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 language | English |
---|---|
Pages (from-to) | 645-654 |
Number of pages | 10 |
Journal | International Conference on Agents and Artificial Intelligence |
Volume | 3 |
DOIs | |
State | Published - 2022 |
Event | 14th International Conference on Agents and Artificial Intelligence , ICAART 2022 - Virtual, Online Duration: Feb 3 2022 → Feb 5 2022 |
Keywords
- Classification
- Deep Learning
- Fairness
- Neural Networks