Counterfactual Fairness: Unidentification, Bound and Algorithm

Yongkai Wu · Lu Zhang · Xintao Wu

73 citations0/0 files storedInternational Joint Conference on Artificial Intelligence

No readable copy stored yet — this record is metadata only.

No open-access location is known for this record yet.

Literature note Cite in a project Citation map

Ethics and Social Impacts of AI Privacy-Preserving Technologies in Data Explainable Artificial Intelligence (XAI)

Abstract

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.

Paper brief

Loading…

Cite this work

Citation unavailable for this work.

BibTeX RIS CSL-JSON

No public copy is stored for this record, so only the metadata is cited.

Citations in this library

Citation map →

Stored only when both papers are in the corpus — 73 citations exist upstream.

References

2017Counterfactual Fairness 2017Avoiding Discrimination through Causal Reasoning 2019Path-Specific Counterfactual Fairness 2018Fairness in Decision-Making — The Causal Explanation Formula 2017A Causal Framework for Discovering and Removing Direct and Indirect Discrimination

Cited by

2022A brief review on algorithmic fairness 2022On the Fairness of Causal Algorithmic Recourse 2023Antidiscrimination Insurance Pricing: Regulations, Fairness Criteria, and Models 2021Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder 2022A review of causality-based fairness machine learning 2020Fairness through Equality of Effort 2022Optimising Equal Opportunity Fairness in Model Training 2020Artificial mental phenomena

Explore the map →

Papers that cite the same references — the relational fallback while embeddings are still backfilling.

Imported from OpenAlex (CC0) — nothing here is generated.