The Dual Nature of Plasticity Loss in Deep Continual Learning: Dissection and Mitigation
Haoyu Wang, Wei P Dai, Jiawei Zhang, Jialun Ma, Mingyi Huang, Yuguo Yu
Abstract
Loss of plasticity (LoP) is the primary cause of cognitive decline in normal aging brains next to cell loss. Recent works show that similar LoP also plagues neural networks during deep continual learning (DCL). While it has been shown that random perturbations of learned weights can alleviate LoP, its underlying mechanisms remain insufficiently understood. Here we offer a unique view of LoP and dissect its mechanisms through the lenses of an innovative framework combining the theory of neural collapse and finite-time Lyapunov exponents (FTLE) analysis. We show that LoP actually consists of two contrasting types: (i) type-1 LoP is characterized by highly negative FTLEs, where the network is prevented from learning due to the collapse of representations; (ii) while type-2 LoP is characterized by excessively positive FTLEs, where the network can train well but the growingly chaotic behaviors reduce its test accuracy. Based on these understandings, we introduce Generalized Mixup, designed to relax the representation space for prolonged DCL and demonstrate its superior efficacy vs. existing methods.
BibTeX
@inproceedings{
wang2025the,
title={The Dual Nature of Plasticity Loss in Deep Continual Learning: Dissection and Mitigation},
author={Haoyu Wang and Wei P Dai and Jiawei Zhang and Jialun Ma and Mingyi Huang and Yuguo Yu},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=vvD0Bre3Dk}
}