# FairALM: Augmented Lagrangian Method for Training Fair Models with Little Regret

arXiv: https://arxiv.org/abs/2004.01355 · HTML: https://mlsanity.com/paper/2004.01355/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2020.

## Built on by (most cited first, 22 of 22)

- [Improving the Fairness of Chest X-ray Classifiers](https://mlsanity.com/paper/2203.12609/) (2022)
- [Survey of Social Bias in Vision-Language Models](https://mlsanity.com/paper/2309.14381/) (2023)
- [Group-Aware Threshold Adaptation for Fair Classification](https://mlsanity.com/paper/2111.04271/) (2021)
- [Competitive Physics Informed Networks](https://mlsanity.com/paper/2204.11144/) (2022)
- [On the Versatile Uses of Partial Distance Correlation in Deep Learning](https://mlsanity.com/paper/2207.09684/) (2022)
- [Machine Unlearning under Retain-Forget Entanglement](https://mlsanity.com/paper/2603.26569/) (2026)
- [Fair Bilevel Neural Network (FairBiNN): On Balancing fairness and accuracy via Stackelberg Equilibrium](https://mlsanity.com/paper/2410.16432/) (2024)
- [An Online Riemannian PCA for Stochastic Canonical Correlation Analysis](https://mlsanity.com/paper/2106.07479/) (2021)
- [Learning Invariant Representations using Inverse Contrastive Loss](https://mlsanity.com/paper/2102.08343/) (2021)
- [Through a fair looking-glass: mitigating bias in image datasets](https://mlsanity.com/paper/2209.08648/) (2022)
- [A Large-Scale Empirical Study on Improving the Fairness of Image Classification Models](https://mlsanity.com/paper/2401.03695/) (2024)
- [Pooling Image Datasets With Multiple Covariate Shift and Imbalance](https://mlsanity.com/paper/2403.02598/) (2024)
- [Backdoor for Debias: Mitigating Model Bias with Backdoor Attack-based Artificial Bias](https://mlsanity.com/paper/2303.01504/) (2023)
- [Distraction is All You Need for Fairness](https://mlsanity.com/paper/2203.07593/) (2022)
- [MLHOps: Machine Learning for Healthcare Operations](https://mlsanity.com/paper/2305.02474/) (2023)
- [Fairness-aware Federated Minimax Optimization with Convergence Guarantee](https://mlsanity.com/paper/2307.04417/) (2023)
- [Dual Optimistic Ascent (PI Control) is the Augmented Lagrangian Method in Disguise](https://mlsanity.com/paper/2509.22500/) (2025)
- [F3: Fair and Federated Face Attribute Classification with Heterogeneous Data](https://mlsanity.com/paper/2109.02351/) (2021)
- [Learning Unbiased Image Segmentation: A Case Study with Plain Knee Radiographs](https://mlsanity.com/paper/2308.04356/) (2023)
- [A Critical Review of Predominant Bias in Neural Networks](https://mlsanity.com/paper/2502.11031/) (2025)
- [Unbiased Model Prediction Without Using Protected Attribute Information](https://mlsanity.com/paper/2603.29270/) (2026)
- [Neuron Incidence Redistribution for Fairness in Medical Image Classification](https://mlsanity.com/paper/2605.19393/) (2026)

## Abstract (arXiv)

Algorithmic decision making based on computer vision and machine learning technologies continue to permeate our lives. But issues related to biases of these models and the extent to which they treat certain segments of the population unfairly, have led to concern in the general public. It is now accepted that because of biases in the datasets we present to the models, a fairness-oblivious training will lead to unfair models. An interesting topic is the study of mechanisms via which the de novo design or training of the model can be informed by fairness measures. Here, we study mechanisms that impose fairness concurrently while training the model. While existing fairness based approaches in vision have largely relied on training adversarial modules together with the primary classification/regression task, in an effort to remove the influence of the protected attribute or variable, we show how ideas based on well-known optimization concepts can provide a simpler alternative. In our proposed scheme, imposing fairness just requires specifying the protected attribute and utilizing our optimization routine. We provide a detailed technical analysis and present experiments demonstrating that various fairness measures from the literature can be reliably imposed on a number of training tasks in vision in a manner that is interpretable.