Equalized Odds

Equalized Odds is a fairness metric in machine learning that requires a classifier’s true positive and false positive rates to be identical across all protected groups, thereby ensuring that prediction accuracy is equally distributed regardless of sensitive attributes.

49

Publications

1.5K

Citations

114

Authors

52

Institutions

Publications per year

2017–2026

44

Authors

114

  1. SG
    Suriya Gunasekar

    Toyota Technological Institute at Chicago, United States

    3 publications · 192 citations

    3

    h-index

  2. AB
    Avrim Blum

    Carnegie Mellon University, United States

    3 publications · 52 citations

    3

    h-index

  3. NS
    Nathan Srebro

    Toyota Technological Institute at Chicago, United States

    3 publications · 192 citations

    3

    h-index

  4. MI
    Mesrob I. Ohannessian

    Massachusetts Institute of Technology, United States

    2 publications · 180 citations

    2

    h-index

  5. BW
    Blake Woodworth

    Toyota Technological Institute at Chicago, United States

    2 publications · 180 citations

    2

    h-index

1–5 of 114

Venues

  1. arXiv (Cornell University)

    Repository · 11 publications · 315 citations

    10

    h-index

  2. Neural Information Processing Systems

    Conference · 3 publications · 64 citations

    3

    h-index

  3. Scientometrics

    2 publications · 41 citations

    2

    h-index

  4. 2022 ACM Conference on Fairness, Accountability, and Transparency

    Conference · 1 publications · 22 citations

    2

    h-index

  5. 1

    h-index

1–5