通过增量概念形成解释对灾难性遗忘的鲁棒性
Explaining Robustness to Catastrophic Forgetting Through Incremental Concept Formation
AI总结：
该研究针对持续学习中的灾难性遗忘问题，基于层级概念形成模型Cobweb/4V的鲁棒性检验三项稳定性假设，通过多数据集对比实验验证了自适应重组、稀疏更新及信息论学习的作用，为构建稳定自适应的持续学习系统提供新思路。
摘要：
灾难性遗忘仍是持续学习中的核心挑战，该场景要求模型随时间整合新知识的同时不丢失先前习得的内容。在前期工作中，我们提出了Cobweb/4V（一种层级概念形成模型），它在视觉领域展现出了抗灾难性遗忘的鲁棒性。受此鲁棒性启发，我们针对促成这种稳定性的因素检验了三项假设：（1）自适应结构重组可提升知识保留能力；（2）稀疏且选择性的更新可减少干扰；（3）基于充分统计量的信息论学习相比基于梯度的反向传播更具优势。为检验这些假设，我们将Cobweb/4V与多种神经基线模型进行对比，其中包括本研究提出的Cobweb框架的神经实现版本CobwebNN。在不同复杂度的数据集（MNIST、Fashion-MNIST、MedMNIST和CIFAR-10）上开展的实验表明，自适应重组可提升学习可塑性，稀疏更新有助于缓解干扰，且信息论学习过程无需回溯过往数据即可保留先验知识。综上，这些发现揭示了可缓解灾难性遗忘的机制，凸显了基于概念的信息论方法在构建稳定且自适应的持续学习系统方面的潜力。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
