Metric-DST: Mitigating Selection Bias Through Diversity-Guided Semi-Supervised Metric Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tepeli, Yasin I., de Wolf, Mathijs, Gonçalves, Joana P.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929608268447744
author Tepeli, Yasin I.
de Wolf, Mathijs
Gonçalves, Joana P.
author_facet Tepeli, Yasin I.
de Wolf, Mathijs
Gonçalves, Joana P.
contents Selection bias poses a critical challenge for fairness in machine learning, as models trained on data that is less representative of the population might exhibit undesirable behavior for underrepresented profiles. Semi-supervised learning strategies like self-training can mitigate selection bias by incorporating unlabeled data into model training to gain further insight into the distribution of the population. However, conventional self-training seeks to include high-confidence data samples, which may reinforce existing model bias and compromise effectiveness. We propose Metric-DST, a diversity-guided self-training strategy that leverages metric learning and its implicit embedding space to counter confidence-based bias through the inclusion of more diverse samples. Metric-DST learned more robust models in the presence of selection bias for generated and real-world datasets with induced bias, as well as a molecular biology prediction task with intrinsic bias. The Metric-DST learning strategy offers a flexible and widely applicable solution to mitigate selection bias and enhance fairness of machine learning models.
format Preprint
id arxiv_https___arxiv_org_abs_2411_18442
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Metric-DST: Mitigating Selection Bias Through Diversity-Guided Semi-Supervised Metric Learning
Tepeli, Yasin I.
de Wolf, Mathijs
Gonçalves, Joana P.
Machine Learning
Artificial Intelligence
Selection bias poses a critical challenge for fairness in machine learning, as models trained on data that is less representative of the population might exhibit undesirable behavior for underrepresented profiles. Semi-supervised learning strategies like self-training can mitigate selection bias by incorporating unlabeled data into model training to gain further insight into the distribution of the population. However, conventional self-training seeks to include high-confidence data samples, which may reinforce existing model bias and compromise effectiveness. We propose Metric-DST, a diversity-guided self-training strategy that leverages metric learning and its implicit embedding space to counter confidence-based bias through the inclusion of more diverse samples. Metric-DST learned more robust models in the presence of selection bias for generated and real-world datasets with induced bias, as well as a molecular biology prediction task with intrinsic bias. The Metric-DST learning strategy offers a flexible and widely applicable solution to mitigate selection bias and enhance fairness of machine learning models.
title Metric-DST: Mitigating Selection Bias Through Diversity-Guided Semi-Supervised Metric Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2411.18442