English

Can We Understand Plasticity Through Neural Collapse?

Machine Learning 2024-04-04 v1 Artificial Intelligence

Abstract

This paper explores the connection between two recently identified phenomena in deep learning: plasticity loss and neural collapse. We analyze their correlation in different scenarios, revealing a significant association during the initial training phase on the first task. Additionally, we introduce a regularization approach to mitigate neural collapse, demonstrating its effectiveness in alleviating plasticity loss in this specific setting.

Keywords

Cite

@article{arxiv.2404.02719,
  title  = {Can We Understand Plasticity Through Neural Collapse?},
  author = {Guglielmo Bonifazi and Iason Chalas and Gian Hess and Jakub Łucki},
  journal= {arXiv preprint arXiv:2404.02719},
  year   = {2024}
}
R2 v1 2026-06-28T15:42:59.952Z