Unveil Sources of Uncertainty: Feature Contribution to Conformal Prediction Intervals

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Idrissi, Marouane Il, Machado, Agathe Fernandes, Gallic, Ewen, Charpentier, Arthur
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909615815393280
author Idrissi, Marouane Il
Machado, Agathe Fernandes
Gallic, Ewen
Charpentier, Arthur
author_facet Idrissi, Marouane Il
Machado, Agathe Fernandes
Gallic, Ewen
Charpentier, Arthur
contents Cooperative game theory methods, notably Shapley values, have significantly enhanced machine learning (ML) interpretability. However, existing explainable AI (XAI) frameworks mainly attribute average model predictions, overlooking predictive uncertainty. This work addresses that gap by proposing a novel, model-agnostic uncertainty attribution (UA) method grounded in conformal prediction (CP). By defining cooperative games where CP interval properties-such as width and bounds-serve as value functions, we systematically attribute predictive uncertainty to input features. Extending beyond the traditional Shapley values, we use the richer class of Harsanyi allocations, and in particular the proportional Shapley values, which distribute attribution proportionally to feature importance. We propose a Monte Carlo approximation method with robust statistical guarantees to address computational feasibility, significantly improving runtime efficiency. Our comprehensive experiments on synthetic benchmarks and real-world datasets demonstrate the practical utility and interpretative depth of our approach. By combining cooperative game theory and conformal prediction, we offer a rigorous, flexible toolkit for understanding and communicating predictive uncertainty in high-stakes ML applications.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13118
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unveil Sources of Uncertainty: Feature Contribution to Conformal Prediction Intervals
Idrissi, Marouane Il
Machado, Agathe Fernandes
Gallic, Ewen
Charpentier, Arthur
Artificial Intelligence
Machine Learning
Cooperative game theory methods, notably Shapley values, have significantly enhanced machine learning (ML) interpretability. However, existing explainable AI (XAI) frameworks mainly attribute average model predictions, overlooking predictive uncertainty. This work addresses that gap by proposing a novel, model-agnostic uncertainty attribution (UA) method grounded in conformal prediction (CP). By defining cooperative games where CP interval properties-such as width and bounds-serve as value functions, we systematically attribute predictive uncertainty to input features. Extending beyond the traditional Shapley values, we use the richer class of Harsanyi allocations, and in particular the proportional Shapley values, which distribute attribution proportionally to feature importance. We propose a Monte Carlo approximation method with robust statistical guarantees to address computational feasibility, significantly improving runtime efficiency. Our comprehensive experiments on synthetic benchmarks and real-world datasets demonstrate the practical utility and interpretative depth of our approach. By combining cooperative game theory and conformal prediction, we offer a rigorous, flexible toolkit for understanding and communicating predictive uncertainty in high-stakes ML applications.
title Unveil Sources of Uncertainty: Feature Contribution to Conformal Prediction Intervals
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2505.13118