Counterfactual Fairness: Unidentification, Bound and Algorithm

By Yongkai Wu, Lu Zhang, Xintao Wu. 2019

115 citations recorded by the source corpus.

Fairness-aware learning studies the problem of building machine learning models that are subject to fairness requirements. Counterfactual fairness is a notion of fairness derived from Pearl's causal model, which considers a model is fair if for a particular individual or group its prediction in the real world is the same as that in the counterfactual world where the individual(s) had belonged to a different demographic group. However, an inherent limitation of counterfactual fairness is that it cannot be uniquely quantified from the observational data in certain situations, due to the unidentifiability of the counterfactual quantity. In this paper, we address this limitation by mathematically bounding the unidentifiable counterfactual quantity, and develop a theoretically sound algorithm for constructing counterfactually fair classifiers. We evaluate our method in the experiments using both synthetic and real-world datasets, as well as compare with existing methods. The results validate our theory and show the effectiveness of our method.

Subfields: Gender Studies, Safety Research

How researchers see this paper

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

In Safety Research

Citations in the corpus

On the Fairness of Causal Algorithmic Recourse (2020, background): “However, it has been argued from causal (Chiappa 2019; Wu et al. 2019) and noncausal (Dwork et al. 2012) perspectives that fairness is fundamentally an individual-level concept:6 group-level fairness still allows for unfairness at the level of the individual, provided that positive and negative…”
Bias and Debias in Recommender System: A Survey and Future Directions (2020, background): “Inspired by the success of causal modeling [166], studying fairness from the causal perspective [135], [136], [137], [138], [139] has attracted increasing attentions.”
PC-Fairness: A Unified Framework for Measuring Causality-based Fairness (2019, methodology): “In [20] the authors propose a method to bound indirect discrimination as the path-speciﬁc effect in unidentiﬁable situations, and in [14] a method is proposed to bound counterfactual fairness.”
Counterfactual Fairness Is Basically Demographic Parity (2022, background): “…use or modify only slightly Deﬁnition 2 to enable training classiﬁers and other decision making algorithms (Zhang and Bareinboim 2018; Chiappa 2019; Wu, Zhang, and Wu 2019; Coston et al. 2020; Black, Yeom, and Fredrikson 2020; Mhasawade and Chunara 2021; Chikahara et al. 2021; von K¨ugelgen et al.…”
A Survey on the Fairness of Recommender Systems (2022, background): “Eliminating unfairness at the causal level is considered essential and has received a growing interest in machine learning [49, 98].”