Matches in Ghent University Academic Bibliography for { <https://biblio.ugent.be/publication/01HEZ1F38MRECYGMENTCMM1P39> ?p ?o. }
Showing items 1 to 27 of
27
with 100 items per page.
- 01HEZ1F38MRECYGMENTCMM1P39 classification C1.
- 01HEZ1F38MRECYGMENTCMM1P39 date "2023".
- 01HEZ1F38MRECYGMENTCMM1P39 language "eng".
- 01HEZ1F38MRECYGMENTCMM1P39 type conference.
- 01HEZ1F38MRECYGMENTCMM1P39 hasPart 01HEZ1RP36991XJ3N02PFDFS2B.pdf.
- 01HEZ1F38MRECYGMENTCMM1P39 subject "Technology and Engineering".
- 01HEZ1F38MRECYGMENTCMM1P39 issn "1613-0073".
- 01HEZ1F38MRECYGMENTCMM1P39 presentedAt urn:uuid:73217a95-b855-4b66-9151-1b7099f2da33.
- 01HEZ1F38MRECYGMENTCMM1P39 volume "3490".
- 01HEZ1F38MRECYGMENTCMM1P39 abstract "In settings such as e-recruitment and online dating, recommendation involves distributing limited opportunities, calling for novel approaches to quantify and enforce fairness. We introduce inferiority, a novel (un)fairness measure quantifying a user’s competitive disadvantage for their recommended items. Inferiority complements envy, a fairness notion measuring preference for others’ recommendations. We combine inferiority and envy with utility, an accuracy-related measure of aggregated relevancy scores. Since these measures are non-differentiable, we reformulate them using a probabilistic interpretation of recommender systems, yielding differentiable versions. We combine these loss functions in a multi-objective optimization problem called FEIR (Fairness through Envy and Inferiority Reduction), applied as post-processing for standard recommender systems. Experiments on synthetic and real-world data demonstrate that our approach improves trade-offs between inferiority, envy, and utility compared to naive recommendations and the baseline methods.".
- 01HEZ1F38MRECYGMENTCMM1P39 author 1c093c10-305f-11ec-812c-9a7649f5a720.
- 01HEZ1F38MRECYGMENTCMM1P39 author 7E14BF6C-50F5-11E5-B4A0-F149B5D1D7B1.
- 01HEZ1F38MRECYGMENTCMM1P39 author 9797BDFE-BE0B-11E4-9A6A-FB22B5D1D7B1.
- 01HEZ1F38MRECYGMENTCMM1P39 author CCDC061E-B0DB-11E5-A24A-8CD8B4D1D7B1.
- 01HEZ1F38MRECYGMENTCMM1P39 dateCreated "2023-11-11T11:14:56Z".
- 01HEZ1F38MRECYGMENTCMM1P39 dateModified "2024-12-12T19:15:09Z".
- 01HEZ1F38MRECYGMENTCMM1P39 editor urn:uuid:11863ccf-2a14-47f6-8e3c-979bb1bc0e6e.
- 01HEZ1F38MRECYGMENTCMM1P39 editor urn:uuid:254b2c62-2b98-49e9-9f68-9278a6e95e98.
- 01HEZ1F38MRECYGMENTCMM1P39 editor urn:uuid:4b361fad-20bf-4cbc-b889-c7f4b7bd20c6.
- 01HEZ1F38MRECYGMENTCMM1P39 editor urn:uuid:a5ea5c81-1b23-4e7b-88b3-28691a99f85e.
- 01HEZ1F38MRECYGMENTCMM1P39 editor urn:uuid:d45b2b31-4d22-4101-8878-e5ecb4faed52.
- 01HEZ1F38MRECYGMENTCMM1P39 name "FEIR : quantifying and reducing envy and inferiority for fair recommendation of limited resources".
- 01HEZ1F38MRECYGMENTCMM1P39 pagination urn:uuid:163d168f-b807-4a5b-b1fd-9c5d32d5908c.
- 01HEZ1F38MRECYGMENTCMM1P39 publisher urn:uuid:96b7891a-5739-4b2f-b993-84118a14fac6.
- 01HEZ1F38MRECYGMENTCMM1P39 sameAs LU-01HEZ1F38MRECYGMENTCMM1P39.
- 01HEZ1F38MRECYGMENTCMM1P39 sourceOrganization urn:uuid:97a00faa-3ada-46a3-a92e-11ee224763c1.
- 01HEZ1F38MRECYGMENTCMM1P39 type C1.