FairGrad: Fairness Aware Gradient Descent

06/22/2022
by   Gaurav Maheshwari, et al.
0

We tackle 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. This reduces their practical applicability. In this paper, we propose FairGrad, a method to enforce fairness based on a reweighting scheme that iteratively learns group specific weights based on whether they are advantaged or not. FairGrad is easy to implement and can accommodate various standard fairness definitions. Furthermore, we show that it is comparable to standard baselines over various datasets including ones used in natural language processing and computer vision.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/21/2023

How to Capture Intersectional Fairness

In this work, we tackle the problem of intersectional group fairness in ...
research
03/01/2023

Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization

Many existing group fairness-aware training methods aim to achieve the g...
research
09/20/2022

Towards Auditing Unsupervised Learning Algorithms and Human Processes For Fairness

Existing work on fairness typically focuses on making known machine lear...
research
05/04/2022

fairlib: A Unified Framework for Assessing and Improving Classification Fairness

This paper presents fairlib, an open-source framework for assessing and ...
research
04/27/2023

Fairness Uncertainty Quantification: How certain are you that the model is fair?

Fairness-aware machine learning has garnered significant attention in re...
research
04/03/2020

FairALM: Augmented Lagrangian Method for Training Fair Models with Little Regret

Algorithmic decision making based on computer vision and machine learnin...
research
05/08/2023

Distribution-aware Fairness Test Generation

This work addresses how to validate group fairness in image recognition ...

Please sign up or login with your details

Forgot password? Click here to reset