# Proxy Non-Discrimination in Data-Driven Systems

arXiv: https://arxiv.org/abs/1707.08120 · HTML: https://mlsanity.com/paper/1707.08120/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jul 2017.

## Built on by (most cited first, 13 of 13)

- [A survey on datasets for fairness-aware machine learning](https://mlsanity.com/paper/2110.00530/) (2021)
- [Evaluating and Mitigating Discrimination in Language Model Decisions](https://mlsanity.com/paper/2312.03689/) (2023)
- [Modeling Techniques for Machine Learning Fairness: A Survey](https://mlsanity.com/paper/2111.03015/) (2021)
- [Can Active Learning Preemptively Mitigate Fairness Issues?](https://mlsanity.com/paper/2104.06879/) (2021)
- [Equity and Artificial Intelligence in Education: Will "AIEd" Amplify or Alleviate Inequities in Education?](https://mlsanity.com/paper/2104.12920/) (2021)
- [What is Proxy Discrimination?](https://mlsanity.com/paper/2205.05265/) (2022)
- [Fairness-Aware Meta-Learning via Nash Bargaining](https://mlsanity.com/paper/2406.07029/) (2024)
- [Fairness without Sensitive Attributes via Knowledge Sharing](https://mlsanity.com/paper/2409.18470/) (2024)
- [Hidden Technical Debts for Fair Machine Learning in Financial Services](https://mlsanity.com/paper/2103.10510/) (2021)
- [Neural Contrastive Clustering: Fully Unsupervised Bias Reduction for Sentiment Classification](https://mlsanity.com/paper/2204.10467/) (2022)
- [Community Detection on Model Explanation Graphs for Explainable AI](https://mlsanity.com/paper/2510.27655/) (2025)
- [Fair Feature Importance Scores via Feature Occlusion and Permutation](https://mlsanity.com/paper/2602.09196/) (2026)
- [Null importance: Disentangling relevance for interpretable machine learning](https://mlsanity.com/paper/2609.19511/) (2026)

## Abstract (arXiv)

Machine learnt systems inherit biases against protected classes, historically disparaged groups, from training data. Usually, these biases are not explicit, they rely on subtle correlations discovered by training algorithms, and are therefore difficult to detect. We formalize proxy discrimination in data-driven systems, a class of properties indicative of bias, as the presence of protected class correlates that have causal influence on the system's output. We evaluate an implementation on a corpus of social datasets, demonstrating how to validate systems against these properties and to repair violations where they occur.