mlsanityData to 14 Oct 2026

Learning Antidote Data to Individual Unfairness

arXiv 2211.15897 ↗First posted 29 Nov 2022cs.LG cs.CYcited by 8

Not on the map. Why?

Abstract (arXiv)

Fairness is essential for machine learning systems deployed in high-stake applications. Among all fairness notions, individual fairness, deriving from a consensus that `similar individuals should be treated similarly,' is a vital notion to describe fair treatment for individual cases. Previous studies typically characterize individual fairness as a prediction-invariant problem when perturbing sensitive attributes on samples, and solve it by Distributionally Robust Optimization (DRO) paradigm. However, such adversarial perturbations along a direction covering sensitive information used in DRO do not consider the inherent feature correlations or innate data constraints, therefore could mislead the model to optimize at off-manifold and unrealistic samples. In light of this drawback, in this paper, we propose to learn and generate antidote data that approximately follows the data distribution to remedy individual unfairness. These generated on-manifold antidote data can be used through a generic optimization procedure along with original training data, resulting in a pure pre-processing approach to individual unfairness, or can also fit well with the in-processing DRO paradigm. Through extensive experiments on multiple tabular datasets, we demonstrate our method resists individual unfairness at a minimal or zero cost to predictive utility compared to baselines.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 32 of its 52 references that are in the map. First posted on arXiv 29 Nov 2022.

Builds on

32 of 52 references.

References · 32

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  2. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  3. 2017Improved Training of Wasserstein GANscited by 2,235
  4. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  5. 2017Counterfactual Fairnesscited by 804
  6. 2019Modeling Tabular data using Conditional GANcited by 699
  7. 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 364
  8. 2018Learning Models with Uniform Performance via Distributionally Robust Optimizationcited by 335
  9. 2018Generating Adversarial Examples with Adversarial Networkscited by 258
  10. 2017Generating Natural Adversarial Examplescited by 183
  11. 2020Large-Scale Methods for Distributionally Robust Optimizationcited by 179
  12. 2018Disentangling Adversarial Robustness and Generalizationcited by 172
20 more
  1. 2018Constructing Unrestricted Adversarial Examples with Generative Modelscited by 135
  2. 2019Adversarial Training Can Hurt Generalizationcited by 132
  3. 2019Training individually fair ML models with Sensitive Subspace Robustnesscited by 73
  4. 2020Learning Certified Individually Fair Representationscited by 69
  5. 2018iFair: Learning Individually Fair Data Representations for Algorithmic Decision Makingcited by 64
  6. 2021It's COMPASlicated: The Messy Relationship between RAI Datasets and Algorithmic Fairness Benchmarkscited by 61
  7. 2021Post-processing for Individual Fairnesscited by 61
  8. 2017Adversarial examples for generative modelscited by 58
  9. 2020Two Simple Ways to Learn Individual Fairness Metrics from Datacited by 54
  10. 2019Metric Learning for Individual Fairnesscited by 52
  11. 2020Verifying Individual Fairness in Machine Learning Modelscited by 49
  12. 2019Average Individual Fairness: Algorithms, Generalization and Experimentscited by 46
  13. 2022Achieving Fairness at No Utility Cost via Data Reweighing with Influencecited by 38
  14. 2020SenSeI: Sensitive Set Invariance for Enforcing Individual Fairnesscited by 37
  15. 2020Individual Fairness in Pipelinescited by 22
  16. 2021Deep Clustering based Fair Outlier Detectioncited by 19
  17. 2020Individual Fairness Revisited: Transferring Techniques from Adversarial Robustnesscited by 17
  18. 2021Statistical inference for individual fairnesscited by 13
  19. 2022Robust Fair Clustering: A Novel Fairness Attack and Defense Frameworkcited by 13
  20. 2021Individually Fair Gradient Boostingcited by 12

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 5; 2025: 1.

8 papers.

  1. 2023Large Language Models Are Better Adversaries: Exploring Generative Clean-Label Backdoor Attacks Against Text Classifierscited by 14
  2. 2024Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Modelscited by 10
  3. 2024AIM: Attributing, Interpreting, Mitigating Data Unfairnesscited by 9
  4. 2024On the Inflation of KNN-Shapley Valuecited by 4
  5. 2024On the Maximal Local Disparity of Fairness-Aware Classifierscited by 3
  6. 2023On the Cause of Unfairness: A Training Sample Perspectivecited by 0
  7. 2024LayerMatch: Do Pseudo-labels Benefit All Layers?cited by 0
  8. 2025Wasserstein Distributionally Robust Optimization Through the Lens of Structural Causal Models and Individual Fairnesscited by 0