# Understanding Instance-Level Impact of Fairness Constraints

arXiv: https://arxiv.org/abs/2206.15437 · HTML: https://mlsanity.com/paper/2206.15437/

## 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 (most cited first, 30 of 47)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Neural Tangent Kernel: Convergence and Generalization in Neural Networks](https://mlsanity.com/paper/1806.07572/) (2018)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [A Reductions Approach to Fair Classification](https://mlsanity.com/paper/1803.02453/) (2018)
- [Estimating Training Data Influence by Tracing Gradient Descent](https://mlsanity.com/paper/2002.08484/) (2020)
- [Deep Learning on a Data Diet: Finding Important Examples Early in Training](https://mlsanity.com/paper/2107.07075/) (2021)
- [What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation](https://mlsanity.com/paper/2008.03703/) (2020)
- [Does Learning Require Memorization? A Short Tale about a Long Tail](https://mlsanity.com/paper/1906.05271/) (2019)
- [Algorithmic decision making and the cost of fairness](https://mlsanity.com/paper/1701.08230/) (2017)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [Actionable Recourse in Linear Classification](https://mlsanity.com/paper/1809.06514/) (2018)
- [Influence Functions in Deep Learning Are Fragile](https://mlsanity.com/paper/2006.14651/) (2020)
- [Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practices](https://mlsanity.com/paper/1906.09208/) (2019)
- [Stronger Data Poisoning Attacks Break Data Sanitization Defenses](https://mlsanity.com/paper/1811.00741/) (2018)
- [Fair Mixup: Fairness via Interpolation](https://mlsanity.com/paper/2103.06503/) (2021)
- [Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goals](https://mlsanity.com/paper/1809.04198/) (2018)
- [Understanding the Origins of Bias in Word Embeddings](https://mlsanity.com/paper/1810.03611/) (2018)

## Built on by (most cited first, 27 of 27)

- [Model Sparsity Can Simplify Machine Unlearning](https://mlsanity.com/paper/2304.04934/) (2023)
- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [Preserving Fairness Generalization in Deepfake Detection](https://mlsanity.com/paper/2402.17229/) (2024)
- [Improving Fairness in Deepfake Detection](https://mlsanity.com/paper/2306.16635/) (2023)
- [Most Influential Subset Selection: Challenges, Promises, and Beyond](https://mlsanity.com/paper/2409.18153/) (2024)
- [AI-Face: A Million-Scale Demographically Annotated AI-Generated Face Dataset and Fairness Benchmark](https://mlsanity.com/paper/2406.00783/) (2024)
- [Fair Machine Unlearning: Data Removal while Mitigating Disparities](https://mlsanity.com/paper/2307.14754/) (2023)
- [Weak Proxies are Sufficient and Preferable for Fairness with Missing Sensitive Attributes](https://mlsanity.com/paper/2210.03175/) (2022)
- [Post-hoc Bias Scoring Is Optimal For Fair Classification](https://mlsanity.com/paper/2310.05725/) (2023)
- [Group-Level Data Selection for Efficient Pretraining](https://mlsanity.com/paper/2502.14709/) (2025)
- [Fairness Without Harm: An Influence-Guided Active Sampling Approach](https://mlsanity.com/paper/2402.12789/) (2024)
- [Label Smoothing Improves Machine Unlearning](https://mlsanity.com/paper/2406.07698/) (2024)
- [Fairshare Data Pricing via Data Valuation for Large Language Models](https://mlsanity.com/paper/2502.00198/) (2025)
- [Towards Algorithmic Fairness by means of Instance-level Data Re-weighting based on Shapley Values](https://mlsanity.com/paper/2303.01928/) (2023)
- [Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools](https://mlsanity.com/paper/2309.17337/) (2023)
- [Fairness Improves Learning from Noisily Labeled Long-Tailed Data](https://mlsanity.com/paper/2303.12291/) (2023)
- [Incorporating Rather Than Eliminating: Achieving Fairness for Skin Disease Diagnosis Through Group-Specific Expert](https://mlsanity.com/paper/2506.17787/) (2025)
- [EAB-FL: Exacerbating Algorithmic Bias through Model Poisoning Attacks in Federated Learning](https://mlsanity.com/paper/2410.02042/) (2024)
- [Representation Magnitude has a Liability to Privacy Vulnerability](https://mlsanity.com/paper/2407.16164/) (2024)
- [To be Robust and to be Fair: Aligning Fairness with Robustness](https://mlsanity.com/paper/2304.00061/) (2023)
- [Unlearning Information Bottleneck: Machine Unlearning of Systematic Patterns and Biases](https://mlsanity.com/paper/2405.14020/) (2024)
- [FairX: A comprehensive benchmarking tool for model analysis using fairness, utility, and explainability](https://mlsanity.com/paper/2406.14281/) (2024)
- [Evaluating the Impact of Local Differential Privacy on Utility Loss via Influence Functions](https://mlsanity.com/paper/2309.08678/) (2023)
- [Detecting labeling bias using influence functions](https://mlsanity.com/paper/2602.19130/) (2026)
- [On the Cause of Unfairness: A Training Sample Perspective](https://mlsanity.com/paper/2306.17828/) (2023)
- [Fair4Free: Generating High-fidelity Fair Synthetic Samples using Data Free Distillation](https://mlsanity.com/paper/2410.01423/) (2024)
- [A Critical Review of Predominant Bias in Neural Networks](https://mlsanity.com/paper/2502.11031/) (2025)

## 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.