{"ID":2849808,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.23756","arxiv_id":"2510.23756","title":"Explaining Robustness to Catastrophic Forgetting Through Incremental Concept Formation","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2510.23756","url_pdf":"https://arxiv.org/pdf/2510.23756v1","authors":"[\"Nicki Barari\",\"Edward Kim\",\"Christopher MacLellan\"]","published":"2025-10-27T18:41:25Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false}