Realistic Counterfactual Explanations with Learned Relations
Many existing methods of counterfactual explanations ignore the intrinsic relationships between data attributes and thus fail to generate realistic counterfactuals. Moreover, the existing models that account for relationships require domain knowledge, which limits their applicability in complex real-world applications. In this paper, we propose a novel approach to realistic counterfactual explanations that preserve the relationships and minimise experts' interventions. The model directly learns the relationships by a variational auto-encoder with minimal domain knowledge and then learns to perturb the latent space accordingly. We conduct extensive experiments on both synthetic and real-world datasets. The experimental results demonstrate that the proposed model learns relationships from the data and preserves these relationships in generated counterfactuals. In particular, it outperforms other methods in terms of Mahalanobis distance, and the constraint feasibility score.
Code (0)
등록된 구현이 없습니다.
Tasks
counterfactualSimilar Papers 제목 키워드 기반
Actionable and diverse counterfactual explanations incorporating domain knowledge and plausibility constraints
Counterfactual explanations improve the actionable interpretability of machine learning models by identifying minimal changes required to achieve a desired outcome. However, existing methods often neglect dependencies am…
A New Approach to Backtracking Counterfactual Explanations: A Causal Framework for Efficient Model Interpretability
Counterfactual explanations enhance interpretability by identifying alternative inputs that produce different outputs, offering localized insights into model decisions. However, traditional methods often neglect causal r…
counterfactualRealAC: A Domain-Agnostic Framework for Realistic and Actionable Counterfactual Explanations
Counterfactual explanations provide human-understandable reasoning for AI-made decisions by describing minimal changes to input features that would alter a model's prediction. To be truly useful in practice, such explana…
Diffusion Counterfactuals for Image Regressors
Counterfactual explanations have been successfully applied to create human interpretable explanations for various black-box models. They are handy for tasks in the image domain, where the quality of the explanations bene…
counterfactualDenoisingregressionCounterfactual Explanations for Predictive Business Process Monitoring
Predictive business process monitoring increasingly leverages sophisticated prediction models. Although sophisticated models achieve consistently higher prediction accuracy than simple models, one major drawback is their…
counterfactualCounterfactual ExplanationExplanation GenerationMulti-class Classification+2