Rethinking Cost-Sensitive Classification in Deep Learning via Adversarial Data Augmentation

Qiyuan Chen (), Raed Al Kontar (), Maher Nouiehed (), X. Jessie Yang () and Corey Lester ()
Additional contact information
Qiyuan Chen: Industrial & Operation Engineering, University of Michigan, Ann Arbor, Michigan 48109
Raed Al Kontar: Industrial & Operation Engineering, University of Michigan, Ann Arbor, Michigan 48109
Maher Nouiehed: Industrial Engineering, American University of Beirut, Beirut 1107 2020, Lebanon
X. Jessie Yang: Industrial & Operation Engineering, University of Michigan, Ann Arbor, Michigan 48109
Corey Lester: College of Pharmacy, University of Michigan, Ann Arbor, Michigan 48109

INFORMS Joural on Data Science, 2025, vol. 4, issue 1, 1-19

Abstract: Cost-sensitive classification is critical in applications where misclassification errors widely vary in cost. However, overparameterization poses fundamental challenges to the cost-sensitive modeling of deep neural networks (DNNs). The ability of a DNN to fully interpolate a training data set can render a DNN, evaluated purely on the training set, ineffective in distinguishing a cost-sensitive solution from its overall accuracy maximization counterpart. This necessitates rethinking cost-sensitive classification in DNNs. To address this challenge, this paper proposes a cost-sensitive adversarial data augmentation (CSADA) framework to make overparameterized models cost sensitive. The overarching idea is to generate targeted adversarial examples that push the decision boundary in cost-aware directions. These targeted adversarial samples are generated by maximizing the probability of critical misclassifications and used to train a model with more conservative decisions on costly pairs. Experiments on well-known data sets and a pharmacy medication image (PMI) data set, made publicly available, show that our method can effectively minimize the overall cost and reduce critical errors while achieving comparable overall accuracy.

Keywords: cost-sensitive learning; adversarial data augmentation; deep neural networks; multiclass classification; overparametrization (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://dx.doi.org/10.1287/ijds.2022.0033 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:inm:orijds:v:4:y:2025:i:1:p:1-19

Access Statistics for this article

More articles in INFORMS Joural on Data Science from INFORMS Contact information at EDIRC.
Bibliographic data for series maintained by Chris Asher ().