灾难性遗忘作为可访问性崩溃：持续学习中知识持久性的三层次框架
Catastrophic Forgetting as Accessibility Collapse: A Three-Level Framework for Knowledge Persistence in Continual Learning
AI总结：
本文提出一个三层次框架（知识存储、表示和可访问性），通过实验证明灾难性遗忘主要是可访问性失败而非表示擦除，重新训练分类器可恢复大部分性能。
摘要：
灾难性遗忘通常被解释为在顺序学习过程中先前获得的知识不可逆转地擦除。在这项工作中，我们研究了一种替代观点：遗忘可能并非源于任务表示的完全破坏，而是源于对保存信息的可访问性丧失。我们引入了一个三层次框架，将知识存储、表示和可访问性分开，并通过在ResNet-18上对顺序CIFAR-100分类进行的一系列持续学习实验来评估每个组件。我们的分析结合了检查点持久性、线性探测、表示几何、分类器重置恢复和逐层可恢复性实验。我们观察到早期任务的完全行为遗忘，任务准确率从54.8%下降到0%，而线性探测性能保留了大约76%的原始表示信息。此外，仅重新训练最终分类器就恢复了原始任务性能的75.7%，而无需修改骨干网络。逐层分析表明，早期和中间层保留了高度可恢复的任务信息，尽管后期阶段严重退化。投影能量和主角度分析表明，保留的知识以分布式高维表示的形式持续存在，而不是通过保留一个小的主导子空间。这些发现表明，灾难性遗忘更适合被描述为可访问性失败而非完全表示擦除，并且即使在功能遗忘发生后，大量任务相关信息仍嵌入在神经表示中。
英文摘要：
Catastrophic forgetting is commonly interpreted as the irreversible erasure of previously acquired knowledge during sequential learning. In this work, we investigate an alternative perspective: that forgetting may arise not from complete destruction of task representations but from a loss of accessibility to preserved information. We introduce a three-level framework separating knowledge storage, representation, and accessibility, and evaluate each component through a series of continual-learning experiments on sequential CIFAR-100 classification using ResNet-18. Our analysis combines checkpoint persistence, linear probing, representation geometry, classifier-reset recovery, and layer-wise recoverability experiments. We observe complete behavioral forgetting of earlier tasks, with task accuracy collapsing from 54.8% to 0%, while linear probe performance retains approximately 76% of the original representational information. Furthermore, retraining only the final classifier restores 75.7% of the original task performance without modifying the backbone network. Layer-wise analysis reveals that early and intermediate layers preserve highly recoverable task information despite severe degradation at later stages. Projection-energy and principal-angle analyses indicate that retained knowledge persists as distributed high-dimensional representations rather than through preservation of a small dominant subspace. These findings suggest that catastrophic forgetting is better characterized as an accessibility failure than complete representational erasure, and that substantial task-relevant information remains embedded within neural representations even after functional forgetting has occurred.
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。
