paper-with-me

홈 › Papers

Generalizability vs. Counterfactual Explainability Trade-Off

2025-05-29 · Fabiano Veglianti, Flavio Giorgi, Fabrizio Silvestri, Gabriele Tolomei

In this work, we investigate the relationship between model generalization and counterfactual explainability in supervised learning. We introduce the notion of $\varepsilon$-valid counterfactual probability ($\varepsilon$-VCP) -- the probability of finding perturbations of a data point within its $\varepsilon$-neighborhood that result in a label change. We provide a theoretical analysis of $\varepsilon$-VCP in relation to the geometry of the model's decision boundary, showing that $\varepsilon$-VCP tends to increase with model overfitting. Our findings establish a rigorous connection between poor generalization and the ease of counterfactual generation, revealing an inherent trade-off between generalization and counterfactual explainability. Empirical results validate our theory, suggesting $\varepsilon$-VCP as a practical proxy for quantitatively characterizing overfitting.

📄 PDF Abstract BibTeX arXiv:2505.23225

Code (0)

등록된 구현이 없습니다.

Tasks

counterfactualvalid

Similar Papers 제목 키워드 기반

Generalizability through Explainability: Countering Overfitting with Counterfactual Examples

2025-02-13 · Flavio Giorgi, Fabiano Veglianti, Fabrizio Silvestri, Gabriele Tolomei

Overfitting is a well-known issue in machine learning that occurs when a model struggles to generalize its predictions to new, unseen data beyond the scope of its training set. Traditional techniques to mitigate overfitt…

counterfactualData Augmentationvalid

GLANCE: Global Actions in a Nutshell for Counterfactual Explainability

2024-05-29 · Loukas Kavouras, Eleni Psaroudaki, Konstantinos Tsopelas, Dimitrios Rontogiannis 외

The widespread deployment of machine learning systems in critical real-world decision-making applications has highlighted the urgent need for counterfactual explainability methods that operate effectively. Global counter…

counterfactual

U-CECE: A Universal Multi-Resolution Framework for Conceptual Counterfactual Explanations

2026-04-09 · Angeliki Dimitriou, Nikolaos Chaidos, Maria Lymperaiou, Giorgos Filandrianos 외 arxiv

As AI models grow more complex, explainability is essential for building trust, yet concept-based counterfactual methods still face a trade-off between expressivity and efficiency. Representing underlying concepts as ato…

From Counterfactuals to Trees: Competitive Analysis of Model Extraction Attacks

2025-02-07 · Awa Khouna, Julien Ferry, Thibaut Vidal

The advent of Machine Learning as a Service (MLaaS) has heightened the trade-off between model explainability and security. In particular, explainability techniques, such as counterfactual explanations, inadvertently inc…

counterfactualModel extraction

Counterfactual Graph Augmentation for Consumer Unfairness Mitigation in Recommender Systems

2023-08-23 · Ludovico Boratto, Francesco Fabbri, Gianni Fenu, Mirko Marras 외

In recommendation literature, explainability and fairness are becoming two prominent perspectives to consider. However, prior works have mostly addressed them separately, for instance by explaining to consumers why a cer…

counterfactualFairnessRecommendation Systems