Differential parity is proposed as a relative fairness metric between decision sets independent of sensitive attributes, usable with or without a reference set and extendable via ML for mismatched data.
Fair- balance: Improving machine learning fairness on multi- plesensitive attributes with data balancing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2021 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Differential Parity: Relative Fairness Between Two Sets of Decisions
Differential parity is proposed as a relative fairness metric between decision sets independent of sensitive attributes, usable with or without a reference set and extendable via ML for mismatched data.