Fairness Constraints

Fairness Constraints is a formal mechanism in algorithmic fairness that imposes mathematical or logical conditions on a machine learning model’s predictions or recommendations to ensure equitable treatment or outcomes across defined demographic groups, thereby restricting the solution space to only those models that satisfy specified fairness criteria.

457

Publications

34.8K

Citations

1.2K

Authors

459

Institutions

Publications per year

2017–2026

306

Authors

1.2K

  1. NK
    Nisheeth K. Vishnoi

    Yale University, United States

    13 publications · 578 citations

    13

    h-index

  2. LE
    L. Elisa Celis

    École Polytechnique Fédérale de Lausanne, Switzerland

    10 publications · 497 citations

    10

    h-index

  3. AR
    Aaron Roth

    University of Pennsylvania, United States

    10 publications · 695 citations

    10

    h-index

  4. MK
    Michael Kearns

    University of Pennsylvania, United States

    10 publications · 695 citations

    10

    h-index

  5. IV
    Isabel Valera

    Max Planck Institute for Software Systems, Germany

    7 publications · 1.9K citations

    7

    h-index

1–5 of 1.2K

Venues

  1. arXiv (Cornell University)

    Repository · 94 publications · 7.1K citations

    34

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 13 publications · 439 citations

    12

    h-index

  3. Neural Information Processing Systems

    Conference · 8 publications · 267 citations

    8

    h-index

  4. IEEE Transactions on Wireless Communications

    8 publications · 1.3K citations

    8

    h-index

  5. International Conference on Machine Learning

    Conference · 6 publications · 299 citations

    6

    h-index

1–5