Conference
Open access
Sep 2026
From Neural Collapse to Label-Limited Evolving Streams: Geometry-Constrained Learning Under Dynamic Class Imbalance
A novel framework named Neural collapse Inspired Label-limited Evolving stream learning (NILE), which exploits Neural Collapse geometry to explicitly construct a Simplex Equiangular Tight Frame (ETF) as a fixed classifier, ensuring maximal inter-class separability to guide feature discriminability.
Hong-Liang Wang, Hong-Yuan Liu, Qi-Rui Hao et al.
· Proceedings of the Thirty-Fi... · 0 citations