On the Robustness of Fairness Practices: A Causal Framework for Systematic Evaluation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912806498992128 |
|---|---|
| author | Monjezi, Verya Kumar, Ashish Trivedi, Ashutosh Tan, Gang Tizpaz-Niari, Saeid |
| author_facet | Monjezi, Verya Kumar, Ashish Trivedi, Ashutosh Tan, Gang Tizpaz-Niari, Saeid |
| contents | Machine learning (ML) algorithms are increasingly deployed to make critical decisions in socioeconomic applications such as finance, criminal justice, and autonomous driving. However, due to their data-driven and pattern-seeking nature, ML algorithms may develop decision logic that disproportionately distributes opportunities, benefits, resources, or information among different population groups, potentially harming marginalized communities. In response to such fairness concerns, the software engineering and ML communities have made significant efforts to establish the best practices for creating fair ML software. These include fairness interventions for training ML models, such as including sensitive features, selecting non-sensitive attributes, and applying bias mitigators. But how reliably can software professionals tasked with developing data-driven systems depend on these recommendations? And how well do these practices generalize in the presence of faulty labels, missing data, or distribution shifts? These questions form the core theme of this paper. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_03621 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | On the Robustness of Fairness Practices: A Causal Framework for Systematic Evaluation Monjezi, Verya Kumar, Ashish Trivedi, Ashutosh Tan, Gang Tizpaz-Niari, Saeid Software Engineering Machine learning (ML) algorithms are increasingly deployed to make critical decisions in socioeconomic applications such as finance, criminal justice, and autonomous driving. However, due to their data-driven and pattern-seeking nature, ML algorithms may develop decision logic that disproportionately distributes opportunities, benefits, resources, or information among different population groups, potentially harming marginalized communities. In response to such fairness concerns, the software engineering and ML communities have made significant efforts to establish the best practices for creating fair ML software. These include fairness interventions for training ML models, such as including sensitive features, selecting non-sensitive attributes, and applying bias mitigators. But how reliably can software professionals tasked with developing data-driven systems depend on these recommendations? And how well do these practices generalize in the presence of faulty labels, missing data, or distribution shifts? These questions form the core theme of this paper. |
| title | On the Robustness of Fairness Practices: A Causal Framework for Systematic Evaluation |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2601.03621 |