Equality of Opportunity in Supervised Learning
@inproceedings{Hardt2016EqualityOO, title={Equality of Opportunity in Supervised Learning}, author={Moritz Hardt and Eric Price and Nathan Srebro}, booktitle={NIPS}, year={2016} }
We propose a criterion for discrimination against a specified sensitive attribute in supervised learning, where the goal is to predict some target based on available features. [...] Key Method Our framework also improves incentives by shifting the cost of poor classification from disadvantaged groups to the decision maker, who can respond by improving the classification accuracy. We enourage readers to consult the more complete manuscript on the arXiv.Expand
Supplemental Code
Github Repo
Via Papers with Code
A Python package to assess and improve fairness of machine learning models.
Figures and Topics from this paper
Paper Mentions
News Article
Blog Post
News Article
News Article
News Article
News Article
News Article
1,308 Citations
Fairness in Supervised Learning: An Information Theoretic Approach
- Computer Science, Mathematics
- 2018 IEEE International Symposium on Information Theory (ISIT)
- 2018
- 18
- Highly Influenced
- PDF
Taking Advantage of Multitask Learning for Fair Classification
- Mathematics, Computer Science
- AIES
- 2019
- 22
- PDF
A Distributionally Robust Approach to Fair Classification
- Computer Science, Mathematics
- ArXiv
- 2020
- 7
- Highly Influenced
- PDF
A Framework for Benchmarking Discrimination-Aware Models in Machine Learning
- Computer Science
- AIES
- 2019
- 4
On preserving non-discrimination when combining expert advice
- Computer Science, Mathematics
- NeurIPS
- 2018
- 17
- PDF
Leveraging Labeled and Unlabeled Data for Consistent Fair Binary Classification
- Computer Science, Mathematics
- NeurIPS
- 2019
- 11
- Highly Influenced
- PDF
Eliminating Latent Discrimination: Train Then Mask
- Computer Science, Mathematics
- ArXiv
- 2018
- 2
- Highly Influenced
- PDF
Fairness in Semi-supervised Learning: Unlabeled Data Help to Reduce Discrimination
- Computer Science, Mathematics
- ArXiv
- 2020
- 4
- Highly Influenced
- PDF
Learning Fair Classifiers: A Regularization-Inspired Approach
- Computer Science, Mathematics
- ArXiv
- 2017
- 34
- Highly Influenced
- PDF
References
SHOWING 1-10 OF 28 REFERENCES
On the relation between accuracy and fairness in binary classification
- Computer Science
- ArXiv
- 2015
- 80
- PDF
Building Classifiers with Independency Constraints
- Computer Science
- 2009 IEEE International Conference on Data Mining Workshops
- 2009
- 214
- PDF
Inherent Trade-Offs in the Fair Determination of Risk Scores
- Computer Science, Mathematics
- ITCS
- 2017
- 712
- PDF