Saved in:
Bibliographic Details
Main Authors: Pitsiorlas, Ioannis, Jamoussi, Nour, Kountouris, Marios
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.10677
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910947145154560
author Pitsiorlas, Ioannis
Jamoussi, Nour
Kountouris, Marios
author_facet Pitsiorlas, Ioannis
Jamoussi, Nour
Kountouris, Marios
contents This work introduces a novel methodology for assessing catastrophic forgetting (CF) in continual learning. We propose a new conformal prediction (CP)-based metric, termed the Conformal Prediction Confidence Factor (CPCF), to quantify and evaluate CF effectively. Our framework leverages adaptive CP to estimate forgetting by monitoring the model's confidence on previously learned tasks. This approach provides a dynamic and practical solution for monitoring and measuring CF of previous tasks as new ones are introduced, offering greater suitability for real-world applications. Experimental results on four benchmark datasets demonstrate a strong correlation between CPCF and the accuracy of previous tasks, validating the reliability and interpretability of the proposed metric. Our results highlight the potential of CPCF as a robust and effective tool for assessing and understanding CF in dynamic learning environments.
format Preprint
id arxiv_https___arxiv_org_abs_2505_10677
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Conformal Predictive Measure for Assessing Catastrophic Forgetting
Pitsiorlas, Ioannis
Jamoussi, Nour
Kountouris, Marios
Machine Learning
Artificial Intelligence
This work introduces a novel methodology for assessing catastrophic forgetting (CF) in continual learning. We propose a new conformal prediction (CP)-based metric, termed the Conformal Prediction Confidence Factor (CPCF), to quantify and evaluate CF effectively. Our framework leverages adaptive CP to estimate forgetting by monitoring the model's confidence on previously learned tasks. This approach provides a dynamic and practical solution for monitoring and measuring CF of previous tasks as new ones are introduced, offering greater suitability for real-world applications. Experimental results on four benchmark datasets demonstrate a strong correlation between CPCF and the accuracy of previous tasks, validating the reliability and interpretability of the proposed metric. Our results highlight the potential of CPCF as a robust and effective tool for assessing and understanding CF in dynamic learning environments.
title A Conformal Predictive Measure for Assessing Catastrophic Forgetting
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2505.10677