Imbalanced Classification through the Lens of Spurious Correlations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hackstein, Jakob, Bender, Sidney
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914127122792448
author Hackstein, Jakob
Bender, Sidney
author_facet Hackstein, Jakob
Bender, Sidney
contents Class imbalance poses a fundamental challenge in machine learning, frequently leading to unreliable classification performance. While prior methods focus on data- or loss-reweighting schemes, we view imbalance as a data condition that amplifies Clever Hans (CH) effects by underspecification of minority classes. In a counterfactual explanations-based approach, we propose to leverage Explainable AI to jointly identify and eliminate CH effects emerging under imbalance. Our method achieves competitive classification performance on three datasets and demonstrates how CH effects emerge under imbalance, a perspective largely overlooked by existing approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2510_27650
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Imbalanced Classification through the Lens of Spurious Correlations
Hackstein, Jakob
Bender, Sidney
Machine Learning
Computer Vision and Pattern Recognition
Class imbalance poses a fundamental challenge in machine learning, frequently leading to unreliable classification performance. While prior methods focus on data- or loss-reweighting schemes, we view imbalance as a data condition that amplifies Clever Hans (CH) effects by underspecification of minority classes. In a counterfactual explanations-based approach, we propose to leverage Explainable AI to jointly identify and eliminate CH effects emerging under imbalance. Our method achieves competitive classification performance on three datasets and demonstrates how CH effects emerge under imbalance, a perspective largely overlooked by existing approaches.
title Imbalanced Classification through the Lens of Spurious Correlations
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.27650