FairGrad: Fairness Aware Gradient Descent

Gaurav Maheshwari, Michaël Perrot

Abstract:

We address the problem of group fairness in classification, where the objective is to learn models that do not unjustly discriminate against subgroups of the population. Most existing approaches are limited to simple binary tasks or involve difficult to implement training mechanisms which reduces their practical applicability. In this paper, we propose FairGrad, a method to enforce fairness based on a re-weighting scheme that iteratively learns group specific weights based on whether they are advantaged or not. FairGrad is easy to implement, accommodates various standard fairness definitions, and comes with minimal overhead. Furthermore, we show that it is competitive with standard baselines over various datasets including ones used in natural language processing and computer vision.

FairGrad is available as a PyPI package at - https://pypi.org/project/fairgrad

Submission Length: Long submission (more than 12 pages of main content)

Changes Since Last Submission:

Changes from the version after the first set of reviews:
- Deanonymized the paper and formatted it as per the guidelines of TMLR.
- Abstract - Added PyPI URL of the Python package corresponding to FairGrad.
- Figure 1- Updated Figure 1 with the link to the package.
- Section 5 - Added acknowledgment at the end of the paper.

Code: https://pypi.org/project/fairgrad

Assigned Action Editor: ~Novi_Quadrianto1

License: Creative Commons Attribution 4.0 International (CC BY 4.0)

Submission Number: 1154