REVIEW 3 cited by
Survey on Causal-based Machine Learning Fairness Notions
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Addressing the problem of fairness is crucial to safely use machine learning algorithms to support decisions with a critical impact on people's lives such as job hiring, child maltreatment, disease diagnosis, loan granting, etc. Several notions of fairness have been defined and examined in the past decade, such as statistical parity and equalized odds. The most recent fairness notions, however, are causal-based and reflect the now widely accepted idea that using causality is necessary to appropriately address the problem of fairness. This paper examines an exhaustive list of causal-based fairness notions and study their applicability in real-world scenarios. As the majority of causal-based fairness notions are defined in terms of non-observable quantities (e.g., interventions and counterfactuals), their deployment in practice requires to compute or estimate those quantities using observational data. This paper offers a comprehensive report of the different approaches to infer causal quantities from observational data including identifiability (Pearl's SCM framework) and estimation (potential outcome framework). The main contributions of this survey paper are (1) a guideline to help selecting a suitable fairness notion given a specific real-world scenario, and (2) a ranking of the fairness notions according to Pearl's causation ladder indicating how difficult it is to deploy each notion in practice.
Forward citations
Cited by 3 Pith papers
-
Position: Beyond Sensitive Attributes, ML Fairness Should Quantify Structural Injustice via Social Determinants
Fairness auditing should target social determinants that carry structural injustice, because mitigating on sensitive attributes alone can create new harms.
-
Exploring Fairness Interventions in Open Source Projects
Only 32% of 62 open source fairness interventions are actively maintained, and support is concentrated in classification models and inprocessing mitigation.
-
Exploring the Landscape of Fairness Interventions in Software Engineering
A survey of fairness interventions in software engineering that organizes prior work into a taxonomy and adds a small empirical analysis of open-source fairness repository maintenance.
Discussion (0). Continue with ORCID to comment.