Metric Optimization and Mainstream Bias Mitigation in Recommender Systems

Roger Zhe Li

doi:10.4233/uuid:235a5f5c-5e18-4e67-a8e6-84a7e310db12

Metric Optimization and Mainstream Bias Mitigation in Recommender Systems

Roger Zhe Li^*

^*Corresponding author for this work

Multimedia Computing

Research output: Thesis › Dissertation (TU Delft)

77 Downloads (Pure)

Original language	English
Qualification	Doctor of Philosophy
Awarding Institution	Delft University of Technology
Supervisors/Advisors	Hanjalic, A., Promotor Urbano Merino, J., Copromotor
Award date	14 Nov 2023
Print ISBNs	978-94-6483-534-2
DOIs	https://doi.org/10.4233/uuid:235a5f5c-5e18-4e67-a8e6-84a7e310db12
Publication status	Published - 2023

Keywords

Recommender Systems
Collaborative Filtering
Learning to Rank
User Fairness
Mainstream Bias Mitigation

Access to Document

10.4233/uuid:235a5f5c-5e18-4e67-a8e6-84a7e310db12

thesis_definitive.pdfFinal published version, 3.01 MBLicence: CC BY

4 Conference contribution

Mitigating Mainstream Bias in Recommendation via Cost-sensitive Learning
Li, R. Z., Urbano, J. & Hanjalic, A., 2023, ICTIR 2023 - Proceedings of the 2023 ACM SIGIR International Conference on the Theory of Information Retrieval. ACM, p. 135-142 8 p. (ICTIR 2023 - Proceedings of the 2023 ACM SIGIR International Conference on the Theory of Information Retrieval).
Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

Open Access
File
1 Citation (Scopus)

43 Downloads (Pure)
Leave No User Behind: Towards Improving the Utility of Recommender Systems for Non-mainstream Users
Li, R. Z., Urbano, J. & Hanjalic, A., 2021, WSDM 2021 - Proceedings of the 14th ACM International Conference on Web Search and Data Mining. ACM, p. 103-111 9 p.
Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

Open Access
File
18 Citations (Scopus)

158 Downloads (Pure)
New Insights into Metric Optimization for Ranking-based Recommendation
Li, R. Z., Urbano, J. & Hanjalic, A., 2021, SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, p. 932-941 10 p. 3462973. (SIGIR 2021 - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval).
Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

Open Access
File
4 Citations (Scopus)

61 Downloads (Pure)

Cite this

@phdthesis{235a5f5c5e184e67a8e684a7e310db12,

title = "Metric Optimization and Mainstream Bias Mitigation in Recommender Systems",

keywords = "Recommender Systems, Collaborative Filtering, Learning to Rank, User Fairness, Mainstream Bias Mitigation",

author = "Li, {Roger Zhe}",

year = "2023",

doi = "10.4233/uuid:235a5f5c-5e18-4e67-a8e6-84a7e310db12",

language = "English",

isbn = "978-94-6483-534-2",

type = "Dissertation (TU Delft)",

school = "Delft University of Technology",

}

TY - THES

T1 - Metric Optimization and Mainstream Bias Mitigation in Recommender Systems

AU - Li, Roger Zhe

PY - 2023

Y1 - 2023

KW - Recommender Systems

KW - Collaborative Filtering

KW - Learning to Rank

KW - User Fairness

KW - Mainstream Bias Mitigation

U2 - 10.4233/uuid:235a5f5c-5e18-4e67-a8e6-84a7e310db12

DO - 10.4233/uuid:235a5f5c-5e18-4e67-a8e6-84a7e310db12

M3 - Dissertation (TU Delft)

SN - 978-94-6483-534-2

ER -

Metric Optimization and Mainstream Bias Mitigation in Recommender Systems

Keywords

Access to Document

Research output

Mitigating Mainstream Bias in Recommendation via Cost-sensitive Learning

Leave No User Behind: Towards Improving the Utility of Recommender Systems for Non-mainstream Users

New Insights into Metric Optimization for Ranking-based Recommendation

Cite this