HyConEx: Hypernetwork classifier with counterfactual explanations for tabular data

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Marszałek, Patryk, Książek, Kamil, Furman, Oleksii, Movsum-zada, Ulvi, Spurek, Przemysław, Śmieja, Marek
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910047675613184
author Marszałek, Patryk
Książek, Kamil
Furman, Oleksii
Movsum-zada, Ulvi
Spurek, Przemysław
Śmieja, Marek
author_facet Marszałek, Patryk
Książek, Kamil
Furman, Oleksii
Movsum-zada, Ulvi
Spurek, Przemysław
Śmieja, Marek
contents In recent years, there has been a growing interest in explainable AI methods. In addition to making accurate predictions, we also want to understand what the model's decision is based on. One of the fundamental levels of interpretability is to provide counterfactual examples explaining the rationale behind the decision and identifying which features, and to what extent, must be modified to alter the model's outcome. To address these requirements, we introduce HyConEx, a classification model based on deep hypernetworks specifically designed for tabular data. Owing to its unique architecture, HyConEx not only provides class predictions but also delivers local interpretations for individual data samples in the form of counterfactual examples that steer a given sample toward an alternative class. While many explainable methods generate counterfactuals for external models, there have been no interpretable classifiers simultaneously producing counterfactual samples so far. HyConEx achieves competitive performance on several metrics assessing classification accuracy and fulfilling the criteria of a proper counterfactual attack. This makes HyConEx a distinctive deep learning model, which combines predictions and explainers as an all-in-one neural network. The code is available at https://github.com/gmum/HyConEx.
format Preprint
id arxiv_https___arxiv_org_abs_2503_12525
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HyConEx: Hypernetwork classifier with counterfactual explanations for tabular data
Marszałek, Patryk
Książek, Kamil
Furman, Oleksii
Movsum-zada, Ulvi
Spurek, Przemysław
Śmieja, Marek
Machine Learning
Artificial Intelligence
In recent years, there has been a growing interest in explainable AI methods. In addition to making accurate predictions, we also want to understand what the model's decision is based on. One of the fundamental levels of interpretability is to provide counterfactual examples explaining the rationale behind the decision and identifying which features, and to what extent, must be modified to alter the model's outcome. To address these requirements, we introduce HyConEx, a classification model based on deep hypernetworks specifically designed for tabular data. Owing to its unique architecture, HyConEx not only provides class predictions but also delivers local interpretations for individual data samples in the form of counterfactual examples that steer a given sample toward an alternative class. While many explainable methods generate counterfactuals for external models, there have been no interpretable classifiers simultaneously producing counterfactual samples so far. HyConEx achieves competitive performance on several metrics assessing classification accuracy and fulfilling the criteria of a proper counterfactual attack. This makes HyConEx a distinctive deep learning model, which combines predictions and explainers as an all-in-one neural network. The code is available at https://github.com/gmum/HyConEx.
title HyConEx: Hypernetwork classifier with counterfactual explanations for tabular data
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2503.12525