Spectral Collapse Drives Loss of Plasticity in Deep Continual Learning

Naicheng He, Kaicheng Guo, Arjun Prakash, Saket Tiwari, Tyrone Serapio, Ruo Yu Tao, Amy Greenwald, George Konidaris

Track: Research Track

Keywords: Continual Learning.+Lifelong Learning.+Plasticity.+Neural Networks

Abstract:

We investigate why deep neural networks suffer from loss of plasticity in deep continual learning, failing to learn new tasks without reinitializing parameters. We show that this failure is preceded by Hessian spectral collapse at new-task initialization, where meaningful curvature directions vanish and gradient descent becomes ineffective. To characterize the necessary condition for successful training, we introduce the notion of $\tau$-trainability and show that current plasticity preserving algorithms can be unified under this framework.
Targeting spectral collapse directly, we then discuss the Kronecker factored approximation of the Hessian, which motivates two regularization enhancements: maintaining high effective feature rank and applying L2 penalties. Experiments on continual supervised and reinforcement learning tasks confirm that combining these two regularizers effectively preserves plasticity.

Submission Number: 63