mlsanityData to 14 Oct 2026

Understanding Instance-Level Impact of Fairness Constraints

arXiv 2206.15437 ↗First posted 30 Jun 2022cs.LG cs.CYcited by 27

Not on the map. Why?

Abstract (arXiv)

A variety of fairness constraints have been proposed in the literature to mitigate group-level statistical bias. Their impacts have been largely evaluated for different groups of populations corresponding to a set of sensitive attributes, such as race or gender. Nonetheless, the community has not observed sufficient explorations for how imposing fairness constraints fare at an instance level. Building on the concept of influence function, a measure that characterizes the impact of a training example on the target model and its predictive performance, this work studies the influence of training examples when fairness constraints are imposed. We find out that under certain assumptions, the influence function with respect to fairness constraints can be decomposed into a kernelized combination of training examples. One promising application of the proposed fairness influence function is to identify suspicious training examples that may cause model discrimination by ranking their influence scores. We demonstrate with extensive experiments that training on a subset of weighty data examples leads to lower fairness violations with a trade-off of accuracy.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Builds on 47 of its 73 references that are in the map. First posted on arXiv 30 Jun 2022.

Builds on

47 of 73 references.

References · 47

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  4. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  5. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  6. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  7. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,621
  8. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  9. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  10. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
  11. 2018Model Cards for Model Reportingcited by 1,080
  12. 2017Counterfactual Fairnesscited by 804
35 more
  1. 2014Certifying and removing disparate impactcited by 715
  2. 2018MINE: Mutual Information Neural Estimationcited by 683
  3. 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 672
  4. 2018A Reductions Approach to Fair Classificationcited by 587
  5. 2020Estimating Training Data Influence by Tracing Gradient Descentcited by 580
  6. 2021Deep Learning on a Data Diet: Finding Important Examples Early in Trainingcited by 533
  7. 2020What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimationcited by 497
  8. 2019Does Learning Require Memorization? A Short Tale about a Long Tailcited by 460
  9. 2017Algorithmic decision making and the cost of fairnesscited by 403
  10. 2018Learning Adversarially Fair and Transferable Representationscited by 353
  11. 2019The many Shapley values for model explanationcited by 344
  12. 2018Actionable Recourse in Linear Classificationcited by 328
  13. 2020Influence Functions in Deep Learning Are Fragilecited by 252
  14. 2019Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practicescited by 174
  15. 2018Stronger Data Poisoning Attacks Break Data Sanitization Defensescited by 135
  16. 2021Fair Mixup: Fairness via Interpolationcited by 109
  17. 2018Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goalscited by 103
  18. 2018Understanding the Origins of Bias in Word Embeddingscited by 91
  19. 2018Learning Controllable Fair Representationscited by 83
  20. 2019On Second-Order Group Influence Functions for Black-Box Predictionscited by 79
  21. 2020Fair Classification with Group-Dependent Label Noisecited by 67
  22. 2021Post-processing for Individual Fairnesscited by 61
  23. 2021Detecting Corrupted Labels Without Training a Model to Predictcited by 58
  24. 2018Two-Player Games for Efficient Non-Convex Constrained Optimizationcited by 55
  25. 2020An Empirical Characterization of Fair Machine Learning For Clinical Risk Predictioncited by 45
  26. 2021Controllable Guarantees for Fair Outcomes via Contrastive Information Estimationcited by 45
  27. 2020A Distributionally Robust Approach to Fair Classificationcited by 43
  28. 2021Leave-one-out Unfairnesscited by 36
  29. 2021Assessing Multilingual Fairness in Pre-trained Multimodal Representationscited by 35
  30. 2019R'enyi Fair Inferencecited by 33
  31. 2021RadFusion: Benchmarking Performance and Fairness for Multimodal Pulmonary Embolism Detection from CT and EHRcited by 32
  32. 2021The Rich Get Richer: Disparate Impact of Semi-Supervised Learningcited by 28
  33. 2021Cohort Shapley value for algorithmic fairnesscited by 13
  34. 2021Can Less be More? When Increasing-to-Balancing Label Noise Rates Considered Beneficialcited by 13
  35. 2018Envy-Free Classificationcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 10; 2024: 10; 2025: 4; 2026: 1.

27 papers.

Sort:

By area:

  1. 2023Model Sparsity Can Simplify Machine Unlearningcited by 214
  2. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  3. 2024Preserving Fairness Generalization in Deepfake Detectioncited by 70
  4. 2023Improving Fairness in Deepfake Detectioncited by 40
  5. 2024Most Influential Subset Selection: Challenges, Promises, and Beyondcited by 32
  6. 2024AI-Face: A Million-Scale Demographically Annotated AI-Generated Face Dataset and Fairness Benchmarkcited by 28
  7. 2023Fair Machine Unlearning: Data Removal while Mitigating Disparitiescited by 26
  8. 2022Weak Proxies are Sufficient and Preferable for Fairness with Missing Sensitive Attributescited by 17
  9. 2023Post-hoc Bias Scoring Is Optimal For Fair Classificationcited by 14
  10. 2025Group-Level Data Selection for Efficient Pretrainingcited by 13
  11. 2024Fairness Without Harm: An Influence-Guided Active Sampling Approachcited by 12
  12. 2024Label Smoothing Improves Machine Unlearningcited by 9
15 more
  1. 2025Fairshare Data Pricing via Data Valuation for Large Language Modelscited by 8
  2. 2023Towards Algorithmic Fairness by means of Instance-level Data Re-weighting based on Shapley Valuescited by 7
  3. 2023Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Toolscited by 7
  4. 2023Fairness Improves Learning from Noisily Labeled Long-Tailed Datacited by 5
  5. 2025Incorporating Rather Than Eliminating: Achieving Fairness for Skin Disease Diagnosis Through Group-Specific Expertcited by 5
  6. 2024EAB-FL: Exacerbating Algorithmic Bias through Model Poisoning Attacks in Federated Learningcited by 4
  7. 2024Representation Magnitude has a Liability to Privacy Vulnerabilitycited by 3
  8. 2023To be Robust and to be Fair: Aligning Fairness with Robustnesscited by 2
  9. 2024Unlearning Information Bottleneck: Machine Unlearning of Systematic Patterns and Biasescited by 2
  10. 2024FairX: A comprehensive benchmarking tool for model analysis using fairness, utility, and explainabilitycited by 2
  11. 2023Evaluating the Impact of Local Differential Privacy on Utility Loss via Influence Functionscited by 1
  12. 2026Detecting labeling bias using influence functionscited by 1
  13. 2023On the Cause of Unfairness: A Training Sample Perspectivecited by 0
  14. 2024Fair4Free: Generating High-fidelity Fair Synthetic Samples using Data Free Distillationcited by 0
  15. 2025A Critical Review of Predominant Bias in Neural Networkscited by 0