Guided Uncertainty Learning Using a Post-Hoc Evidential Meta-Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Barker, Charmaine, Bethell, Daniel, Gerasimou, Simos
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915521544323072
author Barker, Charmaine
Bethell, Daniel
Gerasimou, Simos
author_facet Barker, Charmaine
Bethell, Daniel
Gerasimou, Simos
contents Reliable uncertainty quantification remains a major obstacle to the deployment of deep learning models under distributional shift. Existing post-hoc approaches that retrofit pretrained models either inherit misplaced confidence or merely reshape predictions, without teaching the model when to be uncertain. We introduce GUIDE, a lightweight evidential learning meta-model approach that attaches to a frozen deep learning model and explicitly learns how and when to be uncertain. GUIDE identifies salient internal features via a calibration stage, and then employs these features to construct a noise-driven curriculum that teaches the model how and when to express uncertainty. GUIDE requires no retraining, no architectural modifications, and no manual intermediate-layer selection to the base deep learning model, thus ensuring broad applicability and minimal user intervention. The resulting model avoids distilling overconfidence from the base model, improves out-of-distribution detection by ~77% and adversarial attack detection by ~80%, while preserving in-distribution performance. Across diverse benchmarks, GUIDE consistently outperforms state-of-the-art approaches, evidencing the need for actively guiding uncertainty to close the gap between predictive confidence and reliability.
format Preprint
id arxiv_https___arxiv_org_abs_2509_24492
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Guided Uncertainty Learning Using a Post-Hoc Evidential Meta-Model
Barker, Charmaine
Bethell, Daniel
Gerasimou, Simos
Machine Learning
Reliable uncertainty quantification remains a major obstacle to the deployment of deep learning models under distributional shift. Existing post-hoc approaches that retrofit pretrained models either inherit misplaced confidence or merely reshape predictions, without teaching the model when to be uncertain. We introduce GUIDE, a lightweight evidential learning meta-model approach that attaches to a frozen deep learning model and explicitly learns how and when to be uncertain. GUIDE identifies salient internal features via a calibration stage, and then employs these features to construct a noise-driven curriculum that teaches the model how and when to express uncertainty. GUIDE requires no retraining, no architectural modifications, and no manual intermediate-layer selection to the base deep learning model, thus ensuring broad applicability and minimal user intervention. The resulting model avoids distilling overconfidence from the base model, improves out-of-distribution detection by ~77% and adversarial attack detection by ~80%, while preserving in-distribution performance. Across diverse benchmarks, GUIDE consistently outperforms state-of-the-art approaches, evidencing the need for actively guiding uncertainty to close the gap between predictive confidence and reliability.
title Guided Uncertainty Learning Using a Post-Hoc Evidential Meta-Model
topic Machine Learning
url https://arxiv.org/abs/2509.24492