Bayesian Fairness
Paper i proceeding, 2019

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.

Författare

Christos Dimitrakakis

Chalmers, Data- och informationsteknik, Data Science

Universitetet i Oslo

Yang Liu

University of California at Santa Cruz

David C. Parkes

Harvard University

Goran Radanovic

Harvard University

THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE

509-516


Honolulu, USA,

Ämneskategorier

Etik

Systemvetenskap

Mer information

Senast uppdaterat

2019-12-06