# Differential Adjusted Parity for Learning Fair Representations

arXiv: https://arxiv.org/abs/2502.09765 · HTML: https://mlsanity.com/paper/2502.09765/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 13 Feb 2025.

## Builds on (most cited first, 9 of 9)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [The Variational Fair Autoencoder](https://mlsanity.com/paper/1511.00830/) (2015)
- [Conditional Learning of Fair Representations](https://mlsanity.com/paper/1910.07162/) (2019)
- [It's COMPASlicated: The Messy Relationship between RAI Datasets and Algorithmic Fairness Benchmarks](https://mlsanity.com/paper/2106.05498/) (2021)
- [NestedVAE: Isolating Common Factors via Weak Supervision](https://mlsanity.com/paper/2002.11576/) (2020)
- [Fair Representations by Compression](https://mlsanity.com/paper/2105.14044/) (2021)

## Abstract (arXiv)

The development of fair and unbiased machine learning models remains an ongoing objective for researchers in the field of artificial intelligence. We introduce the Differential Adjusted Parity (DAP) loss to produce unbiased informative representations. It utilises a differentiable variant of the adjusted parity metric to create a unified objective function. By combining downstream task classification accuracy and its inconsistency across sensitive feature domains, it provides a single tool to increase performance and mitigate bias. A key element in this approach is the use of soft balanced accuracies. In contrast to previous non-adversarial approaches, DAP does not suffer a degeneracy where the metric is satisfied by performing equally poorly across all sensitive domains. It outperforms several adversarial models on downstream task accuracy and fairness in our analysis. Specifically, it improves the demographic parity, equalized odds and sensitive feature accuracy by as much as 22.5%, 44.1% and 40.1%, respectively, when compared to the best performing adversarial approaches on these metrics. Overall, the DAP loss and its associated metric can play a significant role in creating more fair machine learning models.