We introduce a new neural network-based continual learning algorithm, dubbed as Uncertainty-regularized Continual Learning (UCL), which builds on traditional Bayesian online learning framework with variational inference. We focus on two significant drawbacks of the recently proposed regularization-based methods: a) considerable additional memory cost for determining the per-weight regularization strengths and b) the absence of gracefully forgetting scheme, which can prevent performance degradation in learning new tasks. In this paper, we show UCL can solve these two problems by introducing a fresh interpretation on the Kullback-Leibler (KL) divergence term of the variational lower bound for Gaussian mean-field approximation. Based on the interpretation, we propose the notion of node-wise uncertainty, which drastically reduces the number of additional parameters for implementing per-weight regularization. Moreover, we devise two additional regularization terms that enforce \emph{stability} by freezing important parameters for past tasks and allow \emph{plasticity} by controlling the actively learning parameters for a new task. Through extensive experiments, we show UCL convincingly outperforms most of recent state-of-the-art baselines not only on popular supervised learning benchmarks, but also on challenging lifelong reinforcement learning tasks. The source code of our algorithm is available at https://github.com/csm9493/UCL.

Summary: The paper presents a regularization-based continual learning method, UCL, where during the training of the current task the parameters of the network are regularized based on their uncertainty in the previous tasks (less uncertainty means that a parameter is important and should not be altered in future tasks). Instead of measuring the uncertainty at the parameter level, as done in the earlier works (e.g.) Variational Continual Learning (VCL), the authors propose to measure uncertainty over the neurons resulting in less number of learnable parameters (mean and variances) to store. To compute the neurons uncertainty, UCL imposes a constraint that all the weights going into a neuron share the same/ common variance. To learn the parameters, a variational objective is used where the authors cleverly opened up the KL term in the ELBO and play with it to impose constraints on the variances of different neurons. The results are reported on MNIST benchmarks and RL tasks.

This paper proposed uncertainty-regularized continue learning (UCL) to address the challenge of catastrophe forgetting of neural networks. In detail, the method improves over variational continual learning (VCL) by modifying the KL regularizer in mean-field Gaussian prior/posterior setting. The approach is mainly justified by intuition explanation rather than theoretical/mathematical arguments. Experiments are performed on supervised continual learning benchmarks (split and permuted MNIST), and the method shows dominating performance over previous baselines (VCL, SI, EWC, HAT). Reviewers include experts in continual learning.

We introduce a new neural network-based continual learning algorithm, dubbed as Uncertainty-regularized Continual Learning (UCL), which builds on traditional Bayesian online learning framework with variational inference. We focus on two significant drawbacks of the recently proposed regularization-based methods: a) considerable additional memory cost for determining the per-weight regularization strengths and b) the absence of gracefully forgetting scheme, which can prevent performance degradation in learning new tasks. In this paper, we show UCL can solve these two problems by introducing a fresh interpretation on the Kullback-Leibler (KL) divergence term of the variational lower bound for Gaussian mean-field approximation. Based on the interpretation, we propose the notion of node-wise uncertainty, which drastically reduces the number of additional parameters for implementing per-weight regularization. Moreover, we devise two additional regularization terms that enforce \emph{stability} by freezing important parameters for past tasks and allow \emph{plasticity} by controlling the actively learning parameters for a new task.

We introduce a new neural network-based continual learning algorithm, dubbed as Uncertainty-regularized Continual Learning (UCL), which builds on traditional Bayesian online learning framework with variational inference. We focus on two significant drawbacks of the recently proposed regularization-based methods: a) considerable additional memory cost for determining the per-weight regularization strengths and b) the absence of gracefully forgetting scheme, which can prevent performance degradation in learning new tasks. In this paper, we show UCL can solve these two problems by introducing a fresh interpretation on the Kullback-Leibler (KL) divergence term of the variational lower bound for Gaussian mean-field approximation. Based on the interpretation, we propose the notion of node-wise uncertainty, which drastically reduces the number of additional parameters for implementing per-weight regularization. Moreover, we devise two additional regularization terms that enforce \emph{stability} by freezing important parameters for past tasks and allow \emph{plasticity} by controlling the actively learning parameters for a new task.