# FairIF: Boosting Fairness in Deep Learning via Influence Functions with Validation Set Sensitive Attributes

arXiv: https://arxiv.org/abs/2201.05759 · HTML: https://mlsanity.com/paper/2201.05759/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 62 references that are in the map.
- First posted on arXiv 15 Jan 2022.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [A Reductions Approach to Fair Classification](https://mlsanity.com/paper/1803.02453/) (2018)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [Fairness in Machine Learning: A Survey](https://mlsanity.com/paper/2010.04053/) (2020)
- [Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment](https://mlsanity.com/paper/1610.08452/) (2016)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias](https://mlsanity.com/paper/1810.01943/) (2018)
- [Deep Face Recognition: A Survey](https://mlsanity.com/paper/1804.06655/) (2018)
- [Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation](https://mlsanity.com/paper/1911.11834/) (2019)
- [Influence Functions in Deep Learning Are Fragile](https://mlsanity.com/paper/2006.14651/) (2020)
- [Fairness without Demographics through Adversarially Reweighted Learning](https://mlsanity.com/paper/2006.13114/) (2020)
- [Coresets via Bilevel Optimization for Continual Learning and Streaming](https://mlsanity.com/paper/2006.03875/) (2020)
- [On the Accuracy of Influence Functions for Measuring Group Effects](https://mlsanity.com/paper/1905.13289/) (2019)
- [Identifying and Correcting Label Bias in Machine Learning](https://mlsanity.com/paper/1901.04966/) (2019)
- [FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging](https://mlsanity.com/paper/2012.15781/) (2020)
- [A Clarification of the Nuances in the Fairness Metrics Landscape](https://mlsanity.com/paper/2106.00467/) (2021)
- [Bias in Machine Learning Software: Why? How? What to do?](https://mlsanity.com/paper/2105.12195/) (2021)
- [On Second-Order Group Influence Functions for Black-Box Predictions](https://mlsanity.com/paper/1911.00418/) (2019)
- [Conditional Learning of Fair Representations](https://mlsanity.com/paper/1910.07162/) (2019)
- [Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning](https://mlsanity.com/paper/2007.01293/) (2020)
- [Interactive Label Cleaning with Example-based Explanations](https://mlsanity.com/paper/2106.03922/) (2021)
- [Second-Order Stochastic Optimization for Machine Learning in Linear Time](https://mlsanity.com/paper/1602.03943/) (2016)

## Built on by (most cited first, 12 of 12)

- [Comprehensive Fair Meta-learned Recommender System](https://mlsanity.com/paper/2206.04789/) (2022)
- [OxonFair: A Flexible Toolkit for Algorithmic Fairness](https://mlsanity.com/paper/2407.13710/) (2024)
- [A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning](https://mlsanity.com/paper/2505.19281/) (2025)
- [Better Training Data Attribution via Better Inverse Hessian-Vector Products](https://mlsanity.com/paper/2507.14740/) (2025)
- [Understanding Programmatic Weak Supervision via Source-aware Influence Function](https://mlsanity.com/paper/2205.12879/) (2022)
- [Group-robust Sample Reweighting for Subpopulation Shifts via Influence Functions](https://mlsanity.com/paper/2503.07315/) (2025)
- [Data Debiasing with Datamodels (D3M): Improving Subgroup Robustness via Data Selection](https://mlsanity.com/paper/2406.16846/) (2024)
- [Influence-based Attributions can be Manipulated](https://mlsanity.com/paper/2409.05208/) (2024)
- [Delayed Feedback Modeling with Influence Functions](https://mlsanity.com/paper/2502.01669/) (2025)
- [Revisiting Data Attribution for Influence Functions](https://mlsanity.com/paper/2508.07297/) (2025)
- [Detecting labeling bias using influence functions](https://mlsanity.com/paper/2602.19130/) (2026)
- [A case for data valuation transparency via DValCards](https://mlsanity.com/paper/2506.23349/) (2025)

## Abstract (arXiv)

Most fair machine learning methods either highly rely on the sensitive information of the training samples or require a large modification on the target models, which hinders their practical application. To address this issue, we propose a two-stage training algorithm named FAIRIF. It minimizes the loss over the reweighted data set (second stage) where the sample weights are computed to balance the model performance across different demographic groups (first stage). FAIRIF can be applied on a wide range of models trained by stochastic gradient descent without changing the model, while only requiring group annotations on a small validation set to compute sample weights. Theoretically, we show that, in the classification setting, three notions of disparity among different groups can be mitigated by training with the weights. Experiments on synthetic data sets demonstrate that FAIRIF yields models with better fairness-utility trade-offs against various types of bias; and on real-world data sets, we show the effectiveness and scalability of FAIRIF. Moreover, as evidenced by the experiments with pretrained models, FAIRIF is able to alleviate the unfairness issue of pretrained models without hurting their performance.