fairlib: A Unified Framework for Assessing and Improving Classification Fairness
This provides a unified tool for researchers and practitioners working on fairness in machine learning, but it is incremental as it consolidates existing methods into a framework.
The authors tackled the problem of assessing and improving classification fairness by developing fairlib, an open-source framework that implements 14 debiasing methods and supports diverse input types, resulting in a modular tool for reproducibility and evaluation.
This paper presents fairlib, an open-source framework for assessing and improving classification fairness. It provides a systematic framework for quickly reproducing existing baseline models, developing new methods, evaluating models with different metrics, and visualizing their results. Its modularity and extensibility enable the framework to be used for diverse types of inputs, including natural language, images, and audio. In detail, we implement 14 debiasing methods, including pre-processing, at-training-time, and post-processing approaches. The built-in metrics cover the most commonly used fairness criterion and can be further generalized and customized for fairness evaluation.