# Achieving non-discrimination in data release

arXiv: https://arxiv.org/abs/1611.07438 · HTML: https://mlsanity.com/paper/1611.07438/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Nov 2016.

## Built on by (most cited first, 23 of 23)

- [Towards Fair Classifiers Without Sensitive Attributes: Exploring Biases in Related Features](https://mlsanity.com/paper/2104.14537/) (2021)
- [FairNeuron: Improving Deep Neural Network Fairness with Adversary Games on Selective Neurons](https://mlsanity.com/paper/2204.02567/) (2022)
- [What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspective](https://mlsanity.com/paper/2206.04101/) (2022)
- [Causal Discovery for Fairness](https://mlsanity.com/paper/2206.06685/) (2022)
- [Through the Data Management Lens: Experimental Analysis and Evaluation of Fair Classification](https://mlsanity.com/paper/2101.07361/) (2021)
- [Learning Counterfactually Invariant Predictors](https://mlsanity.com/paper/2207.09768/) (2022)
- [Fair Bilevel Neural Network (FairBiNN): On Balancing fairness and accuracy via Stackelberg Equilibrium](https://mlsanity.com/paper/2410.16432/) (2024)
- [Disentangled Representation with Causal Constraints for Counterfactual Fairness](https://mlsanity.com/paper/2208.09147/) (2022)
- [Learning Fair Models without Sensitive Attributes: A Generative Approach](https://mlsanity.com/paper/2203.16413/) (2022)
- [Fair Classification via Domain Adaptation: A Dual Adversarial Learning Approach](https://mlsanity.com/paper/2206.03656/) (2022)
- [When Fairness Meets Privacy: Fair Classification with Semi-Private Sensitive Attributes](https://mlsanity.com/paper/2207.08336/) (2022)
- [Striking a Balance in Fairness for Dynamic Systems Through Reinforcement Learning](https://mlsanity.com/paper/2401.06318/) (2024)
- [Distraction is All You Need for Fairness](https://mlsanity.com/paper/2203.07593/) (2022)
- [Non-Invasive Fairness in Learning through the Lens of Data Drift](https://mlsanity.com/paper/2303.17566/) (2023)
- [A Causal Lens for Learning Long-term Fair Policies](https://mlsanity.com/paper/2506.11242/) (2025)
- [CILIATE: Towards Fairer Class-based Incremental Learning by Dataset and Training Refinement](https://mlsanity.com/paper/2304.04222/) (2023)
- [Adaptive Boosting with Fairness-aware Reweighting Technique for Fair Classification](https://mlsanity.com/paper/2401.03097/) (2024)
- [Debiasing Graph Representation Learning based on Information Bottleneck](https://mlsanity.com/paper/2409.01367/) (2024)
- [The Flawed Foundations of Fair Machine Learning](https://mlsanity.com/paper/2306.01417/) (2023)
- [FAIRLABEL: Correcting Bias in Labels](https://mlsanity.com/paper/2311.00638/) (2023)
- [Efficient DNN-Powered Software with Fair Sparse Models](https://mlsanity.com/paper/2407.02805/) (2024)
- [IFFair: Influence Function-driven Sample Reweighting for Fair Classification](https://mlsanity.com/paper/2512.07249/) (2025)
- [Fairness under Graph Uncertainty: Achieving Interventional Fairness with Partially Known Causal Graphs over Clusters of Variables](https://mlsanity.com/paper/2602.23611/) (2026)

## Abstract (arXiv)

Discrimination discovery and prevention/removal are increasingly important tasks in data mining. Discrimination discovery aims to unveil discriminatory practices on the protected attribute (e.g., gender) by analyzing the dataset of historical decision records, and discrimination prevention aims to remove discrimination by modifying the biased data before conducting predictive analysis. In this paper, we show that the key to discrimination discovery and prevention is to find the meaningful partitions that can be used to provide quantitative evidences for the judgment of discrimination. With the support of the causal graph, we present a graphical condition for identifying a meaningful partition. Based on that, we develop a simple criterion for the claim of non-discrimination, and propose discrimination removal algorithms which accurately remove discrimination while retaining good data utility. Experiments using real datasets show the effectiveness of our approaches.