Uncertainty-based Continual Learning for Neural Networks with Low-rank Variance Matrices
Xuan Rao, Bo Zhao, Derong Liu · 2024
Bayesian inference has provided the continual learning (CL) with an elegant framework where past experiences and new knowledge are consolidated into the posterior constantly. Typical approaches rely on Bayesian neural networks whose parameters are updated by variational inference, namely, maximizing the evidence lower bound of log-likelihood. In this paper, we discuss the effects of local reparameterization on the optimization of such networks in the context of CL. The empirical results show that it does not only increase the inference speed of neural networks, but also enhance the CL performance in some scenarios. Additionally, motivated by the observation that variance matrices have low-rank structures, we propose the d-tied variational continual learning (d-tied-VCL) to improve the parameter efficiency of variational continual learning (VCL). Experiments on random classification, per-muted MNIST, and split CIFAR100 show that even VCL with rank-1 variance matrices achieves competitive performance.