Equality of Opportunity in Classification: A Causal Approach

By Junzhe Zhang, Elias Bareinboim. 2018

96 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.

Citations in the corpus

Prediction-Based Decisions and Fairness: A Catalogue of Choices, Assumptions, and Definitions (2018, background): “[180] (in a follow-up paper, they decompose disparity in error rates into causal quantities [179]).”
On the Fairness of Causal Algorithmic Recourse (2020, background): “However, it has been argued both from causal [9, 12, 13, 16] and non-causal [1] perspectives that fairness is fundamentally a concept at the level of the individual.”
Algorithmic recourse under imperfect causal knowledge: a probabilistic approach (2020, background): “The importance of causal reasoning for an ethical and socially beneficial use of ML-assisted technology has also been stressed in a number of recent works in the field of explainability and fair algorithmic decision making [29, 42, 24, 63, 64, 10, 57, 15].”
Noise-tolerant fair classification (2019, background): “…2009; Dwork et al., 2011; Feldman, 2015; Kim et al., 2018; Hardt et al., 2016; Zafar et al., 2017b,a; Kusner et al., 2017; Speicher et al., 2018; Zhang & Bareinboim, 2018; Heidari et al., 2019), and on means of achieving them (Zemel et al., 2013; Zafar et al., 2017b; Calmon et al., 2017; Dwork…”
Fairness risk measures (2019, background): “…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, Kusner et al., 2017].”
Bias in machine learning - what is it good for? (2020, background): “A causal version of equalized odds, denoted Counterfactual Direct Error Rate, is proposed in [50], together with causal versions of other types of model biases.”
Fairness without Harm: Decoupled Classifiers with Preference Guarantees (2019, methodology): “We allow data distributions to vary between groups, sharing this motivation with causal approaches (see e.g., Kusner et al., 2017; Nabi & Shpitser, 2018; Zhang & Bareinboim, 2018; Salimi et al., 2019).”
Counterfactual risk assessments, evaluation, and fairness (2019, background): “The technical challenge is that the assumptions required to estimate these counterfactual metrics prohibit the use of important features, such as prior history, or require full specification of the structural causal model (SCM) [30, 31, 56] These requirements are too restrictive for our settings of ”
Generative causal explanations of black-box classifiers (2020, unknown): “[44] Junzhe Zhang and Elias Bareinboim.”