The Implicit Fairness Criterion of Unconstrained Learning

97 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Fairness in Machine Learning: A Survey (2020, unknown): “However calibrating for multiple protected groups and/or using multiple fairness criteria at once has been shown to be impossible [66, 167, 188, 130, 189, 223, 212, 164].”
Environment Inference for Invariant Learning (2020, background): “…(Hashimoto et al., 2018; Lahoti et al., 2020) match E [ y Φ( x ) ,e ] ∀ e yes IRM (Arjovsky et al., 2019) Group Sufﬁciency (Chouldechova, 2017; Liu et al., 2019) match E [ y Φ( x ) ,e ] ∀ e no EIIL (ours) EIIL (ours) match E [ˆ y Φ( x ) ,e,y = y (cid:48) ] ∀ e yes C-DANN (Li et al., 2018)…”