Guardado en:
Detalles Bibliográficos
Autores principales: Williams, Joshua Nathaniel, Katakkar, Anurag, Heidari, Hoda, Kolter, J. Zico
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2410.14522
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912076221382656
author Williams, Joshua Nathaniel
Katakkar, Anurag
Heidari, Hoda
Kolter, J. Zico
author_facet Williams, Joshua Nathaniel
Katakkar, Anurag
Heidari, Hoda
Kolter, J. Zico
contents Counterfactual explanations have been a popular method of post-hoc explainability for a variety of settings in Machine Learning. Such methods focus on explaining classifiers by generating new data points that are similar to a given reference, while receiving a more desirable prediction. In this work, we investigate a framing for counterfactual generation methods that considers counterfactuals not as independent draws from a region around the reference, but as jointly sampled with the reference from the underlying data distribution. Through this framing, we derive a distance metric, tailored for counterfactual similarity that can be applied to a broad range of settings. Through both quantitative and qualitative analyses of counterfactual generation methods, we show that this framing allows us to express more nuanced dependencies among the covariates.
format Preprint
id arxiv_https___arxiv_org_abs_2410_14522
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Rethinking Distance Metrics for Counterfactual Explainability
Williams, Joshua Nathaniel
Katakkar, Anurag
Heidari, Hoda
Kolter, J. Zico
Machine Learning
Counterfactual explanations have been a popular method of post-hoc explainability for a variety of settings in Machine Learning. Such methods focus on explaining classifiers by generating new data points that are similar to a given reference, while receiving a more desirable prediction. In this work, we investigate a framing for counterfactual generation methods that considers counterfactuals not as independent draws from a region around the reference, but as jointly sampled with the reference from the underlying data distribution. Through this framing, we derive a distance metric, tailored for counterfactual similarity that can be applied to a broad range of settings. Through both quantitative and qualitative analyses of counterfactual generation methods, we show that this framing allows us to express more nuanced dependencies among the covariates.
title Rethinking Distance Metrics for Counterfactual Explainability
topic Machine Learning
url https://arxiv.org/abs/2410.14522