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

Arghya Datta, S. Joshua Swamidass

Research output: Contribution to journalConference articlepeer-review

2 Scopus citations

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.

Original languageEnglish
Pages (from-to)645-654
Number of pages10
JournalInternational Conference on Agents and Artificial Intelligence
Volume3
DOIs
StatePublished - 2022
Event14th International Conference on Agents and Artificial Intelligence , ICAART 2022 - Virtual, Online
Duration: Feb 3 2022Feb 5 2022

Keywords

  • Classification
  • Deep Learning
  • Fairness
  • Neural Networks

Fingerprint

Dive into the research topics of 'Fair-Net: A Network Architecture for Reducing Performance Disparity between Identifiable Sub-populations'. Together they form a unique fingerprint.

Cite this