# Enhanced Fairness Testing via Generating Effective Initial Individual Discriminatory Instances

arXiv: https://arxiv.org/abs/2209.08321 · HTML: https://mlsanity.com/paper/2209.08321/

## Key facts

- Cited by 2 papers in the map (data through 7 Oct 2026).
- Builds on 22 of its 55 references that are in the map.
- First posted on arXiv 17 Sep 2022.

## Builds on (most cited first, 22 of 22)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Fairness in Machine Learning: A Survey](https://mlsanity.com/paper/2010.04053/) (2020)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias](https://mlsanity.com/paper/1810.01943/) (2018)
- [Machine Learning Testing: Survey, Landscapes and Horizons](https://mlsanity.com/paper/1906.10742/) (2019)
- [A Convex Framework for Fair Regression](https://mlsanity.com/paper/1706.02409/) (2017)
- [Identifying and Correcting Label Bias in Machine Learning](https://mlsanity.com/paper/1901.04966/) (2019)
- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [Fairness Testing: Testing Software for Discrimination](https://mlsanity.com/paper/1709.03221/) (2017)
- [A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual & Group Unfairness via Inequality Indices](https://mlsanity.com/paper/1807.00787/) (2018)
- [Bias in Machine Learning Software: Why? How? What to do?](https://mlsanity.com/paper/2105.12195/) (2021)
- [Automated Directed Fairness Testing](https://mlsanity.com/paper/1807.00468/) (2018)
- [Fairness Testing: A Comprehensive Survey and Analysis of Trends](https://mlsanity.com/paper/2207.10223/) (2022)
- [Do the Machine Learning Models on a Crowd Sourced Platform Exhibit Bias? An Empirical Study on Model Fairness](https://mlsanity.com/paper/2005.12379/) (2020)
- [Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipeline](https://mlsanity.com/paper/2106.06054/) (2021)
- [NeuronFair: Interpretable White-Box Fairness Testing through Biased Neuron Identification](https://mlsanity.com/paper/2112.13214/) (2021)
- [Automated Test Generation to Detect Individual Discrimination in AI Models](https://mlsanity.com/paper/1809.03260/) (2018)
- [VerifyMed -- A blockchain platform for transparent trust in virtualized healthcare: Proof-of-concept](https://mlsanity.com/paper/2005.08804/) (2020)
- [Fairkit, Fairkit, on the Wall, Who's the Fairest of Them All? Supporting Data Scientists in Training Fair Models](https://mlsanity.com/paper/2012.09951/) (2020)
- [Software Fairness: An Analysis and Survey](https://mlsanity.com/paper/2205.08809/) (2022)

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

- [MAFT: Efficient Model-Agnostic Fairness Testing for Deep Neural Networks via Zero-Order Gradient Search](https://mlsanity.com/paper/2412.20086/) (2024)
- [Search-Based Fairness Testing: An Overview](https://mlsanity.com/paper/2311.06175/) (2023)

## Abstract (arXiv)

Fairness testing aims at mitigating unintended discrimination in the decision-making process of data-driven AI systems. Individual discrimination may occur when an AI model makes different decisions for two distinct individuals who are distinguishable solely according to protected attributes, such as age and race. Such instances reveal biased AI behaviour, and are called Individual Discriminatory Instances (IDIs). In this paper, we propose an approach for the selection of the initial seeds to generate IDIs for fairness testing. Previous studies mainly used random initial seeds to this end. However this phase is crucial, as these seeds are the basis of the follow-up IDIs generation. We dubbed our proposed seed selection approach I&D. It generates a large number of initial IDIs exhibiting a great diversity, aiming at improving the overall performance of fairness testing. Our empirical study reveal that I&D is able to produce a larger number of IDIs with respect to four state-of-the-art seed generation approaches, generating 1.68X more IDIs on average. Moreover, we compare the use of I&D to train machine learning models and find that using I&D reduces the number of remaining IDIs by 29% when compared to the state-of-the-art, thus indicating that I&D is effective for improving model fairness