HyConEx: Hypernetwork classifier with counterfactual explanations

2025-03-16

AI Summary

To address the trade-off between predictive accuracy and interpretability in tabular classification, this paper proposes HyConEx—an end-to-end interpretable model. HyConEx is the first to unify a classifier and a counterfactual generator within a single deep hypernetwork architecture, enabling joint optimization and intrinsic synergy between prediction and local counterfactual explanation—thereby departing from conventional post-hoc interpretability paradigms. Leveraging gradient-guided differentiable counterfactual search, feature-constrained optimization, and perturbation modeling, HyConEx simultaneously delivers high-accuracy classifications and high-quality counterfactual instances—ensuring feasibility, sparsity, and fidelity. Empirical evaluation across multiple benchmark datasets demonstrates that HyConEx matches state-of-the-art (SOTA) models in classification performance while achieving superior counterfactual quality, as rigorously validated through counterfactual attack assessment.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Transparent, Interpretable, Explainable ML

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

In recent years, there has been a growing interest in explainable AI methods. We want not only to make accurate predictions using sophisticated neural networks but also 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 generated 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.

Problem

• Develops a deep hypernetwork classifier for tabular data.
• Provides counterfactual explanations for model decisions.
• Combines predictions and explainers in one neural network.

Innovation

• HyConEx uses deep hypernetworks for classification.
• Generates counterfactual examples for model interpretability.
• Combines predictions and explanations in one network.