CoMix: Collaborative filtering with mixup for implicit datasets

Cited 3 time in webofscience Cited 0 time in scopus
  • Hit : 396
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorMoon, Jaewanko
dc.contributor.authorJeong, Yoonkiko
dc.contributor.authorChae, Dong-Kyuko
dc.contributor.authorChoi, Jaehoko
dc.contributor.authorShim, Hyunjungko
dc.contributor.authorLee, Jongwukko
dc.date.accessioned2023-03-06T05:00:14Z-
dc.date.available2023-03-06T05:00:14Z-
dc.date.created2023-03-06-
dc.date.created2023-03-06-
dc.date.issued2023-05-
dc.identifier.citationINFORMATION SCIENCES, v.628, pp.254 - 268-
dc.identifier.issn0020-0255-
dc.identifier.urihttp://hdl.handle.net/10203/305456-
dc.description.abstractCollaborative filtering (CF) is the prevalent solution to mitigate massive information overload in modern recommender systems. However, it usually suffers from data sparsity and popularity bias problems. Existing studies exploit auxiliary information or data augmentation, requiring additional data collection or expensive computational overheads. Inspired by Mixup used in the classification problem, we propose a simple-yet-effective data augmentation method for CF, namely Collaborative Mixup (CoMix), for implicit feedback datasets. The underlying idea of CoMix is to generate virtual users/items by logically combining random users/items. Unlike the original Mixup, we synthesize virtual users/items to complement weak collaborative signals by distinguishing the intersection and non-overlapping parts between two users/items. Despite its simplicity, extensive experimental results show that various CF models equipped with CoMix consistently improve the base models on four benchmark datasets.-
dc.languageEnglish-
dc.publisherELSEVIER SCIENCE INC-
dc.titleCoMix: Collaborative filtering with mixup for implicit datasets-
dc.typeArticle-
dc.identifier.wosid000931885100001-
dc.identifier.scopusid2-s2.0-85149633137-
dc.type.rimsART-
dc.citation.volume628-
dc.citation.beginningpage254-
dc.citation.endingpage268-
dc.citation.publicationnameINFORMATION SCIENCES-
dc.identifier.doi10.1016/j.ins.2023.01.110-
dc.contributor.localauthorShim, Hyunjung-
dc.contributor.nonIdAuthorMoon, Jaewan-
dc.contributor.nonIdAuthorJeong, Yoonki-
dc.contributor.nonIdAuthorChae, Dong-Kyu-
dc.contributor.nonIdAuthorChoi, Jaeho-
dc.contributor.nonIdAuthorLee, Jongwuk-
dc.description.isOpenAccessN-
dc.type.journalArticleArticle-
Appears in Collection
AI-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 3 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0