Analyzing Fairness of Computer Vision and Natural Language Processing Models

TL;DR

This paper compares fairness mitigation algorithms in computer vision and NLP models using two major fairness libraries, highlighting how sequential application across different stages can enhance bias reduction without sacrificing model performance.

Contribution

It provides a comparative analysis of fairness mitigation techniques from Fairlearn and AIF360 libraries applied to unstructured datasets in CV and NLP, exploring sequential stage applications.

Findings

Sequential mitigation improves bias reduction.

Some algorithms maintain model performance.

Fairness tools are effective for real-world datasets.

Abstract

Machine learning (ML) algorithms play a critical role in decision-making across various domains, such as healthcare, finance, education, and law enforcement. However, concerns about fairness and bias in these systems have raised significant ethical and social challenges. To address these challenges, this research utilizes two prominent fairness libraries, Fairlearn by Microsoft and AIF360 by IBM. These libraries offer comprehensive frameworks for fairness analysis, providing tools to evaluate fairness metrics, visualize results, and implement bias mitigation algorithms. The study focuses on assessing and mitigating biases for unstructured datasets using Computer Vision (CV) and Natural Language Processing (NLP) models. The primary objective is to present a comparative analysis of the performance of mitigation algorithms from the two fairness libraries. This analysis involves applying the algorithms individually, one at a time, in one of the stages of the ML lifecycle, pre-processing, in-processing, or post-processing, as well as sequentially across more than one stage. The results reveal that some sequential applications improve the performance of mitigation algorithms by effectively reducing bias while maintaining the model's performance. Publicly available datasets from Kaggle were chosen for this research, providing a practical context for evaluating fairness in real-world machine learning workflows.