Bayesian Fairness

Christos Dimitrakakis, Yang Liu, David C. Parkes, Goran Radanovic

AAAI 2019 pp. 509-516

doi:10.1609/AAAI.V33I01.3301509 /aaai/2019/dimitrakakis2019aaai-bayesian/

Abstract

We consider the problem of how decision making can be fair when the underlying probabilistic model of the world is not known with certainty. We argue that recent notions of fairness in machine learning need to explicitly incorporate parameter uncertainty, hence we introduce the notion of Bayesian fairness as a suitable candidate for fair decision rules. Using balance, a definition of fairness introduced in (Kleinberg, Mullainathan, and Raghavan 2016), we show how a Bayesian perspective can lead to well-performing and fair decision rules even under high uncertainty.

PDF AAAI Semantic Scholar

Cite

Text

Dimitrakakis et al. "Bayesian Fairness." AAAI Conference on Artificial Intelligence, 2019. doi:10.1609/AAAI.V33I01.3301509

Markdown

[Dimitrakakis et al. "Bayesian Fairness." AAAI Conference on Artificial Intelligence, 2019.](https://mlanthology.org/aaai/2019/dimitrakakis2019aaai-bayesian/) doi:10.1609/AAAI.V33I01.3301509

BibTeX

@inproceedings{dimitrakakis2019aaai-bayesian,
  title     = {{Bayesian Fairness}},
  author    = {Dimitrakakis, Christos and Liu, Yang and Parkes, David C. and Radanovic, Goran},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2019},
  pages     = {509-516},
  doi       = {10.1609/AAAI.V33I01.3301509},
  url       = {https://mlanthology.org/aaai/2019/dimitrakakis2019aaai-bayesian/}
}