# Demographic-Agnostic Fairness without Harm

arXiv: https://arxiv.org/abs/2509.24077 · HTML: https://mlsanity.com/paper/2509.24077/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 45 references that are in the map.
- First posted on arXiv 28 Sep 2025.

## Builds on (most cited first, 20 of 20)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness](https://mlsanity.com/paper/1711.05144/) (2017)
- [Fairness Without Demographics in Repeated Loss Minimization](https://mlsanity.com/paper/1806.08010/) (2018)
- [Fairness without Demographics through Adversarially Reweighted Learning](https://mlsanity.com/paper/2006.13114/) (2020)
- [No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems](https://mlsanity.com/paper/2011.12945/) (2020)
- [From Parity to Preference-based Notions of Fairness in Classification](https://mlsanity.com/paper/1707.00010/) (2017)
- [How Do Fair Decisions Fare in Long-term Qualification?](https://mlsanity.com/paper/2010.11300/) (2020)
- ["What We Can't Measure, We Can't Understand": Challenges to Demographic Data Procurement in the Pursuit of Fairness](https://mlsanity.com/paper/2011.02282/) (2020)
- [Group Retention when Using Machine Learning in Sequential Decision Making: the Interplay between User Dynamics and Fairness](https://mlsanity.com/paper/1905.00569/) (2019)
- [Fairness in Learning-Based Sequential Decision Algorithms: A Survey](https://mlsanity.com/paper/2001.04861/) (2020)
- [Evaluating Fairness of Machine Learning Models Under Uncertain and Incomplete Information](https://mlsanity.com/paper/2102.08410/) (2021)
- [Fairness and Accuracy under Domain Generalization](https://mlsanity.com/paper/2301.13323/) (2023)
- [Fairness without the sensitive attribute via Causal Variational Autoencoder](https://mlsanity.com/paper/2109.04999/) (2021)
- [Weak Proxies are Sufficient and Preferable for Fairness with Missing Sensitive Attributes](https://mlsanity.com/paper/2210.03175/) (2022)
- [Fair Sequential Selection Using Supervised Learning Models](https://mlsanity.com/paper/2110.13986/) (2021)
- [Fair Ranking as Fair Division: Impact-Based Individual Fairness in Ranking](https://mlsanity.com/paper/2206.07247/) (2022)
- [Fairness Without Harm: An Influence-Guided Active Sampling Approach](https://mlsanity.com/paper/2402.12789/) (2024)
- [Loss Balancing for Fair Supervised Learning](https://mlsanity.com/paper/2311.03714/) (2023)
- [Hyper-parameter Tuning for Fair Classification without Sensitive Attribute Access](https://mlsanity.com/paper/2302.01385/) (2023)
- [Post-processing for Fair Regression via Explainable SVD](https://mlsanity.com/paper/2504.03093/) (2025)

## Built on by (most cited first, 1 of 1)

- [Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMs](https://mlsanity.com/paper/2602.03895/) (2026)

## Abstract (arXiv)

As machine learning (ML) algorithms are increasingly used in social domains to make predictions about humans, there is a growing concern that these algorithms may exhibit biases against certain social groups. Numerous notions of fairness have been proposed in the literature to measure the unfairness of ML. Among them, one class that receives the most attention is textitparity-based, i.e., achieving fairness by equalizing treatment or outcomes for different social groups. However, achieving parity-based fairness often comes at the cost of lowering model accuracy and is undesirable for many high-stakes domains like healthcare. To avoid inferior accuracy, a line of research focuses on textitpreference-based fairness, under which any group of individuals would experience the highest accuracy and collectively prefer the ML outcomes assigned to them if they were given the choice between various sets of outcomes. However, these works assume individual demographic information is known and fully accessible during training. In this paper, we relax this requirement and propose a novel textitdemographic-agnostic fairness without harm (DAFH) optimization algorithm, which jointly learns a group classifier that partitions the population into multiple groups and a set of decoupled classifiers associated with these groups. Theoretically, we conduct sample complexity analysis and show that our method can outperform the baselines when demographic information is known and used to train decoupled classifiers. Experiments on both synthetic and real data validate the proposed method.