When Worlds Collide: Integrating Different Counterfactual Assumptions in Fairness

By Chris Russell, Matt J. Kusner, Joshua R. Loftus, Ricardo M. A. Silva. 2017

180 citations recorded by the source corpus.

Subfields: Causal Inference & Discovery, AI Ethics, Fairness & Society

How researchers see this paper

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

In Causal Inference & Discovery

In AI Ethics, Fairness & Society

Citations in the corpus

Counterfactual Fairness (2017, background): “If competing models with different untestable assumptions are available, there are ways of simultaneously enforcing a notion of approximate counterfactual fairness in all of them, as introduced by us in [32].”
Counterfactuals in Explainable Artificial Intelligence (XAI): Evidence from Human Reasoning (2019, background): “Careful constraints on counterfactuals are required to provide interpretable models of the decisions of AI systems that people can trust and consider to be fair [see also Russell et al., 2017].”
Causal Reasoning for Algorithmic Fairness (2018, background): “If there are substantive disagreements about the functional form of structural equations, multiple models can be integrated in the same predictive framework as introduced by [35].”
Path-Specific Counterfactual Fairness (2018, methodology): “It was recently argued (Qureshi et al., 2016; Bonchi et al., 2017; Kilbertus et al., 2017; Kusner et al., 2017; Nabi & Sh-pitser, 2018; Russell et al., 2017; Zhang et al., 2017; Zhang & Wu, 2017; Zhang & Bareinboim, 2018) that using a causal framework (Pearl, 2000; Dawid, 2007; Pearl et al., 2016;…”
On the Fairness of Causal Algorithmic Recourse (2020, background): “2017a,b), these are sometimes mutually incompatible (Chouldechova 2017), and it has been argued that discrimination, at its heart, corresponds to a (direct or indirect) causal influence of a protected attribute on the prediction, thus making fairness a fundamentally causal problem (Kilbertus et al. ”
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].”
Algorithmic Fairness (2020, background): “For instance, by understanding causes and effects in the data, the model may assist in tackling the challenges of fairness definitions by analyzing which types of discrimination should be allowed and which should not [87, 118].”
Counterfactual Fairness Is Basically Demographic Parity (2022, methodology): “We follow notation laid out by (Kusner et al. 2017) for our formal analysis.”
Human Perceptions of Fairness in Algorithmic Decision Making: A Case Study of Criminal Risk Prediction (2018, background): “Inspired by arguments for applying causal reasoning in fairness [8, 34, 39, 42, 51, 54, 63], fairness judgments might be influenced by whether a feature is likely to cause (i.”
PC-Fairness: A Unified Framework for Measuring Causality-based Fairness (2019, background): “Table 1: Connection between previous fairness notions and PC fairness Description References Relating to PC fairness Total effect [19, 16] O = ∅ and π = Π (System) Direct discrimination [19, 7, 16] O = ∅ or {S} and π = πd = {S → Ŷ } (System) Indirect discrimination [19, 7, 16] O = ∅ or {S} and π = π”
Proxy Fairness (2018, background): “Russell et al. build causal models for different groups with fairness constraints [18].”
The Sensitivity of Counterfactual Fairness to Unmeasured Confounding (2019, background): “While previous work addressed how to enforce counterfactual fairness across a small enumeration of identiﬁable competing models (Russell et al., 2017), in this work we consider misspeciﬁcation in the lack of unidentiﬁable unmeasured confounding.”
MultiVerse: Causal Reasoning using Importance Sampling in Probabilistic Programming (2019, background): “…et al., 2017; Sokol and Flach, 2018; Guidotti et al., 2018; Pedreschi et al., 2019), fairness Kusner et al. (2017); Zhang and Bareinboim (2018); Russell et al. (2017), policy search (e.g. Buesing et al. (2019)) and are also quantities of interest on their own (e.g. Johansson et al. (2016)).”
Robust Optimization for Fairness with Noisy Protected Groups (2020, unknown): “, 2012), and causality/counterfactual fairness (Russell et al., 2017; Kusner et al., 2017).”
A Review on Fairness in Machine Learning (2022, background): “Commonly, causal methods for fairness mitigation are aimed at pre-processing the training data [44, 81, 83, 122, 128, 155, 174, 179].”