Saved in:
Bibliographic Details
Main Authors: Sadiku, Shpresim, Chitranshi, Kartikeya, Kera, Hiroshi, Pokutta, Sebastian
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.16583
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909900067569664
author Sadiku, Shpresim
Chitranshi, Kartikeya
Kera, Hiroshi
Pokutta, Sebastian
author_facet Sadiku, Shpresim
Chitranshi, Kartikeya
Kera, Hiroshi
Pokutta, Sebastian
contents Plausible counterfactual explanations (p-CFEs) are perturbations that minimally modify inputs to change classifier decisions while remaining plausible under the data distribution. In this study, we demonstrate that classifiers can be trained on p-CFEs labeled with induced \emph{incorrect} target classes to classify unperturbed inputs with the original labels. While previous studies have shown that such learning is possible with adversarial perturbations, we extend this paradigm to p-CFEs. Interestingly, our experiments reveal that learning from p-CFEs is even more effective: the resulting classifiers achieve not only high in-distribution accuracy but also exhibit significantly reduced bias with respect to spurious correlations.
format Preprint
id arxiv_https___arxiv_org_abs_2505_16583
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Training on Plausible Counterfactuals Removes Spurious Correlations
Sadiku, Shpresim
Chitranshi, Kartikeya
Kera, Hiroshi
Pokutta, Sebastian
Machine Learning
Plausible counterfactual explanations (p-CFEs) are perturbations that minimally modify inputs to change classifier decisions while remaining plausible under the data distribution. In this study, we demonstrate that classifiers can be trained on p-CFEs labeled with induced \emph{incorrect} target classes to classify unperturbed inputs with the original labels. While previous studies have shown that such learning is possible with adversarial perturbations, we extend this paradigm to p-CFEs. Interestingly, our experiments reveal that learning from p-CFEs is even more effective: the resulting classifiers achieve not only high in-distribution accuracy but also exhibit significantly reduced bias with respect to spurious correlations.
title Training on Plausible Counterfactuals Removes Spurious Correlations
topic Machine Learning
url https://arxiv.org/abs/2505.16583