On conditional parity as a notion of non-discrimination in machine learning
By Yaacov Ritov, Yuekai Sun, Ruofei Zhao. 2017
40 citations recorded by the source corpus.
We identify conditional parity as a general notion of non-discrimination in machine learning. In fact, several recently proposed notions of non-discrimination, including a few counterfactual notions, are instances of conditional parity. We show that conditional parity is amenable to statistical analysis by studying randomization as a general mechanism for achieving conditional parity and a kernel-based test of conditional parity.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Ed H. Chi
- Alex Beutel
- Aditya Krishna Menon
- Jilin Chen
- Christina Ilvento
- Robert C. Williamson
- Zhe Zhao
- Lichan Hong
Citations in the corpus
- Fairness in Recommendation Ranking through Pairwise Comparisons (2019, background): “As such, we can follow the approach of conditioning on other dependent signals as in [7, 41].”
- Fairness risk measures (2019, background): “…[Zafar et al., 2017b] constrains the subgroup error rates to be identical: There are other extant notions of perfect fairness [Zafar et al., 2017a, Ritov et al., 2017, Heidari et al., 2018, Zhang and Bareinboim, 2018], including those for individual rather than group fairness [Dwork et al., 2012,…”
- Putting Fairness Principles into Practice: Challenges, Metrics, and Improvements (2019, background): “Most related is [35], which first proposed this generalized fairness metric and included conditioning on arbitrary variables.”
- Fairness Under Composition (2018, background): “5 satisfies Conditional Parity for a single application.”