# Fair Machine Learning under Limited Demographically Labeled Data

arXiv: https://arxiv.org/abs/2106.04757 · HTML: https://mlsanity.com/paper/2106.04757/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 44 references that are in the map.
- First posted on arXiv 3 Jun 2021.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [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)
- [Meta-Learning with Implicit Gradients](https://mlsanity.com/paper/1909.04630/) (2019)
- [On Fairness and Calibration](https://mlsanity.com/paper/1709.02012/) (2017)
- [Bilevel Programming for Hyperparameter Optimization and Meta-Learning](https://mlsanity.com/paper/1806.04910/) (2018)
- [Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks](https://mlsanity.com/paper/2103.14749/) (2021)
- [Fairness Without Demographics in Repeated Loss Minimization](https://mlsanity.com/paper/1806.08010/) (2018)
- [AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias](https://mlsanity.com/paper/1810.01943/) (2018)
- [Optimizing Millions of Hyperparameters by Implicit Differentiation](https://mlsanity.com/paper/1911.02590/) (2019)
- [Improving fairness in machine learning systems: What do industry practitioners need?](https://mlsanity.com/paper/1812.05239/) (2018)
- [Fairness without Demographics through Adversarially Reweighted Learning](https://mlsanity.com/paper/2006.13114/) (2020)
- [Empirical Risk Minimization under Fairness Constraints](https://mlsanity.com/paper/1802.08626/) (2018)
- [Truncated Back-propagation for Bilevel Optimization](https://mlsanity.com/paper/1810.10667/) (2018)
- [Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees](https://mlsanity.com/paper/1806.06055/) (2018)
- [FairBatch: Batch Selection for Model Fairness](https://mlsanity.com/paper/2012.01696/) (2020)
- [Generalized Inner Loop Meta-Learning](https://mlsanity.com/paper/1910.01727/) (2019)
- [FR-Train: A Mutual Information-Based Approach to Fair and Robust Training](https://mlsanity.com/paper/2002.10234/) (2020)
- [Deep Bilevel Learning](https://mlsanity.com/paper/1809.01465/) (2018)
- [Penalizing Unfairness in Binary Classification](https://mlsanity.com/paper/1707.00044/) (2017)

## Built on by (most cited first, 2 of 2)

- [AIFS-SUBS: Extending Data-Driven Forecasting to Sub-Seasonal Timescales](https://mlsanity.com/paper/2607.05100/) (2026)
- [Transferring Fairness using Multi-Task Learning with Limited Demographic Information](https://mlsanity.com/paper/2305.12671/) (2023)

## Abstract (arXiv)

Research has shown that, machine learning models might inherit and propagate undesired social biases encoded in the data. To address this problem, fair training algorithms are developed. However, most algorithms assume we know demographic/sensitive data features such as gender and race. This assumption falls short in scenarios where collecting demographic information is not feasible due to privacy concerns, and data protection policies. A recent line of work develops fair training methods that can function without any demographic feature on the data, that are collectively referred as Rawlsian methods. Yet, we show in experiments that, Rawlsian methods tend to exhibit relatively high bias. Given this, we look at the middle ground between the previous approaches, and consider a setting where we know the demographic attributes for only a small subset of our data. In such a setting, we design fair training algorithms which exhibit both good utility, and low bias. In particular, we show that our techniques can train models to significantly outperform Rawlsian approaches even when 0.1% of demographic attributes are available in the training data. Furthermore, our main algorithm can accommodate multiple training objectives easily. We expand our main algorithm to achieve robustness to label noise in addition to fairness in the limited demographics setting to highlight that property as well.