Guardado en:
Detalles Bibliográficos
Autores principales: Vadlamani, Aditya T., Srinivasan, Anutam, Maneriker, Pranav, Payani, Ali, Parthasarathy, Srinivasan
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2505.16115
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909858191638528
author Vadlamani, Aditya T.
Srinivasan, Anutam
Maneriker, Pranav
Payani, Ali
Parthasarathy, Srinivasan
author_facet Vadlamani, Aditya T.
Srinivasan, Anutam
Maneriker, Pranav
Payani, Ali
Parthasarathy, Srinivasan
contents Conformal Prediction (CP) is a popular method for uncertainty quantification with machine learning models. While conformal prediction provides probabilistic guarantees regarding the coverage of the true label, these guarantees are agnostic to the presence of sensitive attributes within the dataset. In this work, we formalize \textit{Conformal Fairness}, a notion of fairness using conformal predictors, and provide a theoretically well-founded algorithm and associated framework to control for the gaps in coverage between different sensitive groups. Our framework leverages the exchangeability assumption (implicit to CP) rather than the typical IID assumption, allowing us to apply the notion of Conformal Fairness to data types and tasks that are not IID, such as graph data. Experiments were conducted on graph and tabular datasets to demonstrate that the algorithm can control fairness-related gaps in addition to coverage aligned with theoretical expectations.
format Preprint
id arxiv_https___arxiv_org_abs_2505_16115
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Generic Framework for Conformal Fairness
Vadlamani, Aditya T.
Srinivasan, Anutam
Maneriker, Pranav
Payani, Ali
Parthasarathy, Srinivasan
Machine Learning
Conformal Prediction (CP) is a popular method for uncertainty quantification with machine learning models. While conformal prediction provides probabilistic guarantees regarding the coverage of the true label, these guarantees are agnostic to the presence of sensitive attributes within the dataset. In this work, we formalize \textit{Conformal Fairness}, a notion of fairness using conformal predictors, and provide a theoretically well-founded algorithm and associated framework to control for the gaps in coverage between different sensitive groups. Our framework leverages the exchangeability assumption (implicit to CP) rather than the typical IID assumption, allowing us to apply the notion of Conformal Fairness to data types and tasks that are not IID, such as graph data. Experiments were conducted on graph and tabular datasets to demonstrate that the algorithm can control fairness-related gaps in addition to coverage aligned with theoretical expectations.
title A Generic Framework for Conformal Fairness
topic Machine Learning
url https://arxiv.org/abs/2505.16115