Conformal Prediction of Classifiers with Many Classes based on Noisy Labels

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Penso, Coby, Goldberger, Jacob, Fetaya, Ethan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908487917764608
author Penso, Coby
Goldberger, Jacob
Fetaya, Ethan
author_facet Penso, Coby
Goldberger, Jacob
Fetaya, Ethan
contents Conformal Prediction (CP) controls the prediction uncertainty of classification systems by producing a small prediction set, ensuring a predetermined probability that the true class lies within this set. This is commonly done by defining a score, based on the model predictions, and setting a threshold on this score using a validation set. In this study, we address the problem of CP calibration when we only have access to a calibration set with noisy labels. We show how we can estimate the noise-free conformal threshold based on the noisy labeled data. We derive a finite sample coverage guarantee for uniform noise that remains effective even in tasks with a large number of classes. We dub our approach Noise-Aware Conformal Prediction (NACP). We illustrate the performance of the proposed results on several standard image classification datasets with a large number of classes.
format Preprint
id arxiv_https___arxiv_org_abs_2501_12749
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Conformal Prediction of Classifiers with Many Classes based on Noisy Labels
Penso, Coby
Goldberger, Jacob
Fetaya, Ethan
Machine Learning
Artificial Intelligence
Conformal Prediction (CP) controls the prediction uncertainty of classification systems by producing a small prediction set, ensuring a predetermined probability that the true class lies within this set. This is commonly done by defining a score, based on the model predictions, and setting a threshold on this score using a validation set. In this study, we address the problem of CP calibration when we only have access to a calibration set with noisy labels. We show how we can estimate the noise-free conformal threshold based on the noisy labeled data. We derive a finite sample coverage guarantee for uniform noise that remains effective even in tasks with a large number of classes. We dub our approach Noise-Aware Conformal Prediction (NACP). We illustrate the performance of the proposed results on several standard image classification datasets with a large number of classes.
title Conformal Prediction of Classifiers with Many Classes based on Noisy Labels
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2501.12749