Bayesian Personalized Ranking

Bayesian Personalized Ranking is a pairwise preference learning framework for personalized item ranking that formulates the optimization problem as maximizing the posterior probability of observed user preferences under a Bayesian inference paradigm, distinguishing it from pointwise or regression-based collaborative filtering approaches by focusing on relative item comparisons rather than absolute ratings.

84

Publications

13.3K

Citations

291

Authors

96

Institutions

Publications per year

2017–2026

59

Authors

291

  1. LS
    Lars Schmidt-Thieme

    University of Hildesheim, Germany

    7 publications · 7.5K citations

    7

    h-index

  2. XH
    Xiangnan He

    University of Science and Technology of China, China

    6 publications · 635 citations

    6

    h-index

  3. CF
    Christoph Freudenthaler

    University of Hildesheim, Germany

    6 publications · 7.5K citations

    6

    h-index

  4. YL
    Yong Li

    Tsinghua University, China

    4 publications · 181 citations

    4

    h-index

  5. WP
    Weike Pan

    Shenzhen University, China

    4 publications · 420 citations

    4

    h-index

1–5 of 291

Venues

  1. arXiv (Cornell University)

    Repository · 7 publications · 4.6K citations

    7

    h-index

  2. IEEE Access

    4 publications · 83 citations

    4

    h-index

  3. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 3 publications · 1.1K citations

    3

    h-index

  4. ACM Transactions on Information Systems

    3 publications · 94 citations

    3

    h-index

  5. Information Sciences

    3 publications · 174 citations

    3

    h-index

1–5