# FORML: Learning to Reweight Data for Fairness

arXiv: https://arxiv.org/abs/2202.01719 · HTML: https://mlsanity.com/paper/2202.01719/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 67 references that are in the map.
- First posted on arXiv 3 Feb 2022.

## Builds on (most cited first, 30 of 37)

- [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)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [An Empirical Study of Example Forgetting during Deep Neural Network Learning](https://mlsanity.com/paper/1812.05159/) (2018)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [Learning to learn by gradient descent by gradient descent](https://mlsanity.com/paper/1606.04474/) (2016)
- [Inherent Trade-Offs in the Fair Determination of Risk Scores](https://mlsanity.com/paper/1609.05807/) (2016)
- [Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics](https://mlsanity.com/paper/2009.10795/) (2020)
- [On Fairness and Calibration](https://mlsanity.com/paper/1709.02012/) (2017)
- [Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment](https://mlsanity.com/paper/1610.08452/) (2016)
- [Identifying Mislabeled Data using the Area Under the Margin Ranking](https://mlsanity.com/paper/2001.10528/) (2020)
- [Fairness without Demographics through Adversarially Reweighted Learning](https://mlsanity.com/paper/2006.13114/) (2020)
- [A General and Adaptive Robust Loss Function](https://mlsanity.com/paper/1701.03077/) (2017)
- [A Convex Framework for Fair Regression](https://mlsanity.com/paper/1706.02409/) (2017)
- [Identifying and Correcting Label Bias in Machine Learning](https://mlsanity.com/paper/1901.04966/) (2019)
- [Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goals](https://mlsanity.com/paper/1809.04198/) (2018)
- [FairBatch: Batch Selection for Model Fairness](https://mlsanity.com/paper/2012.01696/) (2020)
- [Class Rectification Hard Mining for Imbalanced Deep Learning](https://mlsanity.com/paper/1712.03162/) (2017)
- [Two-Player Games for Efficient Non-Convex Constrained Optimization](https://mlsanity.com/paper/1804.06500/) (2018)
- [Sample Selection for Fair and Robust Training](https://mlsanity.com/paper/2110.14222/) (2021)
- [AdaFair: Cumulative Fairness Adaptive Boosting](https://mlsanity.com/paper/1909.08982/) (2019)
- [Scalable Learning of Non-Decomposable Objectives](https://mlsanity.com/paper/1608.04802/) (2016)

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

- [Interpreting Unfairness in Graph Neural Networks via Training Node Attribution](https://mlsanity.com/paper/2211.14383/) (2022)
- [Muffin: A Framework Toward Multi-Dimension AI Fairness by Uniting Off-the-Shelf Models](https://mlsanity.com/paper/2308.13730/) (2023)
- [Data Optimization in Deep Learning: A Survey](https://mlsanity.com/paper/2310.16499/) (2023)
- [Fairness-Aware Meta-Learning via Nash Bargaining](https://mlsanity.com/paper/2406.07029/) (2024)
- [DiffusionWorldViewer: Exposing and Broadening the Worldview Reflected by Generative Text-to-Image Models](https://mlsanity.com/paper/2309.09944/) (2023)
- [FERI: A Multitask-based Fairness Achieving Algorithm with Applications to Fair Organ Transplantation](https://mlsanity.com/paper/2310.13820/) (2023)
- [Variational Model Merging for Pareto Front Estimation in Multitask Finetuning](https://mlsanity.com/paper/2412.08147/) (2024)
- [Equalized Generative Treatment: Matching f-divergences for Fairness in Generative Models](https://mlsanity.com/paper/2602.08660/) (2026)
- [Constrained Reweighting of Distributions: an Optimal Transport Approach](https://mlsanity.com/paper/2310.12447/) (2023)
- [The Benefits and Risks of Transductive Approaches for AI Fairness](https://mlsanity.com/paper/2406.12011/) (2024)
- [Component-Based Fairness in Face Attribute Classification with Bayesian Network-informed Meta Learning](https://mlsanity.com/paper/2505.01699/) (2025)
- [LiLAW: Lightweight Learnable Adaptive Weighting to Learn Sample Difficulty & Improve Noisy Training](https://mlsanity.com/paper/2509.20786/) (2025)

## Abstract (arXiv)

Machine learning models are trained to minimize the mean loss for a single metric, and thus typically do not consider fairness and robustness. Neglecting such metrics in training can make these models prone to fairness violations when training data are imbalanced or test distributions differ. This work introduces Fairness Optimized Reweighting via Meta-Learning (FORML), a training algorithm that balances fairness and robustness with accuracy by jointly learning training sample weights and neural network parameters. The approach increases model fairness by learning to balance the contributions from both over- and under-represented sub-groups through dynamic reweighting of the data learned from a user-specified held-out set representative of the distribution under which fairness is desired. FORML improves equality of opportunity fairness criteria on image classification tasks, reduces bias of corrupted labels, and facilitates building more fair datasets via data condensation. These improvements are achieved without pre-processing data or post-processing model outputs, without learning an additional weighting function, without changing model architecture, and while maintaining accuracy on the original predictive metric.