mlsanityData to 14 Oct 2026

On the Cause of Unfairness: A Training Sample Perspective

arXiv 2306.17828 ↗First posted 30 Jun 2023cs.LG cs.AI cs.CYcited by 0

Not on the map. Why?

Abstract (arXiv)

Identifying the causes of a model's unfairness is an important yet relatively unexplored task. We look into this problem through the lens of training data - the major source of unfairness. We ask the following questions: How would the unfairness of a model change if its training samples (1) were collected from a different (e.g. demographic) group, (2) were labeled differently, or (3) whose features were modified? In other words, we quantify the influence of training samples on unfairness by counterfactually changing samples based on predefined concepts, i.e. data attributes such as features, labels, and sensitive attributes. Our framework not only can help practitioners understand the observed unfairness and mitigate it by repairing their training data, but also leads to many other applications, e.g. detecting mislabeling, fixing imbalanced representations, and detecting fairness-targeted poisoning attacks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 41 of its 73 references that are in the map. First posted on arXiv 30 Jun 2023.

Builds on

41 of 73 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  3. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  4. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  5. 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 672
  6. 2018A Reductions Approach to Fair Classificationcited by 587
  7. 2020Estimating Training Data Influence by Tracing Gradient Descentcited by 580
  8. 2019Does Learning Require Memorization? A Short Tale about a Long Tailcited by 460
  9. 2021Retiring Adult: New Datasets for Fair Machine Learningcited by 449
  10. 2018Learning Adversarially Fair and Transferable Representationscited by 353
  11. 2018Actionable Recourse in Linear Classificationcited by 328
  12. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
29 more
  1. 2021Anti-Backdoor Learning: Training Clean Models on Poisoned Datacited by 263
  2. 2020Influence Functions in Deep Learning Are Fragilecited by 252
  3. 2020Fairness without Demographics through Adversarially Reweighted Learningcited by 251
  4. 2018FairGAN: Fairness-aware Generative Adversarial Networkscited by 164
  5. 2019On the Accuracy of Influence Functions for Measuring Group Effectscited by 147
  6. 2022BackdoorBench: A Comprehensive Benchmark of Backdoor Learningcited by 128
  7. 2021Fair Mixup: Fairness via Interpolationcited by 109
  8. 2021DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networkscited by 109
  9. 2018Learning Controllable Fair Representationscited by 83
  10. 2019On Second-Order Group Influence Functions for Black-Box Predictionscited by 79
  11. 2020Fair Classification with Group-Dependent Label Noisecited by 67
  12. 2020Robust Fairness under Covariate Shiftcited by 58
  13. 2019FlipTest: Fairness Testing via Optimal Transportcited by 51
  14. 2022Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Modelscited by 47
  15. 2020Fairness Evaluation in Presence of Biased Noisy Labelscited by 38
  16. 2022Achieving Fairness at No Utility Cost via Data Reweighing with Influencecited by 38
  17. 2022Fairness Reprogrammingcited by 33
  18. 2021The Rich Get Richer: Disparate Impact of Semi-Supervised Learningcited by 28
  19. 2022Fairness Transferability Subject to Bounded Distribution Shiftcited by 28
  20. 2022Understanding Instance-Level Impact of Fairness Constraintscited by 27
  21. 2022Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refittingcited by 26
  22. 2021Fair Classification with Adversarial Perturbationscited by 23
  23. 2021Understanding Instance-Level Label Noise: Disparate Impacts and Treatmentscited by 22
  24. 2021Deep Clustering based Fair Outlier Detectioncited by 19
  25. 2022Characterizing the Influence of Graph Elementscited by 16
  26. 2021Can Less be More? When Increasing-to-Balancing Label Noise Rates Considered Beneficialcited by 13
  27. 2022Robust Fair Clustering: A Novel Fairness Attack and Defense Frameworkcited by 13
  28. 2021Fairness-Aware Unsupervised Feature Selectioncited by 10
  29. 2022Learning Antidote Data to Individual Unfairnesscited by 8

Built on by

Not cited yet.