AI RESEARCH

Rethinking Continual Learning with Progressive Neural Collapse

arXiv CS.LG

ArXi:2505.24254v2 Announce Type: replace Continual Learning (CL) seeks to build an agent that can continuously learn a sequence of tasks, where a key challenge, namely Catastrophic Forgetting, persists due to the potential knowledge interference among different tasks. On the other hand, deep neural networks (DNNs) are shown to converge to a terminal state termed Neural Collapse during