# Training individually fair ML models with Sensitive Subspace Robustness

arXiv: https://arxiv.org/abs/1907.00020 · HTML: https://mlsanity.com/paper/1907.00020/

## Key facts

- Cited by 73 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jun 2019.

## Built on by (most cited first, 30 of 73)

- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [Fair Mixup: Fairness via Interpolation](https://mlsanity.com/paper/2103.06503/) (2021)
- [Fast Model Debias with Machine Unlearning](https://mlsanity.com/paper/2310.12560/) (2023)
- [Post-processing for Individual Fairness](https://mlsanity.com/paper/2110.13796/) (2021)
- [Diagnosing failures of fairness transfer across distribution shift in real-world medical settings](https://mlsanity.com/paper/2202.01034/) (2022)
- [Learning Fair Classifiers with Partially Annotated Group Labels](https://mlsanity.com/paper/2111.14581/) (2021)
- [Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimization](https://mlsanity.com/paper/2108.05449/) (2021)
- [Individual Fairness Guarantees for Neural Networks](https://mlsanity.com/paper/2205.05763/) (2022)
- [Optimising Equal Opportunity Fairness in Model Training](https://mlsanity.com/paper/2205.02393/) (2022)
- [Fairify: Fairness Verification of Neural Networks](https://mlsanity.com/paper/2212.06140/) (2022)
- [De-biasing "bias" measurement](https://mlsanity.com/paper/2205.05770/) (2022)
- [Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization](https://mlsanity.com/paper/2303.00442/) (2023)
- [Latent Space Smoothing for Individually Fair Representations](https://mlsanity.com/paper/2111.13650/) (2021)
- [What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspective](https://mlsanity.com/paper/2206.04101/) (2022)
- [CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models](https://mlsanity.com/paper/2407.02408/) (2024)
- [CertiFair: A Framework for Certified Global Fairness of Neural Networks](https://mlsanity.com/paper/2205.09927/) (2022)
- [Accurate Fairness: Improving Individual Fairness without Trading Accuracy](https://mlsanity.com/paper/2205.08704/) (2022)
- [Statistical inference for individual fairness](https://mlsanity.com/paper/2103.16714/) (2021)
- [Domain Adaptation meets Individual Fairness. And they get along](https://mlsanity.com/paper/2205.00504/) (2022)
- [FairProof : Confidential and Certifiable Fairness for Neural Networks](https://mlsanity.com/paper/2402.12572/) (2024)
- [Fairness and Bias Mitigation in Computer Vision: A Survey](https://mlsanity.com/paper/2408.02464/) (2024)
- [Individually Fair Gradient Boosting](https://mlsanity.com/paper/2103.16785/) (2021)
- [Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach](https://mlsanity.com/paper/2303.03300/) (2023)
- [A Fairness Analysis on Private Aggregation of Teacher Ensembles](https://mlsanity.com/paper/2109.08630/) (2021)
- [Fairness with Continuous Optimal Transport](https://mlsanity.com/paper/2101.02084/) (2021)
- [Wasserstein Robust Classification with Fairness Constraints](https://mlsanity.com/paper/2103.06828/) (2021)
- [Towards A Holistic View of Bias in Machine Learning: Bridging Algorithmic Fairness and Imbalanced Learning](https://mlsanity.com/paper/2207.06084/) (2022)
- [Robust Fairness-aware Learning Under Sample Selection Bias](https://mlsanity.com/paper/2105.11570/) (2021)
- [InfoOT: Information Maximizing Optimal Transport](https://mlsanity.com/paper/2210.03164/) (2022)
- [A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities](https://mlsanity.com/paper/2210.08906/) (2022)

## Abstract (arXiv)

We consider training machine learning models that are fair in the sense that their performance is invariant under certain sensitive perturbations to the inputs. For example, the performance of a resume screening system should be invariant under changes to the gender and/or ethnicity of the applicant. We formalize this notion of algorithmic fairness as a variant of individual fairness and develop a distributionally robust optimization approach to enforce it during training. We also demonstrate the effectiveness of the approach on two ML tasks that are susceptible to gender and racial biases.