丢失或隐藏？监督连续学习中的概念层面遗忘
Lost or Hidden? A Concept-Level Forgetting in Supervised Continual Learning
AI总结：
本文提出一种诊断框架，利用稀疏自编码器分析概念层面遗忘，发现遗忘主要源于表征可访问性变化而非信息擦除。
摘要：
持续学习研究模型如何在适应新任务的同时保留先前知识。尽管已有多种方法缓解灾难性遗忘，但该领域仍以性能为导向，缺乏对视觉模型表征空间中遗忘本质的理解。本文提出利用稀疏自编码器定义任务锚定的潜在特征空间，分析任务特定信息在更细粒度下的演变。我们分解遗忘为显性概念删除、可恢复性和解码性。结果显示，大量看似丢失的概念信息在线性假设下可恢复，而随着任务增加，概念解码性下降。总体而言，我们的发现表明，概念层面遗忘主要归因于表征可访问性变化而非完全信息擦除。
英文摘要：
Continual learning studies how models can adapt to new tasks while retaining previously acquired knowledge. Although a broad spectrum of methods has been proposed to mitigate catastrophic forgetting, the field remains predominantly performance-driven, with limited insight into what forgetting actually corresponds to within the vision model's representation space. Prior work has primarily analyzed forgetting through task-level performance or coarse measures of representational drift, without disentangling output-level accessibility from changes in finer-grained internal structure. To this end, we propose a diagnostic framework that leverages Sparse Autoencoders (SAEs) to define a task-anchored latent feature space, enabling analysis of how task-specific information evolves at a finer granularity, where individual SAE latents are treated as concept proxies for recurring and relatively disentangled visual patterns in the model's internal computations. Within this framework, we decompose forgetting into apparent concept deletion, recoverability, and decodability. We show that a large portion of seemingly lost concept-level information can often be recovered under linearity assumption, with concept decodability degrading as more tasks are introduced. Overall, our findings suggest that a significant part of concept-level forgetting can be attributed to changes in the representational accessibility rather than complete information erasure.
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。
