 2026