Fair-Net: A Network Architecture for Reducing Performance Disparity between Identifiable Sub-populations

Arghya Datta, S. Swamidass

2022

Abstract

In real world datasets, particular groups are under-represented, much rarer than others, and machine learning classifiers will often preform worse on under-represented populations. This problem is aggravated across many domains where datasets are class imbalanced, with a minority class far rarer than the majority class. Naive approaches to handle under-representation and class imbalance include training sub-population specific classifiers that handle class imbalance or training a global classifier that overlooks sub-population disparities and aims to achieve high overall accuracy by handling class imbalance. In this study, we find that these approaches are vulnerable in class imbalanced datasets with minority sub-populations. We introduced Fair-Net, a branched multitask neural network architecture that improves both classification accuracy and probability calibration across identifiable sub-populations in class imbalanced datasets. Fair-Nets is a straightforward extension to the output layer and error function of a network, so can be incorporated in far more complex architectures. Empirical studies with three real world benchmark datasets demonstrate that Fair-Net improves classification and calibration performance, substantially reducing performance disparity between gender and racial sub-populations.

Paper Citation

in Harvard Style

Datta A. and Swamidass S. (2022). Fair-Net: A Network Architecture for Reducing Performance Disparity between Identifiable Sub-populations. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART, ISBN 978-989-758-547-0, pages 645-654. DOI: 10.5220/0010877400003116

in Bibtex Style

@conference{icaart22,
author={Arghya Datta and S. Swamidass},
title={Fair-Net: A Network Architecture for Reducing Performance Disparity between Identifiable Sub-populations},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,},
year={2022},
pages={645-654},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010877400003116},
isbn={978-989-758-547-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,
TI - Fair-Net: A Network Architecture for Reducing Performance Disparity between Identifiable Sub-populations
SN - 978-989-758-547-0
AU - Datta A.
AU - Swamidass S.
PY - 2022
SP - 645
EP - 654
DO - 10.5220/0010877400003116