# Counterfactually Fair Representation

arXiv: https://arxiv.org/abs/2311.05420 · HTML: https://mlsanity.com/paper/2311.05420/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 44 references that are in the map.
- First posted on arXiv 9 Nov 2023.

## Builds on (most cited first, 24 of 24)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [A Reductions Approach to Fair Classification](https://mlsanity.com/paper/1803.02453/) (2018)
- [Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment](https://mlsanity.com/paper/1610.08452/) (2016)
- [Path-Specific Counterfactual Fairness](https://mlsanity.com/paper/1802.08139/) (2018)
- [Counterfactual Fairness in Text Classification through Robustness](https://mlsanity.com/paper/1809.10610/) (2018)
- [Post-processing for Individual Fairness](https://mlsanity.com/paper/2110.13796/) (2021)
- [From Parity to Preference-based Notions of Fairness in Classification](https://mlsanity.com/paper/1707.00010/) (2017)
- [Learning Fair Node Representations with Graph Counterfactual Fairness](https://mlsanity.com/paper/2201.03662/) (2022)
- [Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder](https://mlsanity.com/paper/2011.11878/) (2020)
- [Personalized Counterfactual Fairness in Recommendation](https://mlsanity.com/paper/2105.09829/) (2021)
- [Gender Slopes: Counterfactual Fairness for Computer Vision Models by Attribute Manipulation](https://mlsanity.com/paper/2005.10430/) (2020)
- [Counterfactual Reasoning for Fair Clinical Risk Prediction](https://mlsanity.com/paper/1907.06260/) (2019)
- [Fairness and Accuracy under Domain Generalization](https://mlsanity.com/paper/2301.13323/) (2023)
- [Online certification of preference-based fairness for personalized recommender systems](https://mlsanity.com/paper/2104.14527/) (2021)
- [Fair Sequential Selection Using Supervised Learning Models](https://mlsanity.com/paper/2110.13986/) (2021)
- [Counterfactual fairness: removing direct effects through regularization](https://mlsanity.com/paper/2002.10774/) (2020)
- [Adversarial Learning for Counterfactual Fairness](https://mlsanity.com/paper/2008.13122/) (2020)
- [Loss Balancing for Fair Supervised Learning](https://mlsanity.com/paper/2311.03714/) (2023)
- [Improving Counterfactual Generation for Fair Hate Speech Detection](https://mlsanity.com/paper/2108.01721/) (2021)
- [Disentangled Representation with Causal Constraints for Counterfactual Fairness](https://mlsanity.com/paper/2208.09147/) (2022)
- [Achieving Counterfactual Fairness for Anomaly Detection](https://mlsanity.com/paper/2303.02318/) (2023)
- [COFFEE: Counterfactual Fairness for Personalized Text Generation in Explainable Recommendation](https://mlsanity.com/paper/2210.15500/) (2022)
- [Counterfactual Multi-Token Fairness in Text Classification](https://mlsanity.com/paper/2202.03792/) (2022)

## Built on by (most cited first, 9 of 9)

- [Fairness and Bias Mitigation in Computer Vision: A Survey](https://mlsanity.com/paper/2408.02464/) (2024)
- [Counterfactual Fairness by Combining Factual and Counterfactual Predictions](https://mlsanity.com/paper/2409.01977/) (2024)
- [Counterfactual Fairness Evaluation of Machine Learning Models on Educational Datasets](https://mlsanity.com/paper/2504.11504/) (2025)
- [Lookahead Counterfactual Fairness](https://mlsanity.com/paper/2412.01065/) (2024)
- [Counterfactually Fair Conformal Prediction](https://mlsanity.com/paper/2510.08724/) (2025)
- [Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMs](https://mlsanity.com/paper/2602.03895/) (2026)
- [Learning Counterfactual Outcomes Under Rank Preservation](https://mlsanity.com/paper/2502.06398/) (2025)
- [Individual Fairness In Strategic Classification](https://mlsanity.com/paper/2602.05084/) (2026)
- [Identifiable Multimodal Causal Representation Learning under Partial Latent Sharing](https://mlsanity.com/paper/2605.19135/) (2026)

## Abstract (arXiv)

The use of machine learning models in high-stake applications (e.g., healthcare, lending, college admission) has raised growing concerns due to potential biases against protected social groups. Various fairness notions and methods have been proposed to mitigate such biases. In this work, we focus on Counterfactual Fairness (CF), a fairness notion that is dependent on an underlying causal graph and first proposed by Kusner textitet al.~citekusner2017counterfactual; it requires that the outcome an individual perceives is the same in the real world as it would be in a "counterfactual" world, in which the individual belongs to another social group. Learning fair models satisfying CF can be challenging. It was shown in citekusner2017counterfactual that a sufficient condition for satisfying CF is to not use features that are descendants of sensitive attributes in the causal graph. This implies a simple method that learns CF models only using non-descendants of sensitive attributes while eliminating all descendants. Although several subsequent works proposed methods that use all features for training CF models, there is no theoretical guarantee that they can satisfy CF. In contrast, this work proposes a new algorithm that trains models using all the available features. We theoretically and empirically show that models trained with this method can satisfy CFfootnoteThe code repository for this work can be found in urlhttps://github.com/osu-srml/CFRepresentationLearning.