fairlib: A Unified Framework for Assessing and Improving Classification Fairness

Authors

Xudong Han, The University of Melbourne, Australia
Aili Shen, The University of Melbourne, Australia
Yitong Li, Huawei Technologies Co., Ltd., China
Lea Frermann, The University of Melbourne, Australia
Timothy Baldwin, The University of Melbourne, Australia & Mohamed bin Zayed University of Artificial IntelligenceFollow
Trevor Cohn, The University of Melbourne, Australia

Document Type

Article

Publication Title

arXiv

Abstract

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. Copyright © 2022, The Authors. All rights reserved.

DOI

10.48550/arXiv.2205.01876

Publication Date

4-3-2022

Keywords

Baseline models; De-biasing; Evaluating models; Natural languages; Open source frameworks; Pre-processing; Systematic framework; Time processing; Training time; Unified framework; Machine learning; Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Machine Learning (cs.LG)

Comments

IR Deposit conditions: non-described

Preprint available on arXiv

Recommended Citation

X. Han, A. Shen, Y. Li, L. Frermann, and T. Baldwin, "fairlib: A Unified Framework for Assessing and Improving Classification Fairness", 2022, arXiv.2205.01876