Logo image
Back
Explaining Robustness to Catastrophic Forgetting Through Incremental Concept Formation
Preprint   Open access

Explaining Robustness to Catastrophic Forgetting Through Incremental Concept Formation

Nicki Barari, Edward Kim and Christopher MacLellan
ArXiv.org
27 Oct 2025
DOI: https://doi.org/10.48550/arxiv.2510.23756
url
https://doi.org/10.48550/arXiv.2510.23756View
Preprint (Author's original)arXiv.org - Non-exclusive license to distribute,  Open

Abstract

Computer Science - Artificial Intelligence Computer Science - Learning
Catastrophic forgetting remains a central challenge in continual learning, where models are required to integrate new knowledge over time without losing what they have previously learned. In prior work, we introduced Cobweb/4V, a hierarchical concept formation model that exhibited robustness to catastrophic forgetting in visual domains. Motivated by this robustness, we examine three hypotheses regarding the factors that contribute to such stability: (1) adaptive structural reorganization enhances knowledge retention, (2) sparse and selective updates reduce interference, and (3) information-theoretic learning based on sufficiency statistics provides advantages over gradient-based backpropagation. To test these hypotheses, we compare Cobweb/4V with neural baselines, including CobwebNN, a neural implementation of the Cobweb framework introduced in this work. Experiments on datasets of varying complexity (MNIST, Fashion-MNIST, MedMNIST, and CIFAR-10) show that adaptive restructuring enhances learning plasticity, sparse updates help mitigate interference, and the information-theoretic learning process preserves prior knowledge without revisiting past data. Together, these findings provide insight into mechanisms that can mitigate catastrophic forgetting and highlight the potential of concept-based, information-theoretic approaches for building stable and adaptive continual learning systems.

Metrics

3 Record Views

Details

Logo image