Post-Processing Debiasing is a fairness-enhancing technique in machine learning that belongs to the class of algorithmic debiasing methods, specifically distinguished by its application of adjustments to the output predictions of a trained model to satisfy desired fairness criteria without modifying the model or training process.
5
Publications
195
Citations
10
Authors
6
Institutions
Publications per year
2017–2026
3
Parents
Publications
5
Using Iterated Bagging to Debias Regressions
Leo Breiman · Machine Learning · 2001 · 311 citations · Full text
Challenges in Automated Debiasing for Toxic Language Detection
Xuhui Zhou, Maarten Sap, Swabha Swayamdipta et al. · 2021 · 108 citations · Full text
1–5 of 5
Authors
10
- SS
2
h-index
- MS
2
h-index
- XZ
2
h-index
- YC
2
h-index
- NA
2
h-index
1–5 of 10
Institutions
6
National University of Singapore
Singapore, Singapore
1 h-index
1 publications
29 citations
University of British Columbia
Vancouver, Canada
1 h-index
1 publications
29 citations
University of Washington
Seattle, United States
1 h-index
5 publications
540 citations
Karlsruhe Institute of Technology
Karlsruhe, Germany
1 h-index
2 publications
48 citations
Aichi Institute of Technology
Toyota, Japan
1 h-index
1 publications
22 citations
Allen Institute for Artificial Intelligence
Seattle, United States
1 h-index
4 publications
432 citations
Lingnan Normal University
Zhanjiang, China
1 publications
14 citations
Guangdong University of Foreign Studies
Guangzhou, China
1 publications
14 citations
1–8 of 6
Venues
- arXiv (Cornell University)
Repository · 1 publications · 12 citations
1
h-index
- European Journal of Operational Research
1 publications · 24 citations
1
h-index
- Organizational Behavior and Human Decision Processes
1 publications · 29 citations
1
h-index
- Learning and Instruction
1 publications · 18 citations
- Machine Learning
1 publications · 311 citations
1–5