Generalizability vs. Counterfactual Explainability Trade-Off
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.
Code (0)
등록된 구현이 없습니다.
Tasks
counterfactualvalidSimilar Papers 제목 키워드 기반
Generalizability through Explainability: Countering Overfitting with Counterfactual Examples
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 AugmentationvalidGLANCE: Global Actions in a Nutshell for Counterfactual Explainability
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…
counterfactualU-CECE: A Universal Multi-Resolution Framework for Conceptual Counterfactual Explanations
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
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 extractionCounterfactual Graph Augmentation for Consumer Unfairness Mitigation in Recommender Systems
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