Preserving the fairness guarantees of classifiers in changing environments: a survey
| dc.contributor.author | Barrainkua, Ainhize | |
| dc.contributor.author | Gordaliza Pastor, Paula | |
| dc.contributor.author | Lozano, José Antonio | |
| dc.contributor.author | Quadrianto, Novi | |
| dc.contributor.department | Estadística, Informática y Matemáticas | es_ES |
| dc.contributor.department | Estatistika, Informatika eta Matematika | eu |
| dc.date.accessioned | 2024-06-10T17:20:28Z | |
| dc.date.available | 2024-06-10T17:20:28Z | |
| dc.date.issued | 2023 | |
| dc.date.updated | 2024-06-10T16:59:46Z | |
| dc.description.abstract | The impact of automated decision-making systems on human lives is growing, emphasizing the need for these systems to be not only accurate but also fair. The ield of algorithmic fairness has expanded signiicantly in the past decade, with most approaches assuming that training and testing data are drawn independently and identically from the same distribution. However, in practice, diferences between the training and deployment environments exist, compromising both the performance and fairness of the decision-making algorithms in real-world scenarios. A new area of research has emerged to address how to maintain fairness guarantees in classiication tasks when the data generation processes difer between the source (training) and target (testing) domains. The objective of this survey is to ofer a comprehensive examination of fair classiication under distribution shift by presenting a taxonomy of current approaches. The latter is formulated based on the available information from the target domain, distinguishing between adaptive methods, which adapt to the target environment based on available information, and robust methods, which make minimal assumptions about the target environment. Additionally, this study emphasizes alternative benchmarking methods, investigates the interconnection with related research ields, and identiies potential avenues for future research. | en |
| dc.description.sponsorship | This research was supported by a European Research Council (ERC) Starting Grant for the project “Bayesian Models and Algorithms for Fairness and Transparencyž, funded under the European Union’s Horizon 2020 Framework Programme (grant agreement no. 851538); by the Basque Government under grant IT1504-22 and through the BERC 2022-2025 program; by the Spanish Ministry of Science and Innovation under the grants PID2022-137442NB-I00 and PID2021-128314NB-I00, and through BCAM Severo Ochoa accreditation CEX2021- 001142-S / MICIN / AEI / 10.13039/501100011033. | en |
| dc.format.mimetype | application/pdf | en |
| dc.identifier.citation | Barrainkua, A., Gordaliza, P., Lozano, J. A., Quadrianto, N. (2023) Preserving the fairness guarantees of classifiers in changing environments: A survey. ACM Computing Surveys, 1-31. https://doi.org/10.1145/3637438. | en |
| dc.identifier.doi | 10.1145/3637438 | |
| dc.identifier.issn | 0360-0300 | |
| dc.identifier.uri | https://academica-e.unavarra.es/handle/2454/48326 | |
| dc.language.iso | eng | en |
| dc.publisher | Association for Computing Machinery | en |
| dc.relation.ispartof | ACM Computing Surveys 2023, 1-31 | en |
| dc.relation.projectID | info:eu-repo/grantAgreement/European Commission/Horizon 2020 Framework Programme/851538/ | |
| dc.relation.projectID | info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023/PID2022-137442NB-I00/ES/ | |
| dc.relation.projectID | info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023/PID2021-128314NB-I00/ES/ | |
| dc.relation.projectID | info:eu-repo/grantAgreement/AEI//CEX2021- 001142-S/ | |
| dc.relation.publisherversion | https://doi.org/10.1145/3637438 | |
| dc.rights | © 2023 Copyright held by the owner/author(s). | en |
| dc.rights.accessRights | info:eu-repo/semantics/openAccess | |
| dc.subject | Algorithmic fairness | en |
| dc.subject | Trustworthy machine learning | en |
| dc.subject | Distribution shift | en |
| dc.subject | Covariate shift | en |
| dc.subject | Uncertainty | en |
| dc.subject | Online learning | en |
| dc.subject | Distributionally robust optimisation | en |
| dc.title | Preserving the fairness guarantees of classifiers in changing environments: a survey | en |
| dc.type | info:eu-repo/semantics/article | |
| dc.type.version | info:eu-repo/semantics/acceptedVersion | |
| dspace.entity.type | Publication | |
| relation.isAuthorOfPublication | d5bda28d-00d2-4d45-b4db-f7951b9c5b4a | |
| relation.isAuthorOfPublication.latestForDiscovery | d5bda28d-00d2-4d45-b4db-f7951b9c5b4a |