Publications
Detailed Information
SLIDE: A surrogate fairness constraint to ensure fairness consistency
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Kunwoong | - |
dc.contributor.author | Ohn, Ilsang | - |
dc.contributor.author | Kim, Sara | - |
dc.contributor.author | Kim, Yongdai | - |
dc.date.accessioned | 2022-10-11T00:49:06Z | - |
dc.date.available | 2022-10-11T00:49:06Z | - |
dc.date.created | 2022-09-29 | - |
dc.date.issued | 2022-10 | - |
dc.identifier.citation | Neural Networks, Vol.154, pp.441-454 | - |
dc.identifier.issn | 0893-6080 | - |
dc.identifier.uri | https://hdl.handle.net/10371/185689 | - |
dc.description.abstract | © 2022 Elsevier LtdAs they take a crucial role in social decision makings, AI algorithms based on ML models should be not only accurate but also fair. Among many algorithms for fair AI, learning a prediction ML model by minimizing the empirical risk (e.g., cross-entropy) subject to a given fairness constraint has received much attention. To avoid computational difficulty, however, a given fairness constraint is replaced by a surrogate fairness constraint as the 0–1 loss is replaced by a convex surrogate loss for classification problems. In this paper, we investigate the validity of existing surrogate fairness constraints and propose a new surrogate fairness constraint called SLIDE, which is computationally feasible and asymptotically valid in the sense that the learned model satisfies the fairness constraint asymptotically and achieves a fast convergence rate. Numerical experiments confirm that the SLIDE works well for various benchmark datasets. | - |
dc.language | 영어 | - |
dc.publisher | Pergamon Press Ltd. | - |
dc.title | SLIDE: A surrogate fairness constraint to ensure fairness consistency | - |
dc.type | Article | - |
dc.identifier.doi | 10.1016/j.neunet.2022.07.027 | - |
dc.citation.journaltitle | Neural Networks | - |
dc.identifier.scopusid | 2-s2.0-85135949697 | - |
dc.citation.endpage | 454 | - |
dc.citation.startpage | 441 | - |
dc.citation.volume | 154 | - |
dc.description.isOpenAccess | N | - |
dc.contributor.affiliatedAuthor | Kim, Yongdai | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.