View in EDS PDF Full Text

Addressing popularity discrepancy in collaborative filtering.

Saved in:
Bibliographic Details
Title: Addressing popularity discrepancy in collaborative filtering.
Authors: Yu, Cizhou1 (AUTHOR) czyu22@m.fudan.edu.cn, Li, Dongsheng2 (AUTHOR) dongsli@microsoft.com, Gu, Hansu3 (AUTHOR) hansug@acm.org, Zhang, Peng1 (AUTHOR) zhangpeng_@fudan.edu.cn, Gu, Ning1 (AUTHOR) ninggu@fudan.edu.cn, Lu, Tun1 (AUTHOR) lutun@fudan.edu.cn
Source: Knowledge & Information Systems. Aug2025, Vol. 67 Issue 8, p6525-6551. 27p.
Subjects: Recommender systems, Popularity
Abstract: Collaborative filtering (CF) has emerged as the most successful type of recommendation algorithm during the past few decades. However, we observe that CF algorithms often exhibit a popularity discrepancy between user-interacted items and recommended items, e.g., CF algorithms may recommend items that are more popular than the ones the user preferred, especially to those who prefer non-popular items. To address this previously overlooked bias, we make three key contributions: (1) We introduce two novel metrics, PopDis_ED and PopDis_JS, to quantitatively measure popularity discrepancy, providing new perspectives beyond traditional bias indicators; (2) we propose an innovative model-agnostic mutual debiasing (MUDE) framework that uniquely combines a holistic model with a specialized long-tail model through a popularity-aware gating mechanism; (3) comprehensive experiments on four real-world datasets demonstrate that MUDE improves both recommendation accuracy and popularity discrepancy reduction, outperforming state-of-the-art debiasing methods. Moreover, MUDE shows strong generalizability across different types of CF algorithms, making it a practical solution for real-world recommender systems. [ABSTRACT FROM AUTHOR]
Copyright of Knowledge & Information Systems is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Links:
  – Type: pdflink
Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 186953451
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Addressing popularity discrepancy in collaborative filtering.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Yu%2C+Cizhou%22">Yu, Cizhou</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> czyu22@m.fudan.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Li%2C+Dongsheng%22">Li, Dongsheng</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> dongsli@microsoft.com</i><br /><searchLink fieldCode="AR" term="%22Gu%2C+Hansu%22">Gu, Hansu</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> hansug@acm.org</i><br /><searchLink fieldCode="AR" term="%22Zhang%2C+Peng%22">Zhang, Peng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> zhangpeng_@fudan.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Gu%2C+Ning%22">Gu, Ning</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> ninggu@fudan.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Lu%2C+Tun%22">Lu, Tun</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> lutun@fudan.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Knowledge+%26+Information+Systems%22">Knowledge & Information Systems</searchLink>. Aug2025, Vol. 67 Issue 8, p6525-6551. 27p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Recommender+systems%22">Recommender systems</searchLink><br /><searchLink fieldCode="DE" term="%22Popularity%22">Popularity</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Collaborative filtering (CF) has emerged as the most successful type of recommendation algorithm during the past few decades. However, we observe that CF algorithms often exhibit a popularity discrepancy between user-interacted items and recommended items, e.g., CF algorithms may recommend items that are more popular than the ones the user preferred, especially to those who prefer non-popular items. To address this previously overlooked bias, we make three key contributions: (1) We introduce two novel metrics, PopDis_ED and PopDis_JS, to quantitatively measure popularity discrepancy, providing new perspectives beyond traditional bias indicators; (2) we propose an innovative model-agnostic mutual debiasing (MUDE) framework that uniquely combines a holistic model with a specialized long-tail model through a popularity-aware gating mechanism; (3) comprehensive experiments on four real-world datasets demonstrate that MUDE improves both recommendation accuracy and popularity discrepancy reduction, outperforming state-of-the-art debiasing methods. Moreover, MUDE shows strong generalizability across different types of CF algorithms, making it a practical solution for real-world recommender systems. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Knowledge & Information Systems is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=186953451
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s10115-025-02426-1
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 27
        StartPage: 6525
    Subjects:
      – SubjectFull: Recommender systems
        Type: general
      – SubjectFull: Popularity
        Type: general
    Titles:
      – TitleFull: Addressing popularity discrepancy in collaborative filtering.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Yu, Cizhou
      – PersonEntity:
          Name:
            NameFull: Li, Dongsheng
      – PersonEntity:
          Name:
            NameFull: Gu, Hansu
      – PersonEntity:
          Name:
            NameFull: Zhang, Peng
      – PersonEntity:
          Name:
            NameFull: Gu, Ning
      – PersonEntity:
          Name:
            NameFull: Lu, Tun
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 08
              Text: Aug2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 02191377
          Numbering:
            – Type: volume
              Value: 67
            – Type: issue
              Value: 8
          Titles:
            – TitleFull: Knowledge & Information Systems
              Type: main
ResultId 1