AI RESEARCH
Online Continual Learning with Dynamic Label Hierarchies
arXiv CS.LG
•
ArXi:2605.11742v1 Announce Type: new Online Continual Learning (OCL) aims to learn from endless non\text{-}stationary data streams, yet most existing methods assume a flat label space and overlook the hierarchical organization of real\text{-}world concepts that evolves both horizontally (sibling classes) and vertically (coarse or fine categories). To better reflect this context, we