Welfare-Centric Clustering
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908489866018816 |
|---|---|
| author | Zhang, Claire Jie Esmaeili, Seyed A. Morgenstern, Jamie |
| author_facet | Zhang, Claire Jie Esmaeili, Seyed A. Morgenstern, Jamie |
| contents | Fair clustering has traditionally focused on ensuring equitable group representation or equalizing group-specific clustering costs. However, Dickerson et al. (2025) recently showed that these fairness notions may yield undesirable or unintuitive clustering outcomes and advocated for a welfare-centric clustering approach that models the utilities of the groups. In this work, we model group utilities based on both distances and proportional representation and formalize two optimization objectives based on welfare-centric clustering: the Rawlsian (Egalitarian) objective and the Utilitarian objective. We introduce novel algorithms for both objectives and prove theoretical guarantees for them. Empirical evaluations on multiple real-world datasets demonstrate that our methods significantly outperform existing fair clustering baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_10345 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Welfare-Centric Clustering Zhang, Claire Jie Esmaeili, Seyed A. Morgenstern, Jamie Machine Learning Artificial Intelligence Computers and Society Data Structures and Algorithms Fair clustering has traditionally focused on ensuring equitable group representation or equalizing group-specific clustering costs. However, Dickerson et al. (2025) recently showed that these fairness notions may yield undesirable or unintuitive clustering outcomes and advocated for a welfare-centric clustering approach that models the utilities of the groups. In this work, we model group utilities based on both distances and proportional representation and formalize two optimization objectives based on welfare-centric clustering: the Rawlsian (Egalitarian) objective and the Utilitarian objective. We introduce novel algorithms for both objectives and prove theoretical guarantees for them. Empirical evaluations on multiple real-world datasets demonstrate that our methods significantly outperform existing fair clustering baselines. |
| title | Welfare-Centric Clustering |
| topic | Machine Learning Artificial Intelligence Computers and Society Data Structures and Algorithms |
| url | https://arxiv.org/abs/2508.10345 |