Bayesian Structure Adaptation for Continual Learning
This addresses the challenge of catastrophic forgetting in continual learning for AI systems, though it appears incremental by combining existing regularization and structure adaptation methods.
The paper tackles the problem of continual learning by proposing a Bayesian approach that adapts the structure of deep neural networks for each task, enabling inter-task transfer through overlapping sparse weight subsets. Experimental results show the model performs comparably or better than recent advances on supervised and unsupervised benchmarks.
Continual Learning is a learning paradigm where learning systems are trained with sequential or streaming tasks. Two notable directions among the recent advances in continual learning with neural networks are ($i$) variational Bayes based regularization by learning priors from previous tasks, and, ($ii$) learning the structure of deep networks to adapt to new tasks. So far, these two approaches have been orthogonal. We present a novel Bayesian approach to continual learning based on learning the structure of deep neural networks, addressing the shortcomings of both these approaches. The proposed model learns the deep structure for each task by learning which weights to be used, and supports inter-task transfer through the overlapping of different sparse subsets of weights learned by different tasks. Experimental results on supervised and unsupervised benchmarks shows that our model performs comparably or better than recent advances in continual learning setting.